id
int64 0
17.2k
| year
int64 2k
2.02k
| title
stringlengths 7
208
| url
stringlengths 20
263
| text
stringlengths 852
324k
|
|---|---|---|---|---|
2,013 | 2,017 |
"Transcribing Audio Sucks—So Make Machines Like Trint Do It | WIRED"
|
"https://www.wired.com/2017/04/trint-multi-voice-transcription"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Jesse Jarnow Gear Transcribing Audio Sucks—So Make the Machines Do It Getty Images Save this story Save Save this story Save An unprecedented voice-transcription technology can tell you not only what's being said, but who is saying it.
The web app, named Trint , can listen to an audio recording or a video of two or more speakers (or just one) engaged in natural speech, then provide a written transcript of what was said. Unlike Siri or Google Talk, Trint is designed to transcribe long blocks of text.
While news organizations have invested heavily in video content, the ability to optimize those clips for search engines remains elusive.
Trint's technology is still nascent, but it could eventually give new life to vast swaths of non-text-based media on the internet, like videos and podcasts, by making them readable to both humans and search engines. People could read podcasts they lack the time or ability to listen to. YouTube videos could be indexed with a time-coded transcript, then searched for text terms. There are other applications too: Filmmakers could index their footage for better organization, and journalists, researchers, and lawyers could save the many hours it takes to transcribe long interviews.
As machine learning and automation technologies continue to transform the 21st century (and especially journalism), voice transcription remains a pesky speed bump. Transcription in particular is a technology that some have spent decades pursuing and others deemed outright impossible in our lifetimes. While news organizations and social media outlets alike have invested heavily in video content, the ability to optimize those clips for search engines remains elusive. And with younger readers still preferring print to video anyway, the value of transcribed text remains high.
Based in London and launched in autumn 2016, Trint is a web app built on two separate but entwined elements. The company's transcription algorithm feeds text into a browser interface for editing, which links the words in a transcript directly to the corresponding points in the recording. While the accuracy is hardly perfect (as Trint's founders are the first to admit), the system almost always produces a transcript that's clean enough for searching and editing. At roughly 25 cents per minute (or $15 per hour), Trint's software-as-service costs a quarter of the $1 per minute rate offered by competitors. There's a reason Trint is so cheap: Those other services, like Casting Words and 3Play, use humans to clean up automated transcripts or to do the actual transcribing. Trint is all machines.
Microsoft has released voice recognition toolkits for programmers to experiment with, and Google just last week added multi-voice recognition to its Google Home smart speaker. But Trint's software was among the first public-facing commercial product to serve this space. Other services offer variations. One called Pop Up Archive , which aims itself at podcasters looking to index their episodes for maximum SEO, has a similar interface, price, and level of accuracy as Trint. Built on Microsoft's API and lacking the editing interface, the mobile app BleuText transcribes directly from a phone's voice memo function. It's cheaper, though recording calls directly to a phone is another challenge.
1 According to lead engineer Simon Turvey, Trint users report an error rate of between five and 10 percent for cleanly recorded audio. Though this is close to the eight percent industry standard estimated last year by veteran Microsoft scientist Xuedong Huang, the Trint founders consider their product's editing function to be the feature that gives them a stronger competitive edge. Trint's time-coded transcript and the web-based editor allows users to quickly find and work on the quotes they need.
Putting on headphones and logging mind-numbing hours of transcription work has long been a thankless grunt job (and rite of initiation) at major news organizations. Anybody who has ever transcribed has almost surely wished for even a partial solution. Trint's team knows this pain.
"I've lived this problem and hated transcribing," says Trint CEO and co-founder Jeff Kofman, a veteran journalist with a career spanning three decades. "I figure I've spent thousands of hours of my life transcribing interviews and speeches and news conferences, searching through tapes." A Seemingly Simple Tweak Unlocks Google Home’s Full Potential Siri’s Not Even the Best iPhone Assistant Anymore Samsung’s Bixby Hopes the World Needs Another Voice Assistant Amazon Alexa Hits 10,000 Skills. Here Comes the Hard Part Gerald Friedland, director of the audio and multimedia lab at the International Computer Science Institute, was roundly impressed by the interface. Using a standard test from ICSI's Meeting Recorder Project , Friedland pushed Trint by feeding it a conversation recorded with an iPhone containing "overlap, laughter, emotions, and other things that occur in a meeting." Then he observed how accurately Trint maps the fragments of everyday human speech, if not all of the nuances. "Overall, I think it has a state-of-the-art performance with a nice interface," he says. "The issue is [that] a nice interface is really still needed as the transcription has to be heavily edited after the recognition." Though not yet able to fully differentiate between voices, and gumming up especially when two subjects speak at once, Trint did well while transcribing an interview I recorded in a noisy midtown Manhattan cafe. Another interview recording, conducted in a rock club with a band intermittently soundchecking in the background, likewise produced a workable transcript.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So A truer battle test for Trint, however, was provided by two of the most identifiable and infamously unintelligible voices of the past half-century: Keith Richards and the late Hunter S. Thompson. With whole chapters of Fear & Loathing in Las Vegas made up of transcribed field recordings of Thompson's 1971 Vegas rampage, it was left to a poor (but heroic) editorial assistant to turn the tapes into printed words. With Trint, Thompson might have found somebody else to terrorize.
Trint's transcription of a 1993 television conversation between Thompson and Keith Richards , however, read like somebody far more smashed than even Thompson. The software did surprisingly well with Richards' grizzled British accent, but the late gonzo journalist's half-mumbled word clusters seemed to break Trint's brain entirely. The app simply skipped the offending phrases when Thompson talked too fast, as he did most of the time.
Trint can currently understand 13 languages, including several varieties of English accents. Since it's a cloud-based application, Trint's voice transcription algorithm can be updated frequently to add new languages, new accents (Cuban-accented English is tough), and fresh batches of proper nouns.
But just as Trint might provide a solution to journalists, it could equally provide a technological home for isolated voice research projects without commercial outlets. Trint is partnering with one researcher to address diarization, the accurate identification of individual speakers. Turvey and his team also eventually see Trint being used by conferences, which can provide transcripts of all the presentations once an event is over. But the primary market, says Turvey, is still media organizations looking to make several generations of their unlogged video and audio instantly searchable.
"If we can deliver accurate raw text," he says, "then that becomes a platform upon which the semantic analysis, the sentiment analysis, the topic extraction---all of those things---can then be layered." Though Trint's founders are fond of deploying their brand's name as both a noun and a verb, many journalists---or anybody who's spent any time transcribing---might simply find it synonymous with "amazing." 1 Update on May 10, 2017: An addition was made to this story to include more information about companies and products competing with Trint in the voice-transcription space.
Topics algorithms computer science voice recognition Justin Pot Simon Hill Brenda Stolyar Simon Hill Julian Chokkattu David Nield Brenda Stolyar Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,014 | 2,021 |
"The iOS 15 Privacy Settings You Should Change Right Now | WIRED"
|
"https://www.wired.com/story/ios-15-privacy-settings-you-should-change-right-now"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Matt Burgess Security The iOS 15 Privacy Settings You Should Change Right Now As with any new software update, you should install iOS 15 as soon as possible.
Photograph: Apple Save this story Save Save this story Save Apple’s iOS 15 has dropped. The latest version of the mobile operating system and its iPad equivalent, iOS 15.5, are rolling out around the world. Apple made the download available after announcing the iPhone 13 at its annual hardware event last week.
This story originally appeared on WIRED UK.
Even before it was released, iOS 15 proved controversial. Apple’s child safety tools were intended to be included in this update but have been put on indefinite pause after a surveillance backlash. It’s the second year in a row that a key new feature is missing as the new version of iOS launches.
Apple’s iOS 14’s app tracking controls —that stop advertisers tracking you across your phone—were delayed until May 2021 and were included in iOS 14.5 after Facebook and other advertising firms complained about their impact.
But the complaints didn't stop Apple from introducing the changes.
Child safety tools aside, there are still plenty of new privacy and security features included with iOS 15. As with any new software update you should install the new system as soon as possible. Updates often include much more than new features, and they often squash new bugs and security vulnerabilities—a last-minute iOS 14.8 update , released just before Apple’s iPhone event, shows how important installing new software is.
While Apple has made iOS 15 available to download, it often takes a little while to roll out around the world, which means it might take slightly longer to reach some people than others. Here’s what you need to change when you get the update installed on your phone.
In iOS 14, Apple cleaned up app tracking.
This time around it’s the hidden trackers that are tucked away in the emails you’re sent that are being targeted. These trackers most often come in the format of pixels inserted into the body, header, or footer of emails which beam back information about you to the email sender.
Apple’s new Mail Privacy Protection stops email senders—most often those sending marketing emails and newsletters—from seeing your IP address and when you open the message. Instead, it will route your IP address through multiple proxy servers and randomly assign you another IP address. Mail Privacy Protection isn’t turned on by default, instead, you want to go to Settings , Mail , Privacy Protection and turn on the option for Protect Mail Activity.
Apple has added an App Privacy Report into the Privacy section of Settings in iOS 15—turn it on by tapping on Record App Activity and toggling the option to on. The privacy report gives you a quick glimpse of which of your phone’s sensors each app has used in the past seven days and the domains it has connected to over this time.
You’ll be able to see how many times an app has accessed your photos, camera, microphone, and contacts during the past week (if you have granted them permission to do so). This gives you the ability to check, for example, whether an app really does need to use your microphone to operate. If an app isn’t using the permissions you’ve granted it then it is probably worth turning them off, at least temporarily.
In September 2017, Apple introduced Intelligent Tracking Prevention for the Safari web browser as part of iOS 11. ITP is Safari’s way of blocking the online tracking that follows you around the web as you browse—Apple’s machine learning is used to find which domains track your browsing and then strip away the data that’s stored on people’s phones.
The technology has moved on in the past four years and with iOS 15 Apple is giving the option to hide your IP address from trackers. It means websites can’t turn your IP address into an identifier, which they can then use to connect all your browsing. To turn on IP address hiding, go to Settings , Safari , Hide IP Address and then turn on the toggle for Trackers and Websites.
One of the biggest things you can do to protect yourself from hacking is to turn on two-factor authentication for all your online accounts. Most often with two-factor authentication you’ll have to enter a code—often generated by an app or sent via SMS—alongside your password to access your account.
Codes sent via SMS aren’t as secure as those generated by an app. With iOS 15, Apple is introducing its own authenticator—meaning you don’t have to use an app from another company. This way you can, if you prefer, keep yourself locked inside Apple’s ecosystem. You can set up verification codes in Settings , Passwords.
They can then autofill when you sign in to a site using Safari.
Apple is bundling some of its more advanced privacy options with its iCloud+ subscription. As well as the bump in online storage available with iCloud+ there are also four privacy and security features that are reserved for those who pay. It’s the latest extension of Apple’s push into services.
First is Apple’s iCloud Private Relay—a VPN-like service that routes your web traffic through multiple servers and keeps your location private. Your web traffic is routed in two directions: this is to stop anyone, including Apple, from being able to work out what you’re looking at online. The first part involves servers owned by Apple encrypting the URLs you are visiting and then deleting information tied to it that could identify you. And at the same time another company—Apple says it is working with “trusted partners”—will assign a temporary IP address.
To turn on iCloud Private Relay, if you’re paying for iCloud+, visit Settings , tap on your name at the top of the screen, go to iCloud , Private Relay , and turn the option on. While it shares similar features with VPNs , the service isn’t exactly the same as it only works in Safari rather than across your entire device.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Also included in iCloud+ are Hide My Email , custom email domain options and HomeKit Secure Video.
The first of these generates random email addresses for the sites you want to sign up to but not have your personal details; the second allows you to personalize your iCloud email address with a custom domain name. Finally, the HomeKit changes let you store encrypted video footage in iCloud—though the feature was already available before the iCloud+ rebrand.
Since you’re already thinking about your iPhone’s privacy settings, it’s worth doing a quick review of the existing pre-iOS 15 options. It’s possible you’re sharing data with more apps and companies than you remember and there are some quick steps you can take to improve your on-device privacy.
Start by heading to Settings and then tapping on Privacy.
The first thing you want to do is check whether you have Location Services turned on. For the most privacy-preserving option, you can turn off Location Services completely. However, this may not be the most practical. There are plenty of reasons why you may want an app to know your location—such as a maps app being used to work out your travel direction, or your camera to log where photos are taken. Instead, location sharing settings can be changed for each individual app—options include never, ask next time the app is used, or while using the app.
While you’re in iOS’s Privacy section, tap Tracking.
This option will show you which apps want to track your behavior across other apps and allows you to turn tracking off. Use the toggle to deny apps the ability to ask you if you want to be tracked; all requests to track you will be denied.
Also in Privacy is the ability to see what apps have permission to access your contacts, calendars photos, Bluetooth, files, camera, microphone and other device sensors. Tap on each option to see what apps you have given each permission to and revoke the ones you don’t feel comfortable with.
This story originally appeared on WIRED UK.
📩 The latest on tech, science, and more: Get our newsletters ! Can robots evolve into machines of loving grace? 3D printing helps ultracold quantum experiments go small How community pharmacies stepped up during Covid The Artful Escape is psychedelic perfection How to send messages that automatically disappear 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 📱 Torn between the latest phones? Never fear—check out our iPhone buying guide and favorite Android phones Senior writer X Topics Wired UK ios privacy iPhone encryption apple Reece Rogers Matt Burgess Kate O'Flaherty Lily Hay Newman Reece Rogers K.G. Orphanides Lily Hay Newman Lily Hay Newman Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,015 | 2,021 |
"8 Useful iPhone Tips for Ex-Android Users | WIRED"
|
"https://www.wired.com/story/8-iphone-tips-android-switch"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Lisa Niver Gear 8 Useful iPhone Tips for Ex-Android Users Photograph: Getty Images Save this story Save Save this story Save Seven years ago, working on a video web series shot in Puerto Rico, the director told me they liked the footage I'd shot on my smartphone. The problem was I could not figure out how to get it off the phone. My devices—an Android phone and an Apple laptop—were in a fight, just like my marriage. I thought, “Can’t everyone just get along?” But no, it doesn’t work that way.
I had to use a software bridge to transfer between the phone and the computer, and every time there was an upgrade on either side, the transition became uncertain. I used Commander One , Android Transfer , anything I could find. Nothing worked consistently, especially with large video files. My cohost asked me, “Why are you living in two universes?” While I thought he was referring to the fact that I had recently left my husband on another continent, he actually meant: Why did I have a Nokia phone and a MacBook Air? Shortly after that film shoot, I ditched my husband for good, but I went on to have seven LG phones, as their cameras and video quality kept improving. On any group trip, everyone would agree to let me take the pictures because my camera was just better. It seemed worth the struggle to keep the dual status because the image quality was far superior.
Early in the pandemic, a film director for the Discovery Channel told me he had switched to the iPhone12 Pro Max. Shortly after, LG announced it was leaving the phone business. I asked myself, “What could make my life easier?” and went to Costco to get a new phone. I knew that swapping would have challenges, but I told myself Costco always takes things back and walked out with a new iPhone 12 Pro Max.
My iPhone friends said, “Welcome to the Dark Side” as they anxiously waited for my chat bubbles to change from green to blue. I was a rookie, and it felt like a rocky new relationship at first, but eventually I found my bearings. Here are some of my favorite features and a few cool tricks for Android users making the switch—some of which have even made friends who are loyal iPhone users say, “How do I do that?” My main goal was to have my photos appear on my laptop easily, instead of struggling to move them over from Android. Initially I needed some help with this, so I made an online appointment to speak to Apple Tech Support, and after some back and forth, my devices were able to speak to each other. Tech support helped me redirect the photo library. To work with my photos, all I do now is select a group of photos, create a new album, and Airdrop them from my phone to my desktop. The photos are also in the Photos app on my laptop and backed up immediately in iCloud.
When I make movies from an adventure, like my recent excursion with bears in Ketchikan, Alaska, I can move the videos from the desktop into iMovie, and it is seamless, painless, and so much easier than it used to be.
Good news: An iPhone can make you feel younger. My doctor takes her reading glasses everywhere, and it makes her feel old. With one step, I taught her to turn on Magnifier.
In your iPhone or iPad, go to Settings > Accessibility.
Tap Magnifier , then turn it on. Now tap the button on the right side of the phone three times and the powerful magnifier will open. My doctor can ditch the reading glasses at the market or on a date because she already has her phone. She has had an iPhone for 14 years but never knew it could help her read small print. With Android, you need to download a special app, and while there are plenty to choose from, it’s nice having the feature baked into your phone.
Screen Record, as its name implies, allows you to record a video of your screen. To do so, swipe diagonally down from the upper right corner to get to the control center and then press the screen record button. It will give you a countdown of 3 before it starts, so make sure you are open to what you want to record BEFORE you press the button.
When I wrote a Thrive Global article about brand expert Aliza Licht, she made a video of the article and tweeted it.
When I asked her how to do it, she said, “You need an iPhone!” Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So X content This content can also be viewed on the site it originates from.
On Android, the screenshot function used a combination of pressing buttons on the sides. Whatever the combo is meant to be on the iPhone, I just could not make it work (Ed. Note: It’s supposed to be the Sleep/Wake button and Volume up , but it depends on the model of iPhone you have!) Then I figured out I could use the back tap, which is easier than the actual button combo. To set it up, go to Settings > Accessibility > Touch , and tap Back Tap.
I use double-tap for screenshots. You can pick the action you want from the many choices, and there is an option for both double- and triple-tap. Sometimes I accidentally get a photo because the phone thinks I tapped it when I set it down or it hits something, but those mistakes are easy to delete, and I really like to take screenshots, so it works for me.
One friend called me and said, “Now that you have an iPhone, can you teach me how to add a custom ringtone?” She'd had an iPhone for more than a decade and never figured it out. For your general phone ringtone, go to Settings > Sounds & Haptics > Ringtone > and select a ringtone or download one you have purchased from the Tone Store.
If you want to have a special ring for a contact, open the Contacts app > select a contact, tap Edit , tap Ringtone , then choose a ringtone for that person. I set my dad’s phone to ring like the opening music from his all-time favorite TV show, 24.
You can have a different ring for your boss, spouse, child, or best friend.
When I was meeting a friend in a crowded park for a walk, I dropped a pin in Maps to indicate where I was waiting. She then followed the pin and was able to park her car next to me. You can follow these steps like your own Yellow Brick Road: Open the Apple Maps app, click on the Blue dot (which is where you are), and then click on the blue Share my location button to send the pin to anyone by iMessage or Airdrop. You can do the same in Google Maps, but it requires a few extra hoops to share your location.
Have you always wanted to be a cartoon character? Press the A button on the left of the text message box and then click on the Brown button with the yellow parentheses to create your Memoji, an avatar that looks, sounds, and moves like you. You can even animate your face. Personally, I made my skin blue so I look like an actual character from the movie Avatar.
It makes me laugh every time I see it! You can also send messages in iMessage with invisible ink, which looks like shifting sand. Your recipient then has to rub their finger over the message for the ink to appear, but it's even better if you are sending a photo and do not want anyone looking over someone’s shoulder to see it. There are also sound effects, such as “slam,” “loud,” and “gentle,” and screen effects like balloons, confetti, spotlight, laser, and fireworks. These are accessed by holding down the blue arrow at the end of a text message prior to sending.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lisa Niver's custom-made blue memoji, on her brand new iPhone.
Courtesy Lisa Niver After a few months, I finally feel like I have nearly earned my Apple Girl Scout badge or travel visa for the land of iPhone. It was a bumpy beginning, but I am confident that I will learn more tips and tricks with time. For me, it is better to be all in one universe.
📩 The latest on tech, science, and more: Get our newsletters ! Is Becky Chambers the ultimate hope for science fiction? An excerpt from The Every, Dave Eggers' new novel Why James Bond doesn't use an iPhone The time to buy your holiday presents now Religious exemptions for vaccine mandates shouldn't exist 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers Contributor X Instagram Topics iPhone how-to tips ios phones Android Reece Rogers Scott Gilbertson Scott Gilbertson Carlton Reid Boone Ashworth Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,016 | 2,022 |
"A New EU Law Would Force iPhones to Adopt USB-C Charging | WIRED"
|
"https://www.wired.com/story/eu-law-usb-c-iphones-lightning"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Boone Ashworth Gear A New EU Law Would Force iPhones to Adopt USB-C Charging Photograph: Iaroslav Bushuev/Getty Images Save this story Save Save this story Save The age of the Lightning cable is coming to an end. This week, the European Union passed legislation requiring all phones, tablets, and cameras sold in the EU to come with a USB-C connector. It’s a big move that spells doom for Apple’s proprietary port; most phones sold around the world charge and connect to accessories using the USB-C standard, but iPhones do not.
The EU legislation was first proposed in September 2021 after the European Parliament said it had spent years trying to get companies to voluntarily agree to rely on one type of connector. USB-C, with its fast charging time and speedy data transfer speeds, emerged as the best option for consumers. Plus, if every device in one’s home uses the same charging standard, it reduces waste and increases convenience. Now, the switch to USB-C across the board has officially been approved. The parliament voted overwhelmingly in favor of the change, with 602 votes for and only 13 against.
One of the biggest companies to be affected here is Apple. The ruling all but spells the end for the iPhone’s Lightning charger, as it would likely be unviable for Apple to produce devices with separate ports for different geographical regions on such a large scale.
But this won’t exactly be a shock for Apple. Last year, an EU ruling to enhance repairability of devices likely prompted Apple and other companies to establish their own repair programs in the US. Apple seems to have already prepared for this action, considering it has reportedly been testing iPhones with USB-C chargers.
The USB-C requirements are expected to go into effect by the end of 2024. Starting in 2026, the requirement will also apply to laptops. Devices that charge wirelessly do not yet have to adhere to any specific standard, but most (including iPhones) are already compatible with the Qi charging system.
Here’s this week’s other news in the world of consumer tech.
The insurance company State Farm is suing Rad Power Bikes after it says it had to shell out $250,000 to a client whose ebike caught on fire.
Ebikes have been under increased scrutiny lately because of safety issues. The rapid growth of the electric micromobility market, coupled with the proliferation of poor quality parts and the fact that frame-mounted batteries are susceptible to damage, has led to an increase in the number of fires from the bike’s power cells.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So This also isn’t the only lawsuit Rad Power Bikes is facing over safety issues. In 2021, a 12-year-old died while riding a Rad Power bike, though the cause of the fatal crash wasn’t a battery problem or a manufacturer defect. The parents say that Rad Power’s marketing led the child to go too fast on the motor-powered bike, leading to her crash. Both cases have yet to be decided.
Remember the Amazon Glow? No? Well, that probably makes sense. The underperforming video chat device made for children was less than a year old, and now it is no more. As reported by Gizmodo , Amazon discontinued production of the Glow this week.
The Glow looked like a clunkier version of Facebook’s Portal webcam/stationary tablet screen, and could play videos, display ebooks, and make video calls. But while the Portal is a sleek picture frame-sized device, the Glow was a chunky, unappealing block. It was intended primarily for families with kids, but wound up being a device for no one.
Also on the chopping block this week at Amazon: Scout , the four-wheeled home delivery robot. Bummer, I was thinking about having a Glow delivered via robot. Hmm.
There’s been a surge in unionizing efforts across the US over the past couple years. Workers at companies like Apple, Amazon, Google, and Starbucks have voted to unionize their workplaces to secure more rights and better pay. Of course, some of those companies are pushing back.
In June, Apple employees at a store in Maryland voted to become the first Apple store to unionize.
Since then, Apple has reportedly engaged in union-busting efforts in some of its stores. Now, the US National Labor Relations Board (NLRB) has filed an official complaint against the tech giant.
The NLRB complaint focuses on one store in New York. It claims Apple discriminated against employees there who supported unionizing, and stopped them from putting pro-union flyers in the break room. The case is set to go to a hearing with the NLRB on December 23.
Next week, employees at an Apple store in Oklahoma City will vote on whether to unionize. The Communications Workers of America, the union group that represents the pro-union employees, has also filed a complaint that Apple has threatened workers there too.
Google announced its new Pixel 7 phone line this week. The devices have new chips and some advances in camera technology. Google also finally unveiled the long anticipated Pixel Watch after years of speculation. It’s a pretty, shiny wearable, albeit one that feels like it is trying to play catchup with the Apple Watch and other smartwatches out there.
This week on Gadget Lab , WIRED reviews editor Julian Chokkattu walks listeners through all the new stuff Google announced this week, and whether the company will actually be able to compete in the smartwatch arena.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Staff Writer X Topics apple iPhone Labor electric bikes Amazon Boone Ashworth Boone Ashworth Simon Hill Reece Rogers Julian Chokkattu Nena Farrell Brenda Stolyar Saira Mueller WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,017 | 2,015 |
"Why the MacBook's New USB-C Is the Port of the Future | WIRED"
|
"https://www.wired.com/2015/03/usb-type-c-faq"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Christina Bonnington Gear Why the MacBook's New USB-C Is the Port of the Future The new USB-C port is reversible, and it handles power, HDMI, and data transport.
Apple Save this story Save Save this story Save Yesterday, Apple showed off the MacBook, a new laptop notable for its thinness, its gold coloring, and most surprisingly, the absence of all but one solitary port. It's called USB Type-C, and it's going to transform gadgets as we know them.
Envisioning a future of laptops with just one input---aside from the headphone jack---is like entering an aquarium full of single-tentacled octopi. It's unsettling. How do I charge it? Where does my SD card go? Why can't I hook my computer up to more than two things at once? These are all fair questions, but they can all find an answer in USB Type-C (or USB-C for short). Here's a quick rundown of what you need to know.
A USB-C plug is slender, about the same size as a micro-USB (8.4mm by 2.6mm), but it's reversible. Like Apple's Lightning connector, upside down and right-side up are one and the same. So if you're plugging in your MacBook in the dark, there's no need to futz and fiddle to figure out which way it needs to be plugged in.
It's like a USB on steroids. First off, charging: USB-C can deliver bi-directional power. It can be used to charge a host device, or it can allow the host device to charge a peripheral. It can handle large loads too, delivering up to 20V at 5A (100W). That's more than enough to charge up a notebook, or multiple mobile devices simultaneously.
USB-C is also faster than our current USB-B standard. Data transfers can run at rates up to 10 Gbps, but it's backwards compatible with older USB standards, as long as you have an adapter. Right now, our fastest USB Type B devices transfer data at half that speed.
If you want to nerd out on some more details about USB-C, Ars Technica has more information.
For that, you'll need an adapter, and Apple has a number of options already available: USB-C to USB ($19), USB-C to HDMI, and USB to VGA (both $79). DisplayPort, gigabit Ethernet, SD card adapters, and other connector standards should arrive soon, both from Apple and from third parties.
However, Apple is betting that in the future, you'll have fewer and fewer things you actually need to plug into your computer, thanks to the proliferation of wireless, Bluetooth and Wi-Fi-connected devices.
Wireless headphones are actually worth listening to now, wireless speakers abound, and for things like wearables, you'll likely just leave the charger next to your bed or at your desk.
Regardless of your opinion of the company or its products, USB-C is not another proprietary connector from Apple. It's a new, industry-wide standard, and we should be seeing devices from all sorts of different manufacturers using USB-C in the not-too-distant future. Apple's new MacBook is the first consumer notebook to embrace USB-C.
Yes! Sandisk makes a 32 GB flash drive with a Type C connector, and Lacie's Porsche Design Mobile Drive now comes with a USB-C connector as well. It comes in 500GB, 1TB, or 2TB variants.
The recently announced Nokia N1 also features a Type C connector, however, Nokia's implementation sticks with the current 5Mbps speed standard of USB-B devices.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Topics accessories apple peripherals USB Brenda Stolyar Scott Gilbertson Brenda Stolyar Brenda Stolyar Brendan Nystedt Nena Farrell Jaina Grey Brenda Stolyar WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,018 | 2,015 |
"Life With the MacBook's Single Port Won't Be Easy—Yet | WIRED"
|
"https://www.wired.com/2015/03/life-macbooks-single-port-wont-easyyet"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Tim Moynihan Gear Life With the MacBook's Single Port Won't Be Easy—Yet Apple is betting that a single USB-C port will be enough for most casual users---exactly who the new MacBook is geared toward.
Apple Save this story Save Save this story Save Apple has a history of “addition by subtraction” when it comes to ports and drives. It has over the years ditched FireWire, Ethernet, and optical drives. Now, with the MacBook , it says goodbye to all but a lone pioneering port.
This probably was inevitable. So just how big of an adjustment are you in for? Bigger than you might realize. At least for now.
How we push data to and from our machines constantly evolves thanks to the steady progress of new standards, faster wireless connectivity, streaming services, and the cloud. Apple tends to anticipate these changes---and in some cases force the issue, often being among the first to banish old-guard tech from its devices. It’s been a successful strategy; just ask any phone with a physical keyboard.
But the new ultraportable MacBook doesn’t just nip an optical drive here and a FireWire port there. It cleans house. And while we’re accustomed to hermetically sealed, port-barren devices in our pockets and on our coffee tables, a laptop with plenty of connectivity options is part of what makes minimalism possible elsewhere. With the new MacBook, your “plug and play” options are a 3.5mm headphone port and a USB-C port---a standard that isn’t exactly swimming in compatible components just yet.
The good news is that USB-C is versatile. It’s a standard that, unlike the stalled Thunderbolt interface, will be embraced by many devices and peripherals that don’t originate in Cupertino. It’s capable, too; the port on the new MacBook can shuttle data at 5Gbps, it can charge and be charged by whatever it’s hooked up to, it supports video out, and it's tiny. The only bad news about the shift to USB-C ports is the MacBook has one of them.
Of course, there are ways to compensate, though not as many as you might think. The cheapest, most direct way to get your USB devices to play nice with a USB-C port is a $19 USB-to-USB-C adapter from Apple (or this $13 model from Google , whose Chromebook Pixel features two USB-C ports). That’s a good start, but it still limits your choices to hooking up a single device or charging your laptop.
USB-C Digital AV Multiport Adapter.
Apple Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft For those who need more I/O in their lives, Apple now sells its own USB-C adapters that let you turn that single port into a three-headed hydra supporting HDMI-out, full-size USB 3.1, and a passthrough for power. Another version swaps the HDMI-out port for VGA-out.
They cost $79. Each. That’s more than an Apple TV.
And even those pricey dongles don’t come close to replicating the ports on a MacBook Air or MacBook Pro. The 13-inch Air has a dedicated power connector, a Thunderbolt 2 port, an SDXC card slot, two USB 3.0 ports, and a headphone jack. The 13-inch MacBook Pro has all of that, plus an additional Thunderbolt 2 port and HDMI-out.
Apple’s message is clear: You don't need all those cables. It’s better to carry something that feels almost weightless, something elegant and slim and gold than have some pört-gåsbord weighing you down. "Besides," Apple seems to insist, "you can address all of your needs via Web services, or streaming, or iCloud, or one of the wonderful new features we've added to Yosemite. Would you like more ports? Well, we have inelegant dongles and more-expensive computers for that." At some point, getting data and electricity to and from your MacBook with just one port may be seamless and natural. Today, though, we’re at least a few dongles away. Here’s how the MacBook plays out in practice.
If you use an iPhone for most photos and directly upload your shots to your iCloud photo library (or the cloud service of your choice), you’re set. But if you use one of those old-school “standalone” cameras and one of those dinosaur “SD” or “CompactFlash” cards, you’ll need to wait until somebody makes a card-to-USB-C adapter to get much use out of the MacBook. In the meantime, you could plug a USB card reader into a $13 or $19 or $79 adapter.
Potentially easing the frustration is the fact that most modern cameras have built-in Wi-Fi features, so you can hypothetically leave your card in your camera, beam photos to your phone or a cloud service, and use it as a passthrough to your computer’s hard drive. That sort of set-up would be basically unworkable for pro photographers shuttling RAW files, though, and probably more trouble than it's worth even when dealing with JPEG files in any quantity.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft The same solutions and limitations apply to video editors. Videos taken with an iPhone can be magically ported to the machine via iCloud, Dropbox, or most other cloud services of your choice, so that’s easy enough. USB-C can handle video files zipping back and forth (through an adapter or new cable, for now). Other wireless transfer options aren't very practical for files of the sizes you'll be dealing with. The most likely setup for a wired-in connection will be a USB 3.0 or 3.1 cable running from a video-capture device through a dongle.
Your USB-C external hard drive options are non-existent right now, but help is on the way. This summer, SanDisk will offer a 32GB thumbdrive with USB-C and full-size USB connectors. A LaCie external drive will offer up to 2TB of portable USB-C-connected storage when it's out later this year. End of list so far. But now that there’s a demand, the USB-C drive market will grow. You’ll have plenty of options if you hold out a few months.
Meanwhile, the new MacBook will come with up to 512GB onboard, and cloud-storage services abound these days. That could be enough for most people, but anyone who's been stashing years of valuable files and photos and music on an external drive would be inconvenienced by a MacBook today. To get the important stuff from there to your new machine, for the time being you’ll need an adapter.
While Apple already phased out Ethernet ports across its laptop lineup, there are a few cases in which having one generally comes in handy. If you’re dealing with crappy Wi-Fi service or that odd hotel that only offers jacked-in connectivity, yes, you’ll need a adapter for that.
Belkin already has announced a USB-C-to-Gigabit-Ethernet adapter , but the pricing and release date are still a mystery.
Anyone who uses a laptop as a mobile machine and the docked guts of their home/office scenario will absolutely need to fork over for a dongle or avoid the new MacBook altogether. For now, at least.
Multi-port docks for the MacBook are likely on the way, but without that $79 add-on you won’t be able to simultaneously charge your laptop and work on a bigger screen or use a dual-monitor display. Or use a non-Bluetooth keyboard or mouse when your single port is occupied.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft What may be the strangest USB-C fallout? If you want to mirror your laptop screen on your television, your cheapest and best option at this point is to buy an Apple TV. It costs $69 and supports AirPlay mirroring, while Apple's HDMI-out multi-dongle will cost you $10 more.
Curiously---and this is bound to change soon---there doesn't seem to be a way to charge your iPhone or Pad with the new MacBook without using an adapter. Apple hasn't yet officially announced a Lightning-to-USB-C cable. For all we know, one may come in the MacBook box. Otherwise, for a wired connection, you’d have to use a dongle, plug the fat end of your Lightning cable into that, and charge or sync an iOS device with a cumbersome setup.
There’s a reason, though, that Apple has put concerted effort in making Yosemite interact with iOS devices in wireless ways: Continuity, Handoff, and AirDrop are all geared toward seamless interoperability between its mobile and desktop OS, no literal strings attached. And here's the big thing on the horizon: Future iOS devices will likely use USB-C as their one and only port, which will be an instant fix. Until then, you'll need an adapter or an as-yet-unannounced cable to charge your iDevice from a MacBook.
Here's a fun resulting fact. As of right now, it will be easier to charge an Android device with an Apple computer than to charge an iPhone or iPad with one---just as long as you have this upcoming $20 Belkin cable.
Again, USB-C is a standard, and it's one that will show up on many other devices, too , so don't expect this to be an issue for long.
In many ways, this new MacBook is an exciting harbinger of a bright future, one teeming with interoperability and free of proprietary connectors. We’re not quite there yet, though. And until we are, it's going to be a long, dongle-paved road.
Contributing Writer X Instagram Topics apple Mac peripherals USB Brenda Stolyar Brenda Stolyar Brendan Nystedt Scott Gilbertson Eric Ravenscraft Scott Gilbertson Brenda Stolyar Nena Farrell WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,019 | 2,022 |
"Valve Steam Deck Review: Glitchy but Promising | WIRED"
|
"https://www.wired.com/review/valve-steam-deck"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Saira Mueller Gear Review: Valve Steam Deck Facebook X Email Save Story Photograph: Valve Facebook X Email Save Story $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 5/10 Open rating explainer I've been playing PC games since I was a kid—I remember trying SkiFree on my mom’s desktop when I was too sick to go to school. Since then, I've amassed a vast library of games on Steam, the platform created by Valve; it's how most people play games on their computers. (Valve is also the creator of hits like Half-Life and Portal.
) I was intrigued when Valve announced the Steam Deck last year , a handheld portable gaming console that lets you play your PC games anywhere. It's the potential kick I needed to get through my ever expanding Steam backlog.
Well, I've been using the Steam Deck for several weeks, playing AAA and indie games on my couch, in bed, while sitting on an office chair, in my car, at a café, and on a plane. Some of my fears when I first heard about the gadget were validated—it's bulky, and the layout of the controls isn't very ergonomic, attributes you don't really want in a handheld console.
It also feels like Valve could've used a few more weeks (months?) to polish the software experience. (The Deck was supposed to launch back in December, so it's already been delayed once.) This console has been in development for four years, through a pandemic, so it's not surprising to see last-minute issues to correct. But since I received it, Valve has pushed system updates every single day—meaning I've had to retest certain functions over and over again. Valve says it will continue pushing out frequent updates to squash bugs after launch.
That's both good and bad. It means the software needs more work, but it also shows how committed Valve is to the Steam Deck. I'm glad to see it, because this thing has a ton of potential.
Photograph: Valve I received the top-end Steam Deck that retails for $649, which includes a 512-gigabyte solid-state drive. You can pay as little as $399 for the Deck, but you'll only get a paltry 64 GB of storage. Considering that AAA games are 50 to 70 GB these days, if not more, you'll probably want to pay up for the 256-GB version ($529) at the very least.
That said, the MicroSD card slot is hands down my favorite feature. You can hot-swap in MicroSDs once they're properly formatted to jump in and play a different game, essentially giving the Deck a whole lot more storage. I purchased a 1-terabyte SanDisk Ultra MicroSD card , and it holds all 41 games I wanted to download, including Mass Effect Legendary Edition (110 GB), ARK: Survival Evolved (101 GB), Destiny 2 (74 GB), Cyberpunk 2077 (67 GB), and Death Stranding (64 GB).
The load speed difference between the internal SSD and the MicroSD is minimal— Death Stranding took about 19 seconds to load up on the SSD and 30 seconds on the MicroSD, though this does fluctuate. So far I haven’t noticed any major differences. I also tried this with 32-GB and 256-GB SanDisk Extreme MicroSD cards, and the results were no different. If you're worried about Valve's low storage options, MicroSD cards will have your back.
This Steam Deck is bulky, but not as heavy as I had imagined nor as uncomfortable to hold. It weighs 672 grams; for reference, the Nintendo Switch OLED is 436 grams, and the iPhone 13 is 174 grams. Much of this weight sits on each side of the console, which is curved at the back to fit more comfortably in your hands. It feels weird to hold such a wide handheld (12 inches compared to the 9-inch-long Switch), but you get used to it. Literally. The first time I played for an hour straight, my right hand went numb. I now mix in a few breaks and stretch my hands out regularly and it hasn’t happened since.
My biggest concern was the layout of the buttons, especially since you can't detach the controllers like you can on the Switch. Unlike most controllers, where the buttons and thumb sticks sit on a diagonal—a design iterated on over decades of testing to reduce strain—the Deck’s D-pad and ABXY buttons sit horizontally next to their respective thumb stick. They're quite high up to make room for two trackpads on each side of the console. There are also triggers on the console's shoulders and paddles on the back, which feel great and remind me of the Xbox Elite controller.
Valve Steam Deck Rating: 5/10 $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Photograph: Valve I didn't have trouble with the buttons or the D-pad, and switching between them and the thumb stick was fine. I did feel my thumbs straining to reach the thumb sticks themselves. As for the trackpads, I found myself relying on the touchscreen a whole lot more instead (especially for typing in passwords), as they can be difficult to use when you're trying to click on something small.
The Switch's kickstand has spoiled me—there is no built-in kickstand here. So if you pair third-party Bluetooth controllers to the console, and you might want to, you'll need to buy your own accessory to keep the screen propped up. Valve has a dock (pictured above) with additional ports for connecting Ethernet or hooking it up to your TV, but it's not available yet.
Speaking of the Switch: Because its charging port is on the bottom, it's hard to charge and keep it upright at the same time. The Steam Deck has a different problem. The USB-C charging port is off-center on the top, and the cable tends to get in the way, interfering with my access to the paddles and the ABXY buttons. It's a bit annoying, so you'll need to orient yourself a certain way based on where your outlet is (unless you use a portable battery ).
Connecting the Deck to an external device is easy enough if it uses a USB-C cable or has Bluetooth; otherwise you’ll need an adapter. For example, I connected my Xbox controller just fine, but I had to buy a USB-C to HDMI adapter to plug the console into my 4K TV and computer monitor. (It worked seamlessly with both.) The Deck will run at the external display's resolution, but Valve says it has "some work to do in having the Steam Deck UI handle the resolution change gracefully.” I noticed that as Death Stranding added black bars on all four sides of my TV. The graphics, which look pretty great in handheld mode, don't look as sharp on the big screen though, and I didn't see any options to tweak graphics settings.
Valve Steam Deck Rating: 5/10 $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Photograph: Valve After an hour or more of nonstop gaming, the Deck got hot on the top edge where the fan is, but since you never have to touch this area, it's not really an issue. As for noise, let's just say it's a little quieter than a MacBook under load (not those new fan-less Macs ), though it depends on the game.
Death Stranding made those fans run louder than Townscaper.
That brings us to battery life, one of the Steam Deck's biggest weaknesses. Running it off the 40-watt-hour battery is a race against time. An hour-long play session of Subnautica and Death Stranding caused the Deck to lose 10 percent every 10 minutes. This was while it was in airplane mode, with volume levels at 50 percent and screen brightness at 25 percent. You’ll likely get around an hour and 40 minutes of playing time before the thing dies. For a portable gaming device meant to be used on the go, this is not great.
The Steam Deck’s operating system has been its next biggest flaw. The good news is it’s something that can be fixed—and Valve is working on it. Several problems I ran into have already been patched, but considering the sheer number of bugs I've seen, there's a good chance you'll run into your fair share.
Photograph: Valve Valve Steam Deck Rating: 5/10 $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED After six days with the Deck, it got caught in a startup bug loop that required a full factory reset. I didn’t have the necessary accessories on hand, so I bought a USB stick and USB-C hub to plug the drive and a keyboard into the Deck. I had to use my PC to create a bootable flash drive with the recovery image on it. This process took about 15 minutes (excluding the time I had to wait for those accessories to arrive). Valve developers assured me this is a rare bug and it has since been fixed, but if it does happen again, Valve says it's working on a “smoother, more user-friendly flow for re-imaging” to fix it.
Using the Steam Deck in desktop mode also requires a bit of tech-savviness. This is useful as it lets you run games that have third-party launchers unavailable on Linux, like Blizzard's launcher, Microsoft’s Game Pass for PC, and EA's Origin, but you'll want to install Windows first. For this, you’ll need a bootable drive or MicroSD with Windows on it plus a keyboard to connect to the Deck. The whole process, for someone who isn’t adept at Linux or writing bootable drives, can be overwhelming.
The 1,280 x 800-pixel-resolution LCD screen itself is fine. It's no Switch OLED, but it gets quite bright, so I often leave it pretty dim. However, PC games are designed for large screens, typically 13 inches or more. Switching to a 7-inch screen doesn't always lead to the best experience. Not to mention the shift from keyboard and mouse controls to the D-pad, ABXY buttons, trackpads, thumb sticks, triggers, grip buttons, gyro, and touchscreen—it can all feel a little clunky and overwhelming.
The upside is the ability to remap the controls to suit your own preferences or input an external device—like Xbox’s Adaptive controller —if the existing controls or layout don’t feel comfortable. People with visual accessibility issues, however, may have problems seeing small text on the Deck. I'm slightly nearsighted and had trouble seeing certain markers in Death Stranding.
You technically have access to the more than 60,000 titles in Steam's marketplace, but many games are not going to have optimal performance on the Steam Deck for some time. To help players find optimized games, Valve has a Deck Verified program.
This is essentially a marker Valve doles out after testing a game on the Deck. There are four markers: Verified, which means it “works great on Steam Deck, right out of the box"; Playable, where some things work and others may require some tweaking to make it playable; Unsupported, where the game is “not functional” on the Deck currently; and Unknown, which means Valve has yet to check the game’s Deck compatibility. At the moment, most games fall into that latter category.
Courtesy of Valve Valve Steam Deck Rating: 5/10 $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED I’ve played titles in the Verified, Playable, and Unknown categories, and my experience matches Valve’s warnings. For example, a game might not bring up the touchscreen keyboard automatically for text inputs. That happened in Timberborn , which is listed as Playable with a warning saying, “Entering some text requires manually invoking the on-screen keyboard.” Don’t let the Unknown category scare you away from trying a game, especially if you already own it, as it could play quite well, like Temtem.
Games that are labeled Verified look and feel similar to playing on a desktop PC; the controls are generally intuitive.
One hugely awesome feature I love? Continued Play. It lets you start a game on your PC, save, and then instantly switch to the Deck if you want to move to the couch. It was a lot of fun loading into games I haven’t played for years and picking up where I left off. Unfortunately, developers need to support this Steam Cloud feature, so you may have to wait for this seamless switching to work.
Being able to play games that have been stuck in my Steam library just about anywhere is amazing. I also love that some components of the Steam Deck are repairable or replaceable, like the thumb stick and the SSD. Valve doesn't think you should open the machine up , but you have the option.
Still, it's tough recommending the Steam Deck in its current state just yet—especially if you’re not a hardcore gamer, have visual accessibility issues, or are worried about straining your hands and don’t want to spend extra cash on a separate controller. There is a lot to love, but it feels very much like an early-access game. That said, if you order it now, your expected ship date is somewhere between April and June, so things might be different by then.
Gabe Newell, Valve’s cofounder and president, tells me that Valve will seriously consider customer feedback and use cases for further updates and future iterations. And here's the thing: In my conversations with Newell and the developers, I repeatedly heard “future generations,” as though a second-gen Steam Deck wasn't far off.
I've played multiple games from my backlog over the past few weeks, just because I'm no longer tethered to my gaming PC. The experience hasn't been as seamless as I'd have liked, but give it six months to a year and the OS could be in a completely different state. Or, you know, just wait for the inevitable Steam Deck V2.
Valve Steam Deck Rating: 5/10 $399 at Steam If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $399 at Steam Games Editor X Instagram LinkedIn Topics Shopping Valve Steam video games portable gaming PC Games Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,020 | 2,018 |
"Watch John Boyega Answers the Web's Most Searched Questions | Autocomplete Interview | WIRED"
|
"https://www.wired.com/video/watch/autocomplete-inverviews-john-boyega-answers-the-webs-most-searched-questions"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons John Boyega Answers the Web's Most Searched Questions About Released on 09/06/2022 Hi, I'm John Boyega.
And this is the Wired auto complete interview.
[upbeat music] Huh, these people are really Googling out here.
[upbeat music] What is John Boyega? Do I reveal? Known for? I feel like I'm known for Attack the Block to some people and Star Wars to most cause I've done a little film called Star Wars.
It was an indie, low budget, not a lot of funding but a lot of people know it for some reason.
So, I say, Star Wars.
What is John Boyega doing now? Well, right now I'm doing press for three movies Breaking, The Woman King, and They Cloned Tyrone.
But in my free time, I'm going on dates.
I'm going go karting spending time with friends and going to parties.
What is John Boyega's next movie? I actually don't know.
I'm kind of waiting for these three to come out so someone can see it and then give me a job next year.
Honestly, that's just how it works, guys.
You just gotta do projects, everyone sees it, and then the next year.
But the savings are correct.
I've got enough in the savings.
John Boyega what's in the box? Oh! [laughs] All right, we need to do a part two to this.
Me and Gwen, right? I think that's what everyone's referring to.
Yeah, me and Gwen done this silly, silly show called What's in the Box where we had to basically put our hands in the box and feel lizard, spiders, and all different types of critters.
Good times I miss you, Gwen.
What school did John Boyega go to? I went to an amazing school called Westminster City for boys.
[fart sound] [laughs] I didn't like secondary, well, we call it secondary school.
You lot call it high school.
I didn't enjoy it.
I didn't enjoy it.
I enjoyed college.
I enjoyed university.
And I enjoyed primary school prior to that.
But high school for me was like, I have no money.
I couldn't afford the sneakers that everybody had.
I didn't have the clothes to fit in and stuff.
So, I was just like, Ah.
But then it got to college.
College is when I sprout.
[laughs] [board hits floor] Does John Boyega...
Oh, I'm getting worried now.
Does John Boyega have tattoos? Yeah, I do.
I didn't show them much.
I've had tattoos for a long time people.
I just, yeah, I just wasn't showing them a lot.
So, whenever people see my arms, they're like, Oh! But yeah I have a few tattoos, yeah.
This is a tattoo that I got in representation of my sisters.
My two older siblings, Blessing and Grace.
And then my love for wolves and horse riding.
The synergy in family is so important to me.
And wolves naturally have that synergy in family obviously they roll in packs but the love between them.
My siblings, Blessing, Grace, and John, are represented by three cubs with one wolf, with their breath, going into a horse.
I design all my tattoos.
I sketch and draw and give it to the artists.
So, it's just something like a binding tattoo to remind me of the love between me, Blessing, and Grace, my two older sisters who I love dearly.
I love ya.
And when you lot getting yours? Cus I'm sick and tired of being the only one.
Does John Boyega have an Oscar? I do.
I have an Oscar Isaac.
[Director] What's the most meaningful recognition you have received? The most meaningful so far is my statue at Madam Two Souls.
That is cool.
And I've been seeing some pictures, people uploading going to see this, the wax figure that's been real cool.
Does John Boyega watch anime? Yeah, I do.
I watch Attack on Titan.
I watch Naruto.
I watch One Piece.
I'm on Demon Slayer right now, which I'm enjoying.
I definitely think the style of storytelling for anime is something that other genres can't particularly capture.
But I think that's what anime is for.
I think anime also the story, the story, sometimes a lot of these stories last over 10 years, like you you're with one character for a long amount of time.
Apart from TV, it's very hard to see that kind of content out there too.
Also it's the seriousness and depth in anime.
It's 2D, but you have emotions for the characters as if they actually they have oxygen and blood running through their veins.
So, it's a unique style of storytelling that I really, really love.
And a lot of people do too.
Does John Boyega work out? At the moment, no.
Know what, I want this belly to hang off for a little bit.
I realized soft and muscular, a little bit of dad bod, a little bit of lean and that's what I'm on right now.
And then when I get a role that requires me to be like, Spiderman get that Tom Holland body going on, then I'll change.
But right now I'm on a break.
[Director] Did I ever read that you had some unusual names for the equipment? Dumbbells, chicken drumsticks.
The plates, call them pizza stacks.
When you see a pizza stacked on top of each other I recognize that if I go to the gym, calories has to be a part of my workout in some way because I really like eating and I sometimes hate dieting So, I just call the equipment That's meant to make me look good food that I like.
So, pizza and drumsticks.
And the barbells, I call lollipop.
Cause you know, you know what I mean? But that's just me, guys. I'm weird like that.
[Boom] All right.
All right, this is what people are Googling.
Who John Boyega.
What? People just don't fill out the words.
Who is John Boyega? Why did a person Google this? What they had seen me and then was like, Oh, who is, oh yeah, yeah.
They probably saw me in a trailer and said, Who is that? Well, hi guys. I'm John.
I'm an actor.
I'm a producer.
And I'm just a young 30 year old man.
Who does John Boyega play in Star Wars? I will act as if I am not slightly offended by that question.
But I play a guy called Finn, FN-2187.
Who's a storm trooper turned rebel.
If you haven't watched it now, bloody hell.
I think people underappreciated his lineup in episode nine.
If you recognize episode seven and eight, Finn's hair, he ain't had no lineup.
Nine I got that sorted for you guys.
And then no one gave the character props for that.
So, I have a problem. They didn't appreciate his hairstyle.
Who does John Boyega support? [lips flapping] Mom, dad, wait, wait, is this financial support or is this just moral and that? [laughs] I support a whole bunch of people.
I support some young people through via converse and my filmmaking scheme.
I support some young people at Damilola Taylor center down in the UK, done a few charities and stuff.
And then I financially support mom and dad.
Mom, Dad, just send me the email when you want me to buy you something.
Who is John Boyega dating? We've going on a few dates actually.
I've actually, I have time to actually go out on dates and go on dinners, went to one yesterday.
Nailed it.
Let's see if I get a second one.
See how she feels.
So I'm gonna let you guys know in the next interview, but she was fine.
What I like about being single is that you're given the time to do the work the individual work to work on yourself get your yourself in order.
Get your mind right.
You have the freedom to do for self, which I think is important.
All right.
Is John Boyega, is John Boyega in Kenobi? No, definitely not in Kenobi because Finn is not alive in terms of the cannon and the timeline.
I love it.
I love everyone.
I've been loving it.
I've been having fun with that.
I think it's cool.
I like the fact that Hayden is back, which is fun to see my guy Anakin.
You know and Anakin's one of my faves.
So, I'm enjoying it.
Is John Boyega Nigerian.
[laughs] What kind of question is that? Can you not see the back of my head, the shape of my head? You can all tell when you got in Nigerian brother.
I'm definitely Nigerian.
Actually I have dual citizenship.
So, I have a passport in the UK and I have a passport in Nigeria since birth.
So, yeah, I'm a fully Nigerian. Yeah.
Is John Boyega still acting? Who the hell put this in? Absolutely. A lot of people do ask me that though.
And I understand because it takes us a long time to film the projects.
But just remember guys, before we bring out the projects I have to film them.
So, it took me two years to film these three projects that come out this year.
So, yeah, it takes a long time, but yeah, I am still acting.
Thank you for asking.
Is John Boyega nice? Yeah, yeah, of course.
Yeah. Nice.
Can't be starting no problems.
If you start a problem with me, however, but in general I'm nice. Yeah. I'm cool.
Welcome.
[board hits floor] How John Boyega, how to pronounce John Boyega.
John bo-ye-ga.
Bodega but then just add that y.
For everyone in New York.
How old is John Boyega? I just turned the big three oh.
But obviously fanboy, no pimple, young face.
And then you can look like you're still in your twenties like me.
Thinking my thirties- Well, I'm saying in my thirties like I've been here for a minute, but in terms of just getting here and the information I've been hearing from a lot of other 30 year olds that I've been kind of like listening to, you do things more on purpose.
You have much more of an intuition about what you want.
And I'm looking forward to that more and more.
How did John Boyega become an actor? From primary school I did performing art stuff and I wasn't good at much else.
I tried football.
It was all social circles, I tried to get into the football group, couldn't do that.
I tried to be a part of the highly academic group.
You know, the A Star students, couldn't do that.
Tried to be part of the nerds, got too bored.
Couldn't do that.
Then I saw all the performing arts people doing contemporary dance and tap and they accepted me and I said, Oh, I'm a theater kid.
So, I joined that group.
And then from there I got a corp opportunity with a scholarship to Theater PCCA.
So, I'm quite lucky I was helped.
[Director] Did I read that your first role was a leopard? First of all, I don't like the way you asked that question as if that isn't one of my most known roles.
This is obviously I'm very famous for my first role.
My starring role actually as the leopard in the Anansi Spider-Man stories, which is based off of the old folktale Jamaican books.
I played the leopard, which is you guys wanna see this his turn in, this is ridiculous.
I would say better than anything I've done before.
And that's Star Wars included. All of them.
My first gig.
How tall is John Boyega? Always wanted to answer this.
Guys, it is five 10.
I reached the average.
All these five sevens, five sixes and eights that I've been hearing about is not true.
Five 10. I reached the average.
And if I straighten up my back, I can even get more.
Apart from that, I feel like I'm a good person.
So, hopefully my height doesn't stifle anything.
[laughs] [boom] All right, that's it guys.
Obviously, I'm so shocked to hear that you guys are so intrigued by me.
And I'm thankful for your continuous support.
Anyway, next time.
Wired.
[upbeat musics] Melissa McCarthy & Kristen Bell Answer The Web’s Most Searched Questions NASA Astronauts Answer The Web’s Most Searched Questions Common Answers The Web’s Most Searched Questions Ice Cube Answers The Web’s Most Searched Questions Eve Answers The Web’s Most Searched Questions Seth Rogen & Rose Byrne Answer The Web’s Most Searched Questions The Cast of Warcraft Answer The Web's Most Searched Questions Slow Mo Guys, MatPat, AsapSCIENCE, and Burnie Burns Answer the Web's Most Searched Questions Dana Carvey Answers the Web’s Most Searched Questions Mr. Robot's Carly Chaikin Answers the Web's Most Searched Questions Cara Delevingne Answers the Web’s Most Searched Questions Chelsea Handler Answers the Web’s Most Searched Questions Blindspot's Jaimie Alexander Answers the Web's Most Searched Questions Jennifer Aniston & Jason Bateman Answer the Web's Most Searched Questions Kate McKinnon & Vanessa Bayer Answer the Web's Most Searched Questions The Cast of "Rogue One" Answers the Web's Most Searched Questions Tracy Morgan Answers the Web's Most Searched Questions The Cast of 'Sesame Street' Answer the Web's Most Searched Questions Samuel L. Jackson Answers the Web's Most Searched Questions Jennifer Lawrence & Chris Pratt Answer the Web's Most Searched Questions Reggie Watts Answers the Web's Most Searched Questions Ryan Reynolds & Jake Gyllenhaal Answer the Web's Most Searched Questions Chris Evans Answers the Web's Most Searched Questions Morgan Freeman, Michael Caine, and Alan Arkin Answer the Web's Most Searched Questions Anne Hathaway & Jason Sudeikis Answer the Web's Most Searched Questions Salma Hayek & Eugenio Derbez Answer the Web's Most Searched Questions Amy Schumer & Goldie Hawn Answer the Web's Most Searched Questions Steve Carell & Kristen Wiig Answer the Web's Most Searched Questions Will Ferrell & Amy Poehler Answer the Web's Most Searched Questions Al Gore Answers the Web's Most Searched Questions on Climate Change Matthew McConaughey & Idris Elba Answer the Web's Most Searched Questions Dave Franco, Kumail Nanjiani and Fred Armisen Answer the Web's Most Searched Questions Tom Cruise & Doug Liman Answer the Web's Most Searched Questions Josh Brolin & Taylor Kitsch Answer the Web's Most Searched Questions Matt Damon & Julianne Moore Answer the Web's Most Searched Questions Nick Jonas Answers the Web's Most Searched Questions Gaten Matarazzo and Joe Keery Answer the Web's Most Searched Questions The Last Jedi Cast Answer the Web's Most Searched Questions John Cena Answers the Web's Most Searched Questions Owen Wilson & Ed Helms Answer the Web's Most Searched Questions Will Smith & Joel Edgerton Answer the Web's Most Searched Questions Black Panther Cast Answer the Web's Most Searched Questions Google Search Team Answers the Web's Most Searched Questions Bruce Willis Answers the Web's Most Searched Questions Charlize Theron & David Oyelowo Answer the Web's Most Searched Questions This Is Us Cast Answers the Web's Most Searched Questions Alicia Vikander Answers the Web's Most Searched Questions Jennifer Garner Answers the Web's Most Searched Questions Charlie Day Answers the Web's Most Searched Questions Jeff Goldblum Answers the Web's Most Searched Questions Taraji P. Henson & Tyler Perry Answer the Web's Most Searched Questions John Krasinski Answers the Web's Most Searched Questions Ansel Elgort & Suki Waterhouse Answer the Web's Most Searched Questions Terry Crews Answers the Web's Most Searched Questions Shawn Mendes Answers the Web's Most Searched Questions Solo Cast Answer the Web's Most Searched Questions Jodie Foster Answers the Web's Most Searched Questions Best of Autocomplete: The Cast of Black Panther, Stranger Things and More Answer the Web's Most Searched Questions Robert Pattinson & Mia Wasikowska Answer the Web's Most Searched Questions Alison Brie & Marc Maron Answer the Web's Most Searched Questions 'Sorry to Bother You' Cast Answers the Web's Most Searched Questions 'Ant-Man and the Wasp' Cast Answer the Web's Most Searched Questions Will Arnett Answers the Web's Most Searched Questions Mila Kunis & Justin Theroux Answer the Web's Most Searched Questions Ewan McGregor & Hayley Atwell Answer the Web's Most Searched Questions Liza Koshy Answers the Web's Most Searched Questions 'Dog Days' Cast Answer the Web's Most Searched Questions Ken Jeong Answers the Web's Most Searched Questions Mark Wahlberg, Ronda Rousey and Lauren Cohan Answer the Web's Most Searched Questions John Cho Answers the Web's Most Searched Questions Rami Malek & Charlie Hunnam Answer the Web's Most Searched Questions Anna Kendrick & Blake Lively Answer the Web's Most Searched Questions Paul McCartney Answers the Web's Most Searched Questions Keegan-Michael Key & Olivia Munn Answer the Web's Most Searched Questions Elizabeth Olsen Answers the Web's Most Searched Questions Kevin Hart & Tiffany Haddish Answer the Web's Most Searched Questions Rhett & Link Answer the Web's Most Searched Questions Riverdale Cast Answers the Web's Most Searched Questions Bella Thorne Answers the Web's Most Searched Questions John Mulaney & Nick Kroll Answer the Web's Most Searched Questions Aubrey Plaza & Craig Robinson Answer the Web's Most Searched Questions The Try Guys Answer the Web's Most Searched Questions Keira Knightley & Mackenzie Foy Answer the Web's Most Searched Questions Julia Roberts & Dermot Mulroney Answer the Web's Most Searched Questions Emily Ratajkowski & Aaron Paul Answer the Web's Most Searched Questions Sarah Silverman & John C. Reilly Answer the Web's Most Searched Questions Margot Robbie & Saoirse Ronan Answer the Web's Most Searched Questions Natalie Portman & Jude Law Answer the Web's Most Searched Questions Lin-Manuel Miranda Answers the Web's Most Searched Questions Best WIRED Autocomplete Moments of 2018 Feat. Liza Koshy, David Dobrik, The Try Guys & More Ninja Answers the Web's Most Searched Questions Zedd Answers the Web's Most Searched Questions Bryce Dallas Howard Answers the Web's Most Searched Questions James McAvoy & Sarah Paulson Answer the Web's Most Searched Questions Jane Fonda & Lily Tomlin Answer the Web's Most Searched Questions Daniel Radcliffe Answers the Web's Most Searched Questions Priyanka Chopra, Rebel Wilson & Adam Devine Answer the Web's Most Searched Questions David Dobrik Answers the Web's Most Searched Questions Brie Larson Answers the Web's Most Searched Questions Freddie Highmore Answers the Web's Most Searched Questions Oscar Isaac & Pedro Pascal Answer the Web's Most Searched Questions Markiplier Answers the Web's Most Searched Questions Colin Farrell & Danny DeVito Answer the Web's Most Searched Questions Queer Eye Cast Answer the Web's Most Searched Questions Nikolaj Coster-Waldau Answers the Web's Most Searched Questions Gina Rodriguez Answers the Web's Most Searched Questions Sean Bean Answers the Web's Most Searched Questions Anthony Mackie Answers the Web's Most Searched Questions Lily Collins & Nicholas Hoult Answer the Web's Most Searched Questions Wu-Tang Clan Answer the Web's Most Searched Questions Wanda Sykes Answers the Web's Most Searched Questions Charles Melton Answers the Web's Most Searched Questions Jessica Alba & Gabrielle Union Answer the Web's Most Searched Questions Jon Hamm & David Tennant Answer the Web's Most Searched Questions Thomas Middleditch & O'Shea Jackson Jr. Answer the Web's Most Searched Questions Sophie Turner & Jessica Chastain Answer the Web's Most Searched Questions Mindy Kaling & Emma Thompson Answer the Web's Most Searched Questions Smosh Answers the Web's Most Searched Questions Tom Holland, Zendaya & Jacob Batalon Answer the Web's Most Searched Questions Millie Bobby Brown, Finn Wolfhard & Noah Schnapp Answer the Web's Most Searched Questions Winona Ryder & David Harbour Answer the Web's Most Searched Questions Eric Andre Answers the Web's Most Searched Questions Machine Gun Kelly Answers the Web's Most Searched Questions Charlie Puth Answers the Web's Most Searched Questions Novak Djokovic Answers the Web's Most Searched Questions Anderson Cooper Answers the Web's Most Searched Questions Jim Gaffigan Answers the Web's Most Searched Questions Liam Payne Answers the Web's Most Searched Questions Lilly Singh Answers the Web's Most Searched Questions Gwen Stefani Answers the Web's Most Searched Questions Dove Cameron Answers the Web's Most Searched Questions Kevin Smith Answers the Web's Most Searched Questions Niall Horan Answers the Web's Most Searched Questions Lele Pons Answers the Web's Most Searched Questions Hailee Steinfeld Answers the Web's Most Searched Questions Louis Tomlinson Answers the Web's Most Searched Questions Kiernan Shipka & Isabela Merced Answer the Web's Most Searched Questions Kristen Stewart, Naomi Scott, and Ella Balinska Answer the Web's Most Searched Questions Jack Black & Awkwafina Answer the Web's Most Searched Questions KJ Apa Answers the Web's Most Searched Questions The Best of Autocomplete 2019: Funniest Moments from Stranger Things, Spider-Man and More Billy Eichner & Cobie Smulders Answer the Web's Most Searched Questions Frozen 2 Cast Answer the Web's Most Searched Questions Jada Pinkett Smith Answers the Web's Most Searched Questions Zach Galifianakis & Zoe Saldana Answer the Web's Most Searched Questions Elijah Wood Answers the Web's Most Searched Questions Noah Centineo & Lana Condor Answer the Web's Most Searched Questions Lucy Hale Answers the Web's Most Searched Questions Patrick Stewart Answers the Web's Most Searched Questions Norman Reedus Answers the Web's Most Searched Questions Astronaut Chris Hadfield Answers the Web's Most Searched Questions Nick Offerman Answers the Web's Most Searched Questions Binging with Babish Answers the Web's Most Searched Questions Jamie Dornan & Shailene Woodley Answer the Web's Most Searched Questions Ellie Kemper Answers the Web's Most Searched Questions Joe Biden Answers the Web's Most Searched Questions Ricky Gervais Answers the Web's Most Searched Questions Alicia Keys Answers the Web's Most Searched Questions Tony Hawk Answers the Web's Most Searched Questions Russell Crowe Answers the Web's Most Searched Questions Kevin Bacon Answers the Web's Most Searched Questions Joey King & Joel Courtney Answer the Web's Most Searched Questions Kermit & Miss Piggy Answer the Web's Most Searched Questions Alessia Cara Answers the Web's Most Searched Questions Jamie Foxx & Joseph Gordon-Levitt Answer the Web's Most Searched Questions Mayim Bialik Answers the Web's Most Searched Questions Desus & Mero Answer the Web's Most Searched Questions Dolly Parton Answers the Web's Most Searched Questions Ruby Rose Answers the Web's Most Searched Questions Sonequa Martin-Green Answers the Web's Most Searched Questions Chelsea Handler Answers the Web's Most Searched Questions John C. Reilly & Tim Heidecker Answer the Web's Most Searched Questions Joel McHale Answers the Web's Most Searched Questions Questlove Answers the Web's Most Searched Questions Dua Lipa Answers the Web's Most Searched Questions Zara Larsson Answers the Web's Most Searched Questions Bob Odenkirk and RZA Answer the Web's Most Searched Questions SpongeBob's Tom Kenny & Bill Fagerbakke Answer the Web's Most Searched Questions Jackson Wang Answers the Web's Most Searched Questions Eric Andre Answers the Web's Most Searched Questions...Again LILHUDDY Answers the Web's Most Searched Questions Polo G Answers the Web's Most Searched Questions Hank Azaria Answers the Web's Most Searched Questions Zack Snyder Answers the Web's Most Searched Questions TWICE Answer the Web's Most Searched Questions MONSTA X Answer the Web's Most Searched Questions Siri, Alexa and Google Home Answer the Web's Most Searched Questions Rich Brian and NIKI Answer the Web's Most Searched Questions B.I Answers the Web's Most Searched Questions Never Have I Ever Cast Answer the Web's Most Searched Questions M. Night Shyamalan Answers the Web's Most Searched Questions Henry Golding Answers the Web's Most Searched Questions BTS Answer the Web's Most Searched Questions Emily Blunt & Dwayne Johnson Answer The Web's Most Searched Questions Jennifer Hudson Answers the Web's Most Searched Questions Outer Banks Cast Answer the Web's Most Searched Questions Rita Ora Answers the Web's Most Searched Questions Dove Cameron Answers the Web's Most Searched Questions...Again Daniel Radcliffe Answers MORE of the Web's Most Searched Questions Ben Platt & Amandla Stenberg Answer The Web's Most Searched Questions Tom Hardy & Andy Serkis Answer the Web's Most Searched Questions On My Block Cast Answer the Web's Most Searched Questions Daniel Craig & Lashana Lynch Answer the Web's Most Searched Questions William Shatner Answers the Web's Most Searched Questions Madison Beer Answers the Web's Most Searched Questions Marshmello Answers the Web's Most Searched Questions Amanda Seyfried & Finn Wittrock Answer the Web's Most Searched Questions Nina Dobrev Answers the Web's Most Searched Questions Kit Harington Answers the Web's Most Searched Questions Kristen Bell & Kirby Howell-Baptiste Answer the Web's Most Searched Questions Dominic Monaghan & Billy Boyd Answer the Web's Most Searched Questions Cowboy Bebop Cast Answer the Web's Most Searched Questions YouTube Search Team Answers the Web's Most Searched Questions Jack Whitehall Answers the Web's Most Searched Questions Andrew Garfield Answers the Web's Most Searched Questions Sabrina Carpenter Answers the Web's Most Searched Questions Simu Liu Answers the Web's Most Searched Questions Tom Holland, Zendaya & Jacob Batalon Answer MORE of the Web's Most Searched Questions Eric Nam Answers the Web's Most Searched Questions Ben Affleck & Lily Rabe Answer the Web's Most Searched Questions ATEEZ Answer the Web's Most Searched Questions Seth Rogen Answers The Web’s Most Searched Questions Owen Wilson Answers The Web’s Most Searched Questions David Byrne Answers the Web's Most Searched Questions Johnny Knoxville Answers the Web's Most Searched Questions Channing Tatum & Sandra Bullock Answer the Web's Most Searched Questions Karen Gillan Answers the Web's Most Searched Questions Leslie Mann & Judd Apatow Answer the Web's Most Searched Questions Cole Sprouse Answers the Web's Most Searched Questions Nicolas Cage Answers the Web's Most Searched Questions TommyInnit Answers the Web's Most Searched Questions Drew Gooden Answers the Web's Most Searched Questions Seth MacFarlane Answers the Web's Most Searched Questions Sadie Sink, Noah Schnapp & Gaten Matarazzo Answer the Web’s Most Searched Questions Taika Waititi Answers the Web’s Most Searched Questions Maisie Williams Answers the Web’s Most Searched Questions Jacksepticeye Answers the Web's Most Searched Questions Chris Hemsworth Answers the Web's Most Searched Questions Guinness World Records Answer the Web's Most Searched Questions The Russo Brothers Answer the Web's Most Searched Questions Keke Palmer Answers the Web's Most Searched Questions Marques Brownlee Answers the Web's Most Searched Questions Neil Patrick Harris Answers the Web's Most Searched Questions Jennifer Lopez & Leah Remini Answer the Web's Most Searched Questions Dakota Johnson & Jeff Bridges Answer the Web's Most Searched Questions High School Musical: The Musical: The Series Cast Answer the Web's Most Searched Questions Kevin Hart & Mark Wahlberg Answer the Web's Most Searched Questions Danny DeVito Answers the Web's Most Searched Questions Lili Reinhart Answers the Web's Most Searched Questions John Boyega Answers the Web's Most Searched Questions Sofía Vergara & Simon Cowell Answer the Web's Most Searched Questions Steve-O Answers the Web's Most Searched Questions Stray Kids Answer the Web's Most Searched Questions Charli & Dixie D'Amelio Answer the Web's Most Searched Questions NCT 127 Answer the Web's Most Searched Questions Hasan Minhaj Answers the Web's Most Searched Questions Cobra Kai's Ralph Macchio Answers the Web's Most Searched Questions Mrwhosetheboss Answers the Web's Most Searched Questions Chloë Grace Moretz Answers the Web's Most Searched Questions Millie Bobby Brown Answers the Web's Most Searched Questions Jenna Ortega Answers the Web's Most Searched Questions Veritasium's Derek Muller Answers the Web's Most Searched Questions Jason Momoa Answers the Web's Most Searched Questions LaurDIY Answers the Web's Most Searched Questions Nigel Ng & Uncle Roger Answer the Web's Most Searched Questions Finn Wolfhard & Guillermo del Toro Answer the Web's Most Searched Questions Ludwig Answers the Web's Most Searched Questions John Krasinski & Michael Kelly Answer the Web's Most Searched Questions ITZY Answer the Web's Most Searched Questions Danny Gonzalez Answers the Web's Most Searched Questions Ashton Kutcher Answers the Web's Most Searched Questions Paul Rudd & Jonathan Majors Answer the Web's Most Searched Questions Outer Banks Cast Answer the Web's Most Searched Questions Again Kelly Slater Answers Surfing Questions From Twitter KAROL G Answers the Web's Most Searched Questions Penn Badgley Answers the Web's Most Searched Questions Chris Pine, Hugh Grant & Michelle Rodriguez Answer the Web's Most Searched Questions Willem Dafoe Answers the Web's Most Searched Questions KSI Answers the Web's Most Searched Questions Bob Odenkirk Answers the Web's Most Searched Questions Jisoo Answers the Web's Most Searched Questions Ali Wong & Steven Yeun Answer the Web's Most Searched Questions Chris Evans & Ana de Armas Answer the Web's Most Searched Questions Airrack Answers the Web's Most Searched Questions ChatGPT Answers the Web's Most Searched Questions James & Sean Gunn Answer the Web's Most Searched Questions Mark Hamill Answers the Web's Most Searched Questions Shameik Moore, Issa Rae & Hailee Steinfeld Answer The Web's Most Searched Questions Tom Segura Answers The Web's Most Searched Questions Robert Downey Jr. & Christopher Nolan Answer The Web's Most Searched Questions Bear Grylls Answers The Web's Most Searched Questions Smosh Answer The Web's Most Searched Questions Ice Cube Answers The Web's Most Searched Questions Stephen Curry Answers The Web's Most Searched Questions 'Heart of Stone' Cast Answers The Web's Most Searched Questions 'Critical Role' Cast Answers The Web's Most Searched Questions Harry Mack Freestyles The Web's Most Searched Questions Olivia Rodrigo Answers The Web's Most Searched Questions Pokimane Answers The Web's Most Searched Questions MoistCr1TiKaL Answers The Web's Most Searched Questions Dream Answers The Web's Most Searched Questions Fanum Answers The Web's Most Searched Questions Casey Neistat Answers The Web's Most Searched Questions | WIRED Måneskin Answer the Web's Most Searched Questions Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,021 | 2,018 |
"iPad Pro (2018) Review: Almost a Laptop Killer | WIRED"
|
"https://www.wired.com/review/review-ipad-pro-2018"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Jeffrey Van Camp Gear Review: iPad Pro (2018) Facebook X Email Save Story Apple Facebook X Email Save Story $1,200 at Amazon (11-Inch, 1 TB) $900 at Best Buy (11-Inch, 256 GB) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 8/10 Open rating explainer Like a college graduate ready to head off into the workforce and start a career, Apple has graduated the iPad from tablet school. As he prepared to lift the curtain on the new 11-inch and 12.9-inch iPad Pro last week, CEO Tim Cook explained that Apple sees the iPad as a personal computer now. Apple says that new designation makes iPad the top-selling line of PCs in the world.
It’s a fair comparison. After using a new iPad Pro 12.9 for a few days, I can say that it's most definitely a refreshing, positive step forward for the iPad. It could also be called a "computer." Is it the right computer for you? That's another story.
The first thing you’ll notice about the new iPad Pro is what it’s missing. Like the iPhone XR and its peers, the Pro has no home button. Instead, its screen stretches from edge to edge... to edge to edge. All four sides are rimmed with thin and equally-sized black bezels, making it easier to forget where the top of the device really is. Sometimes iOS will actually point out where the power button is on the edge because, rightfully, it thinks I may have forgotten.
The back of the 5.9mm aluminum shell feels incredibly sturdy, and sheds the tapered edges that have defined the iPad for most of its existence. The back is now flat like the bottom of a box, right up to the side. The design looks like a refined version of the iPhone 5. The shape also feels like what the original 2011 iPad was trying to accomplish—this time with no bump in the back, except for the camera.
The Liquid Retina LCD displays are huge, stretching 11 or nearly 13 inches, depending on which model you choose. They’re gorgeous and packed with pixels. Like the iPhone XR, the corners of the display are rounded thanks to precision-milled glass and a host of other tech treats. Color is vibrant and precise enough for Photoshopping and minute color tweaking if needed. (Apple tests the color accuracy of its displays in 160 different points.) The Pro also adapts the warmth of its display to the lighting in your room.
The new iPad Pro also comes with Face ID , which uses a collection of cameras, sensors, and algorithms to identify your face in a way that it claims is more secure than fingerprint authentication or passwords. It works well, and doesn’t require that cut-out notch on the screen like the iPhone. It’s not quirk-free, though. We usually hold our iPhones in a portrait (vertical) orientation because that’s just how they fit in our hand. With an iPad like this, you almost always use two hands, and that means there isn’t really a "right" or "wrong" way to hold it. From time to time, my hands would sometimes accidentally block the Face ID camera when I held it in landscape (widescreen) orientation. And if I’m lounging around, my face may also be out of view. As I’ve gotten used to keeping my head in front of the tablet screen, and my hands away from its front-facing camera, Face ID evolved from a hindrance to a helpful, secure aid. I’ve never bothered to add a passcode or use Touch ID on older iPads. Now it’s easy enough that I just might.
The 7-megapixel front camera is also pretty proficient at selfies, Animoji , and video chatting—-provided your hand isn’t blocking it. The 12-megapixel shooter is also up to iPhone standards, though I’ve found it a little too cumbersome (and embarrassing!) to use a 13-inch tablet as a camera while I’ve roamed around San Francisco this weekend. Apple did show me some impressive demonstrations of its augmented reality capabilities, made possible by that camera. I examined the inside of a plant to learn all about how it lives in an app called Plantale, and had fun bringing a Lego Ninjago playset to life as an iOS game. I grew up as one of those kids who hated damaging his beautiful Lego creations. I may have had more fun if I could have blown them up digitally.
The inside of the iPad is just as impressive as the outside. The Pro has an A12X Bionic chip, which is kind of a turbocharged version of the processor that’s packed into every iPhone XS and XR. It has eight cores: four for super demanding work, like playing Fortnite , and four more for easier tasks, like perusing your email. This year, it can mix and match those cores more efficiently, giving it almost 2x better multi-core performance than before. The graphics chip also pumps out around 2x more power, all without compromising the 10-hour battery life every iPad has gotten.
Apple claims the new iPad Pro is faster than 92 percent of all laptops sold in the past year, including some with an Intel Core i7 CPU, and compared its game graphics prowess to an Xbox One S. No apps or games I’ve used have been able to make the Pro break a sweat at all and benchmark numbers have been impressive.
Photographers and video editors might like the new storage options. The Pro comes with 64GB of memory by default, but you can bump that number as high as 1TB. And since this tablet has a USB-C charging port, you can more easily connect it to a camera, external monitor, and other accessories. Yes, that is singular. There is only one port. Start shopping for dongles if you need more. Apple now sells a ton of them.
And pick up some good wireless headphones while you’re at it. Though Apple’s redesigned quad speakers sound amazing for a tablet (or laptop), the headphone jack is gone.
Apple redesigned its two key accessories for the new iPad Pro. The new Apple Pencil ($129) and Smart Keyboard Folio ($179) each got noticeable upgrades this year. The one you choose may indicate how much you’ll like your new iPad Pro.
No laptop can emulate the drawing capabilities of the Apple Pencil, or feel as natural to hold and use with touch.
The Apple Pencil is my favorite. It now has a matte plastic design and comes flat on one side so it can magnetically snap onto the edge of either size iPad Pro—automatically pairing via Bluetooth and charging. It’s hard to stress how much of a game changer this simple magnetic charging is, but it eliminates a lot of needless steps. The Pencil is always charged, paired, and ready to go. (Just be careful; it can still snap off in your bag.) I’m a god-awful artist, but I found myself doodling on the iPad Pro. Three years after its debut, the refined Pencil is still the most responsive, accurate digital writing tool I’ve ever used. It’s fun to try out different virtual drawing tools, like colored pencils, and as a leftie, I love that iPad never thinks I’m trying to draw with my palm.
Apple iPad Pro (11 or 12.9-Inch, 2018) Rating: 8/10 $1,200 at Amazon (11-Inch, 1 TB) $900 at Best Buy (11-Inch, 256 GB) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The 12.9-inch Pro is still a huge tablet, but feels more manageable this year thanks to the thinner bezels. In fact, it’s now about the size of a magazine (or sheet of paper, as Apple likes to point out), which is a comfortable, familiar size for reading and writing.
The Smart Keyboard Folio is also improved. It magnetically snaps onto the back of the tablet with an equally pleasant click and also just works. It now has two angles you can choose from and the keys are naturally spaced and have enough travel (depth) and click to them that it didn’t take me any time to adjust from my MacBook Pro. My only complaints? It would be nice to have even more angles, and the larger iPad can feel a bit unstable if you use it on your lap. Since the camera sits on the left side, it’s tough to frame yourself properly for a video chat.
By every measure I can think of, these are the best, most powerful, most capable iPads I’ve ever used. They put other tablets to shame.
But Apple has begged the question: Can an 11-inch ($799) or 13-inch ($999) iPad Pro replace your need for a MacBook or Windows PC at work? It’s possible, but you’ll need the right kind of occupation, and a lot of patience and determination.
No laptop can emulate the drawing capabilities of the Apple Pencil, or feel as natural to hold and use with touch. It’s not even close. The iPad Pro has a clear lead over PCs there.
As a more traditional work PC, it sometimes struggles. In a pinch, the iPad Pro and its Smart Keyboard are usable. For example, I wrote this review on the Pro in Google Docs while also opening webpages on the right side of my screen, but it took me longer than normal to do research and collect links—and a good long while to figure out how to do other tasks. I wanted to use the normal web version of Docs, but I had to use the app. My office also uses a collaboration tool called Airtable that wouldn’t work in an iPad browser. It also tossed me to the app, which lacked key features. Attaching specific files was kind of a nightmare in the Gmail app, too. Some apps, like Spotify, don’t allow Split View multitasking (side-by-side viewing) at all yet. You have to use them full screen. Spreadsheets are also tougher (slower) to manipulate in the apps I’ve used.
I found solutions to all of these problems, and I’m sure I can keep finding creative solutions to make the iPad Pro work as a PC, but the hassles will keep coming. The iPad’s web browsers are still treated more like their less-capable smartphone counterparts, and the apps that are supposed to work in their place also sometimes lack desktop features. Part of this is the fault of developers, but Apple bears responsibility, as well.
It doesn’t feel like the world is ready to treat my iPad as an equal to a PC yet—even if that iPad is a lot more powerful and user friendly. Now that Apple has declared the iPad is a PC, it should take more of the guardrails off of iOS and strongly encourage developers to treat it like they do the Mac. It’s time for iOS to grow up and get a job.
Apple iPad Pro (11 or 12.9-Inch, 2018) Rating: 8/10 $1,200 at Amazon (11-Inch, 1 TB) $900 at Best Buy (11-Inch, 256 GB) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The iPad Pro is one of the most powerful computers you can own. It could be the best PC, too. Or better than a Mac. For now, it still has to settle for being the best tablet money can buy.
Apple iPad Pro (11 or 12.9-Inch, 2018) Rating: 8/10 $1,200 at Amazon (11-Inch, 1 TB) $900 at Best Buy (11-Inch, 256 GB) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $1,200 at Amazon (11-Inch, 1 TB) $900 at Best Buy (11-Inch, 256 GB) Reviews Director X Topics apple iPad review Wired Recommends Shopping Lauren Goode Brendan Nystedt Lauren Goode Brendan Nystedt Jeffrey Van Camp Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,022 | 2,023 |
"Which iPhone 15 Model Should You Buy? | WIRED"
|
"https://www.wired.com/story/apple-iphone-15-deals"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Julian Chokkattu Gear Which iPhone 15 Model Should You Buy? Photograph: Apple Save this story Save Save this story Save The iPhone 15 is here, and it comes with quite a few drastic changes.
The 11-year-old Lightning charging port has been replaced by USB-C , the notorious notch at the top of the screen has disappeared to make way for the Dynamic Island, and on the iPhone 15 Pro models the long-lived mute switch has been phased out for a programmable Action Button. It's a lot! But which iPhone 15 model is best for you? And does any model have enough enhancements to make an upgrade worth the money? If you've been mulling these questions ever since Apple debuted the new handsets , I'm here to help. Below, I break down the differences between all four iPhone 15 models, which one is right for you, and whether you should upgrade at all.
Check out our Best MagSafe Accessories , Best Apple 3-in-1 Chargers , and Best MagSafe Power Banks for more Apple recommendations. We'll be testing iPhone 15 cases soon.
Special offer for Gear readers: Get WIRED for just $5 ($25 off).
This includes unlimited access to WIRED.com , full Gear coverage, and subscriber-only newsletters. Subscriptions help fund the work we do every day.
Updated September 22, 2023: The iPhones are now available, and we've updated language and pricing reflecting the launch.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Our common answer to this question is actually a question we ask you: Is your current smartphone doing OK? If it's performing just fine and you're still getting software updates, then the answer is no. This is especially true if you have an iPhone 13 or iPhone 14 —they're still pretty recent! If you are having battery life issues but everything else is OK, then you may want to explore a battery replacement for a nominal fee first. We also have a guide to repairing your iPhone you may find helpful.
However, this year our standard answer is also slightly different. Apple has changed the charging port on the iPhone 15 range from Lightning to USB-C. If you have a bunch of USB-C devices and hate having to keep track of a separate Lightning cable, then the convenience might be worth the price of upgrading. Lightning accessories aren't going to disappear overnight, but it's also not worth investing in them anymore, as more and more accessory makers will strictly stick to USB-C.
If you've decided to upgrade, be sure to read our guide on how to sell your iPhone.
You can use Apple’s Trade-In program , but you can likely get more money selling a handset yourself. Always back up your iPhone first , then factory reset it to wipe your data. When you get your new smartphone, read our guide on how to set up your new iPhone for more tips and tricks.
The iPhone 15 Pro lineup.
Photograph: Apple The iPhone 15 range includes the iPhone 15, iPhone 15 Plus, iPhone 15 Pro, and iPhone 15 Pro Max. The iPhone 15 and iPhone 15 Plus ( 7/10, WIRED Recommends ) are exactly the same except for their size and battery life. The Pro models ( 8/10, WIRED Recommends ), unfortunately, have one big difference outside of size, but we'll get to that below. All of them come with a braided 60-watt USB-C to USB-C cable in the box.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Along with USB-C, all these phones have the Dynamic Island design that uses the area of the screen around the selfie camera to display notifications, officially bringing an end to the era of the notch. The phones all come with two years of Emergency SOS by Satellite and Crash Detection, plus the new Roadside Assistance service Apple just announced, giving you more ways to get help in dire situations. After two years, Apple will charge a fee to access these satellite services, but it has not disclosed how much these subscriptions will cost.
As usual, the iPhone 15 range supports Face ID, MagSafe accessories , and 5G connectivity. Plus all the phones have a new second-generation ultra-wideband chipset, which offers three times the range than before to precisely detect the location of nearby friends and devices via the Find My app. The screens are protected by Apple's ceramic-based material, and the phones are rated IP68 for dust and water resistance. Apple has also brought the textured matte finish from the Pro iPhones to the entire lineup, and the colors of the phones are infused into the glass skin itself.
The iPhone 15.
Photograph: Apple Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft For the cameras, Apple says it has beefed up its Photonic Engine image processing system to capture 24-megapixel photos by default across all the new devices, an upgrade from 12 megapixels. That means you get more detail in your shots, but also larger files. (Probably not a coincidence as to why it added larger iCloud+ storage plans.
) Since all of these phones have a 48-megapixel camera, they all have a 2X mode that uses the center portion of the sensor to zoom in—essentially, it will produce sharper results than any 2X optical camera Apple has ever shipped. There are all sorts of other camera upgrades, like how Portrait mode finally supports Live Photos, and now you're able to convert a normal photo into a portrait by adjusting the blur strength and focus long after you snap the shot.
Here's how they differ from each other and from their predecessors: iPhone 15 ($829) : The 6.1-inch display on the iPhone 15 ( 7/10, WIRED Recommends ) can now get up to 1,600 nits in peak brightness, and a further 2,000 nits in outdoor conditions, meaning you should have no trouble reading the screen on bright sunny days. It's powered by the A16 Bionic processor, which powers last year's iPhone 14 Pro.
The USB-C port only supports the USB 2 standard, so you're restricted to the same 480 megabits per second data transfer speeds as the Lightning connector. The 12-megapixel ultrawide camera is still present. If you just want a new iPhone with the updated changes and don't care for the rest of the features, get this model.
iPhone 15 Plus ($929) : The 6.7-inch iPhone 15 Plus has all the same features as the iPhone 15 mentioned above, but you get a larger screen and longer battery life. Last year, we found the iPhone 14 Plus offered some of the best battery life in the lineup, so this is a good option if you prioritize a big screen or longevity.
iPhone 15 Pro ($999) : The 6.1-inch iPhone 15 Pro ( 8/10, WIRED Recommends ) model now has a titanium frame that makes it 19 grams lighter, a 10 percent reduction in weight over its predecessor. Titanium material is more durable than the stainless steel of yesteryear too, though this is still a glass sandwich. The bezels around the screen are slimmer than ever, and the phone is powered by Apple's newest mobile chip, the A17 Pro. Apple says the enhanced graphics processor on this chip makes AAA games like Resident Evil Village and Assassin's Creed Mirage look much better, with high-fidelity graphics and hardware-accelerated ray tracing. The mute switch on the side of the phone has disappeared in favor of the Action Button. You can customize this button to trigger a variety of actions, and can even launch Shortcuts.
It's worth noting that the 48-megapixel camera in this model has a 50 percent larger sensor than the 48-megapixel camera in the non-Pro iPhones, so you're getting a better camera experience by default. This iPhone also has a 3X optical zoom camera in addition to the 12-megapixel ultrawide; the latter of which is what you can use to trigger the macro camera for close-ups. The Pro iPhones remain the only ones with a 120-Hz screen refresh rate, which makes interacting with the screen feel more fluid and responsive. Buy this model if you want the lightweight titanium, faster data transfer speeds, the nicer camera, and the action button, but don't want a big iPhone.
iPhone 15 Pro Max ($1,199) : The 6.7-inch Pro Max ( 8/10, WIRED Recommends ) has everything I just mentioned for the iPhone 15 Pro. These two models also support the USB 3 standard, so you can expect data transfer speeds of 10 gigabits per second, though you'll need to buy a different USB-C cable that can take advantage of those speeds. (The USB-C cable that comes in the box doesn't support the full speed the Pro is capable of.) Where the Pro Max differentiates is the camera. Instead of a 3X optical zoom, Apple has stuffed in a 5X teleprism camera, allowing you greater zoom capabilities on this iPhone. This telephoto camera uses a new 3D sensor-shift stabilization model for greater stability in your photos and videos. It's one of the best camera phones available right now. This is also the only iPhone that starts with 256 GB of storage, but it's also the only one that got a price bump of $100. Buy this model if you want the best camera experience.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft These aren't the only iPhones Apple is selling right now. You can save money by going for the iPhone 13 ($599) , iPhone 14 ($699) , or iPhone SE 2022 ($429).
Read our Best iPhone guide for more suggestions. All of these are solid buys, though you can find them for less in “used, like new” condition on sites like Swappa, Back Market, and eBay.
I strongly recommend you buy your iPhone unlocked. When you want to switch carriers, it's less of a hassle to do it if you have an unlocked phone. You can buy all of these iPhones unlocked at Apple’s website. If you do choose to activate your network through Apple, the company says its carrier models are all unlocked—except for when you purchase an AT&T device on an installment plan.
Remember, there are no physical SIM trays in the iPhone anymore ever since the iPhone 14. It's pretty easy to switch over your phone number during the setup process if you're coming from an iPhone, but Android owners switching over may need to contact their carrier to make it work.
The iPhone 15 starts at $829 at Apple for 128 GB.
The iPhone 15 Plus starts at $929 at Apple for 128 GB.
The iPhone 15 Pro starts at $999 at Apple for 128 GB.
The iPhone 15 Pro Max starts at $1,199 at Apple for 256 GB.
If you buy the carrier version, you’ll automatically get a $30 discount off the iPhone 15 and iPhone 15 Plus, bringing the prices down to $799 and $899.
Here are a few promotions that carriers are running on these iPhones. Keep in mind that most of these carriers offering discounts are doing so via monthly bill credits. A “$1,000 off” deal on an iPhone means you'll see your monthly bill lowered over the course of several months.
AT&T is offering the iPhone 15 Pro and iPhone 15 for free if you have an eligible trade-in for new and existing customers, you just have to be on any of the Unlimited Your Way plans. You can also get $830 off the iPhone 15 Plus or $1,000 off the iPhone 15 Pro Max.
Verizon is offering up to $830 off the iPhone 15 lineup (including the Pro models ) on certain Unlimited plans and if you trade in an eligible device. If you switch to Verizon or add a new line on an Unlimited Ultimate plan, you can get up to $1,000 off the iPhone 15 lineup ( Pro models included ) if you trade in an older iPhone in any condition. Those going with the Unlimited Plus or Unlimited Welcome plans can get $830 or $415 off the lineup with an iPhone trade in.
T-Mobile is offering an iPhone 15 Pro (or up to $1,000 off any iPhone 15 series ) when you trade in an eligible device on its Go5G Plus or Go5G Next plans. You can also get up to $650 off an iPhone 15 series device on the Magenta Max plan, $350 off on Go5G and Magenta plans, or $200 off on nearly all other T-Mobile plans when you trade in an eligible device. If you pick up an iPhone 15 model, you can get $700 off the second one if you add a new line on almost all T-Mobile plans.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Reviews Editor X Topics apple Shopping iPhone buying guides phones smartphones Eric Ravenscraft Jaina Grey Julian Chokkattu Jaina Grey Brenda Stolyar Adrienne So Simon Hill Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,023 | 2,017 |
"Google Glass, Oculus, HoloLens: The Race for Augmented Reality Glasses Starts Now | WIRED"
|
"https://www.wired.com/story/future-of-augmented-reality-2018"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Steven Levy Backchannel The Race for AR Glasses Starts Now Laurent Hrybyk Save this story Save Save this story Save Though the Next Big Thing won’t appear for a while, we know pretty much what it will look like: a lightweight, always-on wearable that obliterates the divide between the stuff we see on screens and the stuff we see when we look up from our screens. “We know what we really want: AR glasses,” said Oculus’s chief scientist Michael Abrash at Facebook’s F8 developers’ conference in April. “They aren’t here yet, but when they arrive they’re going to be the great transformational technologies of the next 50 years.” He predicted that in the near future, “instead of carrying stylish smartphones everywhere, we’ll be wearing stylish glasses.” And he added that “these glasses will offer AR, VR, and everything in between, and we’ll wear them all day and we’ll use them in every aspect of our lives.” Steven Levy is Backchannel's founder and Editor in Chief.
--------- Sign up to get Backchannel's weekly newsletter, and follow us on Facebook , Twitter , and Instagram.
That may seem surprising to those still thinking of mixed-reality wearables as a series of over-promises: Google Glass’s humiliating stumble; Snapchat’s low-selling Spectacles; Magic Leap’s epically late headset; and, um, the disappointing initial sales of Oculus’s own virtual-reality headsets. But you can write those off as baby steps, because all the big companies are going long on augmented reality. In 2018, you’ll see the building blocks on your mobile phones. These are just the earliest attempts at a new technology platform that will eventually have its unveiling as a mainstream, must-have wearable.
Indeed, an augmented reality Manhattan Project has become one of those things—like streaming video entertainment, search engines, and a phalanx of Washington lobbyists—that every self-respecting tech oligarch must have these days. And as far as the future is concerned, tech’s Big Five believe it may be the most important.
More Predictions for 2018 Sandra Upson Ricki Harris Rex Sorgatz There’s been an increasing consensus that artificial reality—the technology that tricks the senses into seeing, hearing, and interacting with digital objects and scenarios as if they are as substantial as the furniture we sit on and the people across from us—will become the Fourth Platform in computing. Each of the previous three uber-platforms, coming roughly every 15 years or so, has been an epochal event, offering an opportunity for reshuffling the power rankings of tech companies. And each threatened the existence of industry leaders blinded by the false sunshine of the Innovator’s Dilemma , which holds that the winners in one round of tech progress are too locked into their victories to bet on the next wave.
In the early eighties, personal computing destroyed mini-computer companies, and launched Apple and Microsoft. The mid-nineties saw the explosion of the internet, bushwhacking endless industries and spawning giants like Google and Amazon. The 2007 iPhone kicked off the mobile era; companies going all-in thrived, while those that came late to mobile (yes, I mean, you, Microsoft) suffered.
In the short run, we’re stuck with a landscape ruled by five behemoths (Microsoft has recovered enough to join the cabal). These companies appear so powerful that it would be easy to miss how fragile their futures may be. A new technology platform always forces a new round of musical chairs as the companies that are the first to recognize it and build the tools to support it dominate a new wave. Augmented reality is that new platform. (Some even call it the final computing platform, but that’s really reserved for the inevitable brain implant, which is easily another 15 years out.) Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Not every company working on post-reality glasses shares an identical vision; some have differing views of how immersive it should be. But all have quietly adopted the implicit assumption that a persistent, wearable artificial reality is the next big thing. The pressure of the competition has forced them to begin releasing interim products, now.
…And A Few More: Scott Rosenberg Alexis Sobel Fitts Steven Levy Erin Griffith When something doesn’t work, the companies can’t afford to give up. Look what happened at Google. One of the most humiliating missteps in its history was the botching of Glass, which started as a geek passion project and wound up as an object of ridicule. Instead of burying the incident, the company persisted. As I reported last summer , Glass is getting great reviews from serious businesses, like manufacturing and health care, giving Google’s parent company Alphabet an apparent edge in actually field-testing the glasses concept.
Microsoft might beg to differ. It has already released its own device, a more immersive headset called HoloLens.
And newer companies dedicated to augmented reality, such as Magic Leap (powered in part by a $350 million Google investment), are pushing the limits of the current science. But you can bet your Bitcoins that Amazon and Apple are also striving to be the Warby Parker of this new paradigm. Just check out some of Apple’s patents.
And earlier this month, Amazon joined the fray, introducing a new AWS service to help developers create applications in augmented and virtual reality. Available now in preview, it lets non-VR experts create “scenes” that run on a variety of devices, including Oculus, Gear and Google’s Daydream. Called Sumerian , after the seminal Mesopotamian civilization, it signals Amazon’s belief that its dominance in commerce will extend to an artificial world.
While we wait for the ultimate augmented reality glasses, 2018’s version of augmented reality involves layering information—from Harry Potter characters to Ikea furniture —onto the live images provided by your mobile phone camera. Apple, Microsoft, Google, and Facebook all are providing deep toolsets for developers to create apps for this approach.
All of those efforts are just a test run for the ultimate vision quest: a set of always-on glasses that will blur the line between the physical world and a digital contract made of pure information. The impact on society will be mind-boggling and, in some respects, troubling and even dangerous. But we’ve got maybe between 5 and 15 years to start arguing about those effects. Meanwhile, in secret labs around the world, tech oligarchs and wannabes are hard at work inventing a wave of computing that will literally be in your face. Like it or not, the next field of battle in tech is for your field of vision.
Editor at Large X Topics Backchannel augmented reality virtual reality Steven Levy Christopher Beam Samanth Subramanian Virginia Heffernan Amit Katwala Vauhini Vara Gideon Lichfield Lexi Pandell Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,024 | 2,019 |
"AI-Powered Apps Could Make Us More Creative—or Less Human | WIRED"
|
"https://www.wired.com/story/ai-powered-apps-more-creative-or-less-human"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Lauren Goode Gear AI-Powered Apps Could Make Us More Creative—or Less Human Andria Lo Save this story Save Save this story Save Application Personal services Text generation Company Microsoft Google Alphabet End User Consumer Sector Consumer services No worries! That’s the bot talking, offering a breezy response to a mildly apologetic email: Your coworker wants to reschedule a meeting? Sure thing! And they’ve proposed a new time? That works! If you’ve opted in to Gmail’s Smart Replies , these exchanges should look familiar. The AI-generated shortcuts at the bottom of an email promise effortless efficiency in exchange for a tiny piece of your digital humanity. But us humans are proving eager to make the trade: More than 10 percent of all replies on Gmail now start with a suggested Smart Reply.
Cool, thanks! The apps we rely on to stay productive at the office are being infused with ever larger helpings of artificial intelligence.
They’ve been getting smarter for awhile, but recent advances in cloud computing, neural networks, and deep learning have sped things up. “When we first did spam filtering in Gmail 14 years ago, we were using algorithms that were sophisticated at that time. Our AI techniques have changed a lot since then,” says Rajen Sheth, director of product management for Google Cloud AI. “Things like Smart Reply and Smart Compose have really brought this to the forefront.” Google’s Smart Compose is the show-off cousin of Smart Reply. It actually tries to complete phrases for you as you’re typing an email, and it’s uncannily good at predicting what you intend to say next. (“Thanks,” I started to write to a Google spokesperson. “This is really…” “helpful,” Smart Compose suggested.) Other products in G Suite, the company’s assortment of work-related apps, are peppered with assistive features, too. In Docs, the Explore tab uses machine learning to suggest documents, emails, or web links related to the topic you’re currently working on. The mobile version of Calendar lets you create goals, then automatically jams them into your schedule for you. Thanks to AI, you’re no longer sorry-too-swamped to file your travel expenses on time.
Microsoft , eager to shed its image as the stalwart provider of ho-hum desktop software, has been imbuing Office 365 with AI-powered features. Word now knows when you’re making a to-do list and tracks those items as … to-do items. PowerPoint uses computer vision and machine learning to color-match your slides with the hues in imported photos. And thanks to image recognition tech, you can snap a photo of a data table, import it into Excel, and end up with a fully editable table. Clippy was never so skilled.
Microsoft has suggested that the future of AI in the workplace may be one in which your email app can sense, by your tone, that you’re frustrated. But that doesn’t mean the company is hurrying to suggest email etiquette, or plans to ask if you’re really sure you want to hit Send. That’s partly because Microsoft says it wants people to remain the heroes of their work domains, for now. “The bigger part of our responsibility is figuring out how to keep the assistant in a more humble position, providing just a whisper of a recommendation,” says Ronette Lawrence, Microsoft’s AI planning and user research lead.
Related Stories Tech Reboot Lauren Goode How Tuesday Pia Ceres Digital Assistants Klint Finley Tech behemoths aren’t the only ones automating onerous office tasks. Cloud-first newcomers have been helping to establish what work looks like in the age of AI. Bots have become a near-essential part of Slack’s collaborative chat software; every so often a Slackbot will suggest you leave a channel you haven’t visited in awhile. The Seattle-based startup Textio is wielding machine learning to help recruiters and HR managers write more compelling job postings. Thanks to AI, the company has learned that using “AI” in an engineering job post is less effective than it used to be. “Big data”? So five years ago.
Perhaps because of this, Textio cofounder and chief executive Kieran Snyder, a natural language processing expert and former Microsoft product manager, prefers to call Textio an “augmented writing” platform. “There’s been a lot of stuff that’s aimed at making your work look pretty, or collaborate easily, but nothing that made words work better,” she says. Snyder claims the average time to fill an open job role is about 10 days shorter for clients who use “growth mindset” phrases suggested by Textio’s software.
Textio’s larger implications are staring users right in the face, no bot guidance needed: The tech doesn’t just speed up the hiring process, but also diversifies it.
The software recognizes phrases that tend to attract more women job applicants, and alternately, more men. For one Textio client, the phrase “work independently” has driven a 27 percent higher rate of job applicants who identify as women. Phrases like “ninja” or “rock star” skew more towards male applicants.
The question with AI-driven work tools, then, particularly ones engineered to identify potential biases , is whether they help solve for biases or perpetuate them. The answer is likely both. Plenty of computer scientists have determined that biases in AI algorithms are inevitable; machine learning models will simply adopt their human authors’ own worldviews. Relying on a bot to handle your messaging might seem like it would produce a neutral outcome, but like you the bot has its own baggage. Late last year, Google opted to remove gender-based pronouns from Smart Compose after a company researcher discovered, during a beta test, an email about an investor meeting defaulted to the pronoun “him.” (Google says the live version of Smart Compose never exhibited this bias.) Beyond that, AI-powered work apps raise questions around privacy (you knew your boss had system admin access to your work, but what does your bot know about you?) and the small matter of humanity. What do chats and emails, art forms in their earliest days, look like when we’re all exchanging the same rote AI-penned messages? Will our resumes be indistinguishable from one another? Will our slide decks all look the same? (OK, they already do.) Will WIRED articles drafted in AI-powered writing software all read the same? Microsoft’s Lawrence says she believes the opposite could prove true—that the more boring tasks AI can handle for us, the more free time we humans have to be creative.
Sounds good, thanks.
Lauren Goode (@laurengoode) is a senior writer at WIRED covering consumer tech.
This article appears in the March issue.
Subscribe now.
The AI text generator that's too dangerous to make public Women will dominate—and dismantle— music in 2019 A new tool protects videos from deepfakes and tampering Forget people, Elroy's self-flying drone hauls heavy cargo Glitches reveal Google Books' human scanners 👀 Looking for the latest gadgets? Check out our latest buying guides and best deals all year round 📩 Hungry for even more deep dives on your next favorite topic? Sign up for the Backchannel newsletter Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Senior Writer X Topics magazine-27.03 artificial intelligence Google Microsoft bias privacy Reece Rogers Scott Gilbertson Scott Gilbertson Virginia Heffernan Boone Ashworth Carlton Reid Boone Ashworth Boone Ashworth WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,025 | 2,023 |
"Where Memory Ends and Generative AI Begins | WIRED"
|
"https://www.wired.com/story/where-memory-ends-and-generative-ai-begins"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Lauren Goode Gear Where Memory Ends and Generative AI Begins Photograph: Tara Moore/Getty Images Save this story Save Save this story Save In late March, a well-funded artificial intelligence startup hosted what it said was the first ever AI film festival at the Alamo Drafthouse theater in San Francisco. The startup, called Runway , is best known for cocreating Stable Diffusion , the standout text-to-image AI tool that captured imaginations in 2022. In February of this year, Runway released a tool that could change the entire style of an existing video with just a simple prompt. Runway told budding filmmakers to have at it and later selected 10 short films to showcase at the fest.
The short films were mostly demonstrations of technology. Well-constructed narratives took a backseat. Some were surreal, and in at least one instance intentionally macabre. But the last film shown made the hair stand up on the back of my neck. It felt as though the filmmaker had deliberately misunderstood the assignment, eschewing video for still images. Called Expanded Childhood , the AI “film” was a slideshow of photos with a barely audible echo of narration.
Director Sam Lawton, a 21-year-old film student from Nebraska, later told me he used OpenAI’s DALL-E to alter the images. He assembled a series of photos from his childhood, fed them to the AI tool, and gave it various commands to expand the images: to fill in the edges with more cows, or trees; to insert people into the frame who hadn’t really been there; to reimagine what the kitchen looked like. Toss another puppy into the bathtub—why not? Lawton showed the AI-generated images to his father, recorded his befuddled reactions, and inserted the audio into the film.
“No, that’s not our house.
Wow —wait a minute. That’s our house. Something’s wrong. I don’t know what that is. Do I just not remember it?” Lawton’s father can be heard saying.
Where do real memories end and generative AI begin? It’s a question for the AI era, where our holy photos merge with holey memories, where new pixels are generated whole cloth by artificial intelligence. Over the past few weeks, tech giants Google and Adobe , whose tools collectively reach billions of fingertips, have released AI-powered editing tools that completely change the context of images, pushing the boundaries of truth, memory, and enhanced photography.
Google dipped its toes in the water with the release of Magic Eraser in 2021. Now the company is testing Magic Editor , a feature on select Android phones that repositions subjects, removes photobombers, and edits out other unseemly elements, then uses generative AI to fill in pixel gaps. Adobe, arguably the most famous maker of creative editing software, announced earlier this week that it was putting its generative AI engine Firefly into Adobe Photoshop. The aptly named Generative Fill feature will edit photos and insert new content via a text-based prompt. Type in “add some clouds” and there they appear.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Adobe is calling it a “co-pilot” for creative workflows, which parrots the phrasing that other tech companies, such as Microsoft, are using to describe generative AI apps. It implies that you are still in total control. In this framing AI is offering an assist, taking over navigation when you need a bathroom break. This is something of a misportrayal when the AI is actually acting as a cartographer, redrawing the maps of your existence.
“‘Perfect your memories’ is perhaps the most haunting phrase I’ve ever read,” Signal Foundation president and former Googler Meredith Whittaker tweeted in February, in response to Google’s announcement that its Magic Eraser tool would become available to a wider range of phones.
In its marketing of the tool, Google shows an image of a young girl facing a choppy sea. Nearer to the shoreline is a family of four, presumably not hers. Magic Eraser disappears them.
Let’s be totally clear: We could always edit photos. Whether by scissor, razor, or paint, as long as the printed photo has existed, we’ve edited. Photoshop’s provenance was timed to the rise of the personal computer, which, non-hyperbolically speaking, changed everything.
The first version of Photoshop launched in 1990. “Jennifer in Paradise” was the digital photo seen around the world: an image of Photoshop cocreator John Knoll’s wife sitting on a beach in Bora Bora. In demos, Knoll would outline his wife using the now-famous lasso tool, then clone her. He copied, pasted, shrank, and diffused an island in the distance. “A duplicate island!” Knoll said in a video posted to Adobe’s YouTube channel in 2010. An island that was not really there. A fabricated land mass.
Something Blue Lauren Goode Robo Promos Paresh Dave State of the Art Madeline Ashby Ideas Rumman Chowdhury What’s different today—what generative AI is pushing boundaries on—is the speed with which these edits can be made and who can make them. “Editing tools have existed for a long time,” says Shimrit Ben-Yair, the head of Google Photos. “And obviously we’ve been offering editing tools on Photos for a while now. As these platforms have grown their user bases, these tools become much more accessible and available to people. And edited images become more common.” A early demonstration of Google’s Magic Eraser tool features two kids sporting wetsuits and boogie boards, with two adults in the distant background. The kids and adults have different skin tones, and the somewhat uncomfortable assumption in this demo—also emphasized by the distance between them—is that they are not family. Google’s Magic Eraser outlined the adults in the background, then disappeared them.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft In a newer demo, Magic Editor, which ships later this year, erased the bag strap from a woman’s shoulder as she posed in front of a waterfall, then filled in the gaps with more jacket material. Why the bag strap in a hiking photo was so bothersome, I do not know. But those aesthetic decisions are the prerogative of the photo’s creator, Google says.
Adobe’s Generative Fill is much more, well, generative. A long-haired corgi scampers down an empty road. That’s it, that’s the photo. But Generative Fill lengthens the road. It transforms barren trees into a springtime bloom. A white pickup truck appears, and whether it’s driving toward the corgi or away from it changes the tension of the photo in a notable way. But, look, now there are puddles. Surely that’s a happy photo? Generative AI is even smart enough to draft a reflection of the scampering pup in the puddles. It does this all in seconds. I’m blown away.
But after the astonishment comes “What now?” Suppose that is my hiking photo, my dog, my family on the beach. How will I remember that day if in the future they are only watercolor in my brain, and I increasingly turn to my photo roll for more vivid strokes? Did I actually not carry a bag while hiking? Did the pickup truck come dangerously close to my dog that day? Did I only ever vacation on pristine, private beaches? Executives at both Google and Adobe say the power of the tools must be considered within the context of the photo. Who is taking it, who is sharing it, where it’s being shared to. “I think in the context of a public space, there are different expectations than that of a photo being shared in a private space,” says Ben-Yair. “If someone is sharing a photo with you via Google Photos itself or a messaging app that you use, you trust that source. And you might see the editing as something that enhances the photo, because you trust that source.” “But the more layers of abstraction there are,” she continues, “Where you don’t know the source, then yeah, you have to think through, how authentic is this photo?” Similarly, Andy Parsons of Adobe says there’s a “continuum of use cases” for AI-edited photos. An artist (or individual who fancies themself an artist) might use generative AI to alter a photo that’s meant to be a creative interpretation, not documentation. On the other hand, “if it’s very critically important to know that what’s being presented in the photo is a reflection of reality, such as in a news organization, we expect to see more and more photographers being required to provide transparency,” Parsons says.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Parsons is something like the king of provenance at Adobe. His actual title is senior director of the Content Authenticity Initiative, a group Adobe cocreated in 2019 to establish cross-industry guidelines around content origination and media transparency. It was the doctored Nancy Pelosi video , Parsons says, in which the Speaker of the House appeared to be slurring her words, that “again, changed history.” Even though the editing wasn’t credited to AI, the sheer manipulation of the Pelosi video made Adobe reconsider how its powerful editing tools might be used. Adobe’s earliest partners in the CAI were Twitter and The New York Times.
The Coalition now has more than a thousand members across various industries.
Then, in 2021, Adobe joined forces with the BBC, chip-makers Intel and ARM, and Microsoft to create yet another consortium for standards around “digital provenance,” called Coalition for Content Provenance and Authenticity, or C2PA.
At Microsoft’s annual software conference this week, the company said that its Bing Image Creator will soon use C2PA-standard cryptographic methods to sign AI-generated content. (Google’s Ben-Yair also says this is an “active area of work for the company that we’re going to explain once we get closer to the launch of it.”) “We’re all focused on the same idea,” Parsons says. “We’ve kind of lost the arms race in detecting what may be fake. The chasm has been crossed. So the protection and countermeasure we have is knowing what model was used to capture or create an image and to make that metadata trustworthy.” In theory, these cryptographic standards ensure that if a professional photographer snaps a photo for, say, Reuters and that photo is distributed across Reuters international news channels, both the editors commissioning the photo and the consumers viewing it would have access to a full history of provenance data. They’ll know if shadows were punched up, if police cars were removed, if someone was cropped out of the frame. Elements of photos that, according to Parsons, you’d want to be cryptographically provable and verifiable.
Of course, all of this is predicated on the notion that we—the people who look at photos—will want to, or care to, or know how to, verify the authenticity of a photo. It assumes that we are able to distinguish between social and culture and news, and that those categories are clearly defined. Transparency is great, sure; I still fell for Balenciaga Pope. The image of Pope Francis wearing a stylish jacket was first posted in the subreddit r/Midjourney as a kind of meme, spread amongst Twitter users and then picked up by news outlets reporting on the virality and implications of the AI-generated image. Art, social, news—all were equally blessed by the Pope. We now know it’s fake, but Balenciaga Pope will live forever in our brains.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft After seeing Magic Editor, I tried to articulate something to Shimrit Ben-Yair without assigning a moral value to it, which is to say I prefaced my statement with, “I’m trying to not assign a moral value to this.” It is remarkable, I said, how much control of our future memories is in the hands of giant tech companies right now simply because of the tools and infrastructure that exist to record so much of our lives.
Ben-Yair paused a full five seconds before responding. “Yeah, I mean … I think people trust Google with their data to safeguard. And I see that as a very, very big responsibility for us to carry.” It was a forgettable response, but thankfully, I was recording. On a Google app.
After Adobe unveiled Generative Fill this week, I wrote to Sam Lawton, the filmmaker behind Expanded Childhood , to ask if he planned to use it. He’s still partial to AI image generators like Midjourney and DALL-E 2, he wrote, but sees the usefulness of Adobe integrating generative AI directly into its most popular editing software.
“There’s been discourse on Twitter for a while now about how AI is going to take all graphic designer jobs, usually referencing smaller Gen AI companies that can generate logos and what not,” Lawton says. “In reality, it should be pretty obvious that a big player like Adobe would come in and give these tools straight to the designers to keep them within their ecosystem.” As for his short film, he says the reception to it has been “interesting,” in that it has resonated with people much more than he thought it would. He’d thought the AI-distorted faces, the obvious fakeness of a few of the stills, compounded with the fact that it was rooted in his own childhood, would create a barrier to people connecting with the film. “From what I’ve been told repeatedly, though, the feeling of nostalgia, combined with the uncanny valley, has leaked through into the viewer’s own experience,” he says.
Lawton tells me he has found the process of being able to see more context around his foundational memories to be therapeutic, even when the AI-generated memory wasn’t entirely true.
Update, May 26 at 11:00 am: An earlier version of this story said Magic Eraser could be used in videos; that's an error and has been corrected. Also, the recounting of two separate Google product demos has been edited to clarify which specific features were shown in each demo.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Senior Writer X Topics photoshop Memories Photography artificial intelligence Google Adobe Reece Rogers Boone Ashworth Carlton Reid Scott Gilbertson Scott Gilbertson Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,026 | 2,023 |
"GPT-4 Will Make ChatGPT Smarter but Won't Fix Its Flaws | WIRED"
|
"https://www.wired.com/story/gpt-4-openai-will-make-chatgpt-smarter-but-wont-fix-its-flaws"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Knight Business GPT-4 Will Make ChatGPT Smarter but Won't Fix Its Flaws Photograph: jayk7/Getty Images Save this story Save Save this story Save With its uncanny ability to hold a conversation, answer questions, and write coherent prose, poetry, and code, the chatbot ChatGPT has forced many people to rethink the potential of artificial intelligence.
The startup that made ChatGPT, OpenAI , today announced a much-anticipated new version of the AI model at its core.
The new algorithm, called GPT-4 , follows GPT-3, a groundbreaking text-generation model that OpenAI announced in 2020 , which was later adapted to create ChatGPT last year.
The new model scores more highly on a range of tests designed to measure intelligence and knowledge in humans and machines, OpenAI says. It also makes fewer blunders and can respond to images as well as text.
However, GPT-4 suffers from the same problems that have bedeviled ChatGPT and cause some AI experts to be skeptical of its usefulness—including tendencies to “hallucinate” incorrect information, exhibit problematic social biases, and misbehave or assume disturbing personas when given an “adversarial” prompt.
“While they’ve made a lot of progress, it’s clearly not trustworthy,” says Oren Etzioni, a professor emeritus at the University of Washington and the founding CEO of the Allen Institute for AI.
“It’s going to be a long time before you want any GPT to run your nuclear power plant.” OpenAI provided several demos and data from benchmarking tests to show GPT-4’s capabilities. The new model can not only beat the passing score on the Uniform Bar Examination, which is used to qualify lawyers in many US states, but it got a score in the top 10 percent of those of humans.
It also scores more highly than GPT-3 on other exams designed to test knowledge and reasoning, in subjects including biology, art history, and calculus. And it gets better marks than any other AI language model on tests designed by computer scientists to gauge progress in such algorithms. “In some ways it’s more of the same,” Etzioni says. “But it’s more of the same in an absolutely mind-blowing series of advances.” GPT-4 can also perform neat tricks seen before from GPT-3 and ChatGPT, like summarizing and suggesting edits to pieces of text. It can also do things its predecessors could not, including acting as a Socratic tutor that helps guide students toward correct answers and discussing the contents of photographs. For example, if provided a photo of ingredients on a kitchen counter, GPT-4 can suggest an appropriate recipe. If provided with a chart, it can explain the conclusions that can be drawn from it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “It definitely seems to have gained some abilities,” says Vincent Conitzer , a professor at CMU who specializes in AI and who has begun experimenting with the new language model. But he says it still makes errors, such as suggesting nonsensical directions or presenting fake mathematical proofs.
ChatGPT caught the public’s attention with a stunning ability to tackle many complex questions and tasks via an easy-to-use conversational interface. The chatbot does not understand the world as humans do and just responds with words it statistically predicts should follow a question.
But that underlying mechanism also means that ChatGPT and systems like it will often make up facts. And despite OpenAI’s efforts to make the model resistant to abuse, it can be prompted into misbehaving, for example by suggesting it role-play doing something it refuses to do when asked directly. OpenAI says GPT-4 is 40 percent more likely to provide “factual responses” and says that GPT-4 is 82 percent less likely to respond to requests that should be disallowed. The company did not say how often the previous version, GPT-3, provides factually incorrect responses or responds to requests it should reject.
Still, Ilya Sutskever, cofounder and chief scientist at OpenAI, claims those as perhaps the most significant advances with the new model. “The thing that stands in the way of ChatGPT being really useful to many people for many tasks is reliability,” he says. “GPT-4 isn't there yet, but it is a lot closer.” Conitzer at CMU says GPT-4 appears to include new guardrails that prevent it from generating undesirable responses but adds that its new capabilities may lead to new ways of exploiting it.
The arrival of GPT-4 has been long anticipated in tech circles, including with vigorous meme-making about the unreleased software’s potential powers. It arrives at a heady moment for the tech industry, which has been jolted by the arrival of ChatGPT into renewed expectation of a new era of computing powered by AI.
Inspired by the potential of ChatGPT, Microsoft invested $10 billion in OpenAI this January. The following month it showed off an upgrade of its search engine Bing that uses ChatGPT to collate information and answer complex questions. Last year Microsoft released a coding tool that uses GPT to auto-complete chunks of code for a programmer.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The furor around the chatbot has also stoked interest in new startups building or using similar AI technology and has left some companies feeling flat-footed.
Google , which has spent years investing in AI research and which invented some of the key algorithms used to build GPT and ChatGPT, is scrambling to catch up. OpenAI’s research paper on GPT-4 discloses few details of how GPT-4 was built or how it works, citing the competition around these new AI tools as well as the risks they pose.
This week Google announced an API and new developer tools for a text-generating model of its own, called PaLM, which functions similarly to OpenAI’s GPT. Google is also testing a chatbot to compete with ChatGPT called Bard and has said that it will use the underlying technology to improve search.
OpenAI says a version of ChatGPT that uses GPT-4 is available for paid users of the chatbot, and the company will gradually make the new language model available through its API.
The capabilities of ChatGPT and similar AI programs have stirred debate around how AI may automate or revolutionize some office jobs.
More advanced iterations may be able to take on new skills. However, Etzioni is keen to emphasize that—impressive though GPT-4 is—there are still countless things that humans take for granted that it cannot do. “We have to remember that, however eloquent ChatGPT is, it's still just a chatbot,” he says.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Senior Writer X Topics artificial intelligence machine learning deep learning algorithms neural networks bots ChatGPT OpenAI Will Knight Khari Johnson Will Bedingfield Khari Johnson Khari Johnson Aarian Marshall Niamh Rowe Peter Guest Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,027 | 2,023 |
"New models and developer products announced at DevDay"
|
"https://openai.com/blog/new-models-and-developer-products-announced-at-devday"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Blog New models and developer products announced at DevDay GPT-4 Turbo with 128K context and lower prices, the new Assistants API, GPT-4 Turbo with Vision, DALL·E 3 API, and more.
November 6, 2023 Authors OpenAI Announcements , Product Today, we shared dozens of new additions and improvements, and reduced pricing across many parts of our platform. These include: New GPT-4 Turbo model that is more capable, cheaper and supports a 128K context window New Assistants API that makes it easier for developers to build their own assistive AI apps that have goals and can call models and tools New multimodal capabilities in the platform, including vision, image creation (DALL·E 3), and text-to-speech (TTS) We’ll begin rolling out new features to OpenAI customers starting at 1pm PT today.
Learn more about OpenAI DevDay announcements for ChatGPT.
GPT-4 Turbo with 128K context We released the first version of GPT-4 in March and made GPT-4 generally available to all developers in July. Today we’re launching a preview of the next generation of this model, GPT-4 Turbo.
GPT-4 Turbo is more capable and has knowledge of world events up to April 2023. It has a 128k context window so it can fit the equivalent of more than 300 pages of text in a single prompt. We also optimized its performance so we are able to offer GPT-4 Turbo at a 3x cheaper price for input tokens and a 2x cheaper price for output tokens compared to GPT-4.
GPT-4 Turbo is available for all paying developers to try by passing gpt-4-1106-preview in the API and we plan to release the stable production-ready model in the coming weeks.
Function calling updates Function calling lets you describe functions of your app or external APIs to models, and have the model intelligently choose to output a JSON object containing arguments to call those functions. We’re releasing several improvements today, including the ability to call multiple functions in a single message: users can send one message requesting multiple actions, such as “open the car window and turn off the A/C”, which would previously require multiple roundtrips with the model ( learn more ). We are also improving function calling accuracy: GPT-4 Turbo is more likely to return the right function parameters.
Improved instruction following and JSON mode GPT-4 Turbo performs better than our previous models on tasks that require the careful following of instructions, such as generating specific formats (e.g., “always respond in XML”). It also supports our new JSON mode , which ensures the model will respond with valid JSON. The new API parameter response_format enables the model to constrain its output to generate a syntactically correct JSON object. JSON mode is useful for developers generating JSON in the Chat Completions API outside of function calling.
Reproducible outputs and log probabilities The new seed parameter enables reproducible outputs by making the model return consistent completions most of the time. This beta feature is useful for use cases such as replaying requests for debugging, writing more comprehensive unit tests, and generally having a higher degree of control over the model behavior. We at OpenAI have been using this feature internally for our own unit tests and have found it invaluable. We’re excited to see how developers will use it.
Learn more.
We’re also launching a feature to return the log probabilities for the most likely output tokens generated by GPT-4 Turbo and GPT-3.5 Turbo in the next few weeks, which will be useful for building features such as autocomplete in a search experience.
Updated GPT-3.5 Turbo In addition to GPT-4 Turbo, we are also releasing a new version of GPT-3.5 Turbo that supports a 16K context window by default. The new 3.5 Turbo supports improved instruction following, JSON mode, and parallel function calling. For instance, our internal evals show a 38% improvement on format following tasks such as generating JSON, XML and YAML. Developers can access this new model by calling gpt-3.5-turbo-1106 in the API. Applications using the gpt-3.5-turbo name will automatically be upgraded to the new model on December 11. Older models will continue to be accessible by passing gpt-3.5-turbo-0613 in the API until June 13, 2024.
Learn more.
Assistants API, Retrieval, and Code Interpreter Today, we’re releasing the Assistants API , our first step towards helping developers build agent-like experiences within their own applications. An assistant is a purpose-built AI that has specific instructions, leverages extra knowledge, and can call models and tools to perform tasks. The new Assistants API provides new capabilities such as Code Interpreter and Retrieval as well as function calling to handle a lot of the heavy lifting that you previously had to do yourself and enable you to build high-quality AI apps.
This API is designed for flexibility; use cases range from a natural language-based data analysis app, a coding assistant, an AI-powered vacation planner, a voice-controlled DJ, a smart visual canvas—the list goes on. The Assistants API is built on the same capabilities that enable our new GPTs product : custom instructions and tools such as Code interpreter, Retrieval, and function calling.
A key change introduced by this API is persistent and infinitely long threads , which allow developers to hand off thread state management to OpenAI and work around context window constraints. With the Assistants API, you simply add each new message to an existing thread.
Assistants also have access to call new tools as needed, including: Code Interpreter : writes and runs Python code in a sandboxed execution environment, and can generate graphs and charts, and process files with diverse data and formatting. It allows your assistants to run code iteratively to solve challenging code and math problems, and more.
Retrieval : augments the assistant with knowledge from outside our models, such as proprietary domain data, product information or documents provided by your users. This means you don’t need to compute and store embeddings for your documents, or implement chunking and search algorithms. The Assistants API optimizes what retrieval technique to use based on our experience building knowledge retrieval in ChatGPT.
Function calling : enables assistants to invoke functions you define and incorporate the function response in their messages.
As with the rest of the platform, data and files passed to the OpenAI API are never used to train our models and developers can delete the data when they see fit.
You can try the Assistants API beta without writing any code by heading to the Assistants playground.
The Assistants API is in beta and available to all developers starting today. Please share what you build with us ( @OpenAI ) along with your feedback which we will incorporate as we continue building over the coming weeks. Pricing for the Assistants APIs and its tools is available on our pricing page.
New modalities in the API GPT-4 Turbo with vision GPT-4 Turbo can accept images as inputs in the Chat Completions API, enabling use cases such as generating captions, analyzing real world images in detail, and reading documents with figures. For example, BeMyEyes uses this technology to help people who are blind or have low vision with daily tasks like identifying a product or navigating a store. Developers can access this feature by using gpt-4-vision-preview in the API. We plan to roll out vision support to the main GPT-4 Turbo model as part of its stable release.
Pricing depends on the input image size. For instance, passing an image with 1080×1080 pixels to GPT-4 Turbo costs $0.00765. Check out our vision guide.
DALL·E 3 Developers can integrate DALL·E 3, which we recently launched to ChatGPT Plus and Enterprise users, directly into their apps and products through our Images API by specifying dall-e-3 as the model. Companies like Snap, Coca-Cola, and Shutterstock have used DALL·E 3 to programmatically generate images and designs for their customers and campaigns. Similar to the previous version of DALL·E, the API incorporates built-in moderation to help developers protect their applications against misuse. We offer different format and quality options, with prices starting at $0.04 per image generated. Check out our guide to getting started with DALL·E 3 in the API.
Text-to-speech (TTS) Developers can now generate human-quality speech from text via the text-to-speech API. Our new TTS model offers six preset voices to choose from and two model variants, tts-1 and tts-1-hd.
tts is optimized for real-time use cases and tts-1-hd is optimized for quality. Pricing starts at $0.015 per input 1,000 characters. Check out our TTS guide to get started.
Listen to voice samples Select text As the golden sun dips below the horizon, casting long shadows across the tranquil meadow, the world seems to hush, and a sense of calmness envelops the Earth, promising a peaceful night’s rest for all living beings.
Select voice Model customization GPT-4 fine tuning experimental access We’re creating an experimental access program for GPT-4 fine-tuning.
Preliminary results indicate that GPT-4 fine-tuning requires more work to achieve meaningful improvements over the base model compared to the substantial gains realized with GPT-3.5 fine-tuning. As quality and safety for GPT-4 fine-tuning improves, developers actively using GPT-3.5 fine-tuning will be presented with an option to apply to the GPT-4 program within their fine-tuning console.
Custom models For organizations that need even more customization than fine-tuning can provide (particularly applicable to domains with extremely large proprietary datasets—billions of tokens at minimum), we’re also launching a Custom Models program , giving selected organizations an opportunity to work with a dedicated group of OpenAI researchers to train custom GPT-4 to their specific domain. This includes modifying every step of the model training process, from doing additional domain specific pre-training, to running a custom RL post-training process tailored for the specific domain. Organizations will have exclusive access to their custom models. In keeping with our existing enterprise privacy policies, custom models will not be served to or shared with other customers or used to train other models. Also, proprietary data provided to OpenAI to train custom models will not be reused in any other context. This will be a very limited (and expensive) program to start—interested orgs can apply here.
Lower prices and higher rate limits Lower prices We’re decreasing several prices across the platform to pass on savings to developers (all prices below are expressed per 1,000 tokens): GPT-4 Turbo input tokens are 3x cheaper than GPT-4 at $0.01 and output tokens are 2x cheaper at $0.03.
GPT-3.5 Turbo input tokens are 3x cheaper than the previous 16K model at $0.001 and output tokens are 2x cheaper at $0.002. Developers previously using GPT-3.5 Turbo 4K benefit from a 33% reduction on input tokens at $0.001. Those lower prices only apply to the new GPT-3.5 Turbo introduced today.
Fine-tuned GPT-3.5 Turbo 4K model input tokens are reduced by 4x at $0.003 and output tokens are 2.7x cheaper at $0.006. Fine-tuning also supports 16K context at the same price as 4K with the new GPT-3.5 Turbo model. These new prices also apply to fine-tuned gpt-3.5-turbo-0613 models.
Older models New models GPT-4 Turbo GPT-4 8K Input: $0.03 Output: $0.06 GPT-4 32K Input: $0.06 Output: $0.12 GPT-4 Turbo 128K Input: $0.01 Output: $0.03 GPT-3.5 Turbo GPT-3.5 Turbo 4K Input: $0.0015 Output: $0.002 GPT-3.5 Turbo 16K Input: $0.003 Output: $0.004 GPT-3.5 Turbo 16K Input: $0.001 Output: $0.002 GPT-3.5 Turbo fine-tuning GPT-3.5 Turbo 4K fine-tuning Training: $0.008 Input: $0.012 Output: $0.016 GPT-3.5 Turbo 4K and 16K fine-tuning Training: $0.008 Input: $0.003 Output: $0.006 Higher rate limits To help you scale your applications, we’re doubling the tokens per minute limit for all our paying GPT-4 customers. You can view your new rate limits in your rate limit page.
We’ve also published our usage tiers that determine automatic rate limits increases, so you know what to expect in how your usage limits will automatically scale. You can now request increases to usage limits from your account settings.
Copyright Shield OpenAI is committed to protecting our customers with built-in copyright safeguards in our systems. Today, we’re going one step further and introducing Copyright Shield—we will now step in and defend our customers, and pay the costs incurred, if you face legal claims around copyright infringement. This applies to generally available features of ChatGPT Enterprise and our developer platform.
Whisper v3 and Consistency Decoder We are releasing Whisper large-v3, the next version of our open source automatic speech recognition model (ASR) which features improved performance across languages. We also plan to support Whisper v3 in our API in the near future.
We are also open sourcing the Consistency Decoder , a drop in replacement for the Stable Diffusion VAE decoder. This decoder improves all images compatible with the by Stable Diffusion 1.0+ VAE, with significant improvements in text, faces and straight lines.
Learn more about our OpenAI DevDay announcements for ChatGPT.
Authors OpenAI View all articles Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,028 | 2,023 |
"Introducing GPTs"
|
"https://openai.com/blog/introducing-gpts"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Blog Introducing GPTs You can now create custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills.
November 6, 2023 Authors OpenAI Announcements , Product We’re rolling out custom versions of ChatGPT that you can create for a specific purpose—called GPTs. GPTs are a new way for anyone to create a tailored version of ChatGPT to be more helpful in their daily life, at specific tasks, at work, or at home—and then share that creation with others. For example, GPTs can help you learn the rules to any board game, help teach your kids math, or design stickers.
Anyone can easily build their own GPT—no coding is required. You can make them for yourself, just for your company’s internal use, or for everyone. Creating one is as easy as starting a conversation, giving it instructions and extra knowledge, and picking what it can do, like searching the web, making images or analyzing data. Try it out at chat.openai.com/create.
Example GPTs are available today for ChatGPT Plus and Enterprise users to try out including Canva and Zapier AI Actions.
We plan to offer GPTs to more users soon.
Learn more about our OpenAI DevDay announcements for new models and developer products.
GPTs let you customize ChatGPT for a specific purpose Since launching ChatGPT people have been asking for ways to customize ChatGPT to fit specific ways that they use it. We launched Custom Instructions in July that let you set some preferences, but requests for more control kept coming. Many power users maintain a list of carefully crafted prompts and instruction sets, manually copying them into ChatGPT. GPTs now do all of that for you.
The best GPTs will be invented by the community We believe the most incredible GPTs will come from builders in the community. Whether you’re an educator, coach, or just someone who loves to build helpful tools, you don’t need to know coding to make one and share your expertise.
The GPT Store is rolling out later this month Starting today, you can create GPTs and share them publicly. Later this month, we’re launching the GPT Store, featuring creations by verified builders. Once in the store, GPTs become searchable and may climb the leaderboards. We will also spotlight the most useful and delightful GPTs we come across in categories like productivity, education, and “just for fun”. In the coming months, you’ll also be able to earn money based on how many people are using your GPT.
We built GPTs with privacy and safety in mind As always, you are in control of your data with ChatGPT. Your chats with GPTs are not shared with builders. If a GPT uses third party APIs, you choose whether data can be sent to that API. When builders customize their own GPT with actions or knowledge, the builder can choose if user chats with that GPT can be used to improve and train our models. These choices build upon the existing privacy controls users have, including the option to opt your entire account out of model training.
We’ve set up new systems to help review GPTs against our usage policies.
These systems stack on top of our existing mitigations and aim to prevent users from sharing harmful GPTs, including those that involve fraudulent activity, hateful content, or adult themes. We’ve also taken steps to build user trust by allowing builders to verify their identity. We'll continue to monitor and learn how people use GPTs and update and strengthen our safety mitigations. If you have concerns with a specific GPT, you can also use our reporting feature on the GPT shared page to notify our team.
GPTs will continue to get more useful and smarter, and you’ll eventually be able to let them take on real tasks in the real world. In the field of AI, these systems are often discussed as “agents”. We think it’s important to move incrementally towards this future, as it will require careful technical and safety work—and time for society to adapt. We have been thinking deeply about the societal implications and will have more analysis to share soon.
Developers can connect GPTs to the real world In addition to using our built-in capabilities, you can also define custom actions by making one or more APIs available to the GPT. Like plugins, actions allow GPTs to integrate external data or interact with the real-world. Connect GPTs to databases, plug them into emails, or make them your shopping assistant. For example, you could integrate a travel listings database, connect a user’s email inbox, or facilitate e-commerce orders.
The design of actions builds upon insights from our plugins beta, granting developers greater control over the model and how their APIs are called. Migrating from the plugins beta is easy with the ability to use your existing plugin manifest to define actions for your GPT.
Enterprise customers can deploy internal-only GPTs Since we launched ChatGPT Enterprise a few months ago, early customers have expressed the desire for even more customization that aligns with their business. GPTs answer this call by allowing you to create versions of ChatGPT for specific use cases, departments, or proprietary datasets. Early customers like Amgen, Bain, and Square are already leveraging internal GPTs to do things like craft marketing materials embodying their brand, aid support staff with answering customer questions, or help new software engineers with onboarding.
Enterprises can get started with GPTs on Wednesday. You can now empower users inside your company to design internal-only GPTs without code and securely publish them to your workspace. The admin console lets you choose how GPTs are shared and whether external GPTs may be used inside your business. Like all usage on ChatGPT Enterprise, we do not use your conversations with GPTs to improve our models.
We want more people to shape how AI behaves We designed GPTs so more people can build with us. Involving the community is critical to our mission of building safe AGI that benefits humanity. It allows everyone to see a wide and varied range of useful GPTs and get a more concrete sense of what’s ahead. And by broadening the group of people who decide 'what to build' beyond just those with access to advanced technology it's likely we'll have safer and better aligned AI. The same desire to build with people, not just for them, drove us to launch the OpenAI API and to research methods for incorporating democratic input into AI behavior, which we plan to share more about soon.
We’ve made ChatGPT Plus fresher and simpler to use Finally, ChatGPT Plus now includes fresh information up to April 2023. We’ve also heard your feedback about how the model picker is a pain. Starting today, no more hopping between models; everything you need is in one place. You can access DALL·E, browsing, and data analysis all without switching. You can also attach files to let ChatGPT search PDFs and other document types. Find us at chatgpt.com.
Learn more about OpenAI DevDay announcements for new models and developer products.
Authors OpenAI View all articles Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,029 | 2,023 |
"The Pope’s Coat Is Here to Ruin Your Faith | WIRED"
|
"https://www.wired.com/story/pope-coat-artificial-intelligence-internet-trust"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Angela Watercutter Culture The Pope’s Coat Is Here to Ruin Your Faith Photograph: Antonio Masiello/Getty Images Save this story Save Save this story Save The Monitor is a weekly column devoted to everything happening in the WIRED world of culture, from movies to memes, TV to Twitter.
Future generations will acknowledge the vibe shift. It happened last weekend, when all of a sudden social media feeds filled with images of Pope Francis, typically a pious and plain dude, looking like a boss in a sleek white puffer coat. It was instantly a meme, a LOL in a sea of bad news. It was also not real. Someone created the image using the artificial intelligence tool Midjourney. But it fooled a lot of people—so many that news outlets began calling it “one of the first instances of wide-scale misinformation stemming from artificial intelligence.” Reality Check Reece Rogers Art Official Angela Watercutter Ideas Joshua Glick Just typing that sentence feels haunting. Like the first time you see someone in a red cloak in The Handmaid’s Tale.
Not that this portends dystopia. It was, after all, just one image of the pope looking fly. But what if it was an image declaring itself to be a battlefield in the war in Ukraine? Or of President Biden taking some kind of secret meeting? The possibilities of AI generating that kind of misinformation are daunting.
Getting scores of people to fall for a disastrous deepfake of Volodymyr Zelensky takes a little more work than misleading them with a goofy picture of a pontiff, of course. As Charlie Warzel pointed out in The Atlantic this week, everyone uses “different heuristics to try to suss out truth,” and it’s easier to believe Pope Francis would wear a puffer than that, say, those AI images of former president Donald Trump getting arrested are real. So it’s not hard to see why so many just saw them, giggled, and kept scrolling without questioning their authenticity.
But this does set a troubling precedent. The creator of the Pope Coat image wasn’t attempting to mislead anyone. In fact, he told BuzzFeed News he was just tripping on shrooms and trying to think of funny images. But what if it was part of a misinformation campaign? A lot of AI-generated content is already so clean that it’s hard for human eyes and ears to detect its origins.
Viewers would probably never have known that Anthony Bourdain’s voice was faked in the documentary Roadrunner if director Morgan Neville hadn’t told The New Yorker.
Deepfakes are already being used as political tools.
As it is, skeptics can consult trusted news sources if they suspect an image is fake, but trust in the news media is already approaching record lows.
If anyone can now generate an image of anything, and faith in any source that might debunk that image is at an all-time low, who is going to believe their lying eyes? A few days after the AI-generated images of Pope Francis went viral, the pontiff was taken to a hospital in Rome for a respiratory infection.
He’s been improving ever since, but as that (real) news spread, it got a bit lost amidst stories of the fake image. The pope was trending for two very different reasons, and at first glance it was hard to determine which was the one of substance.
The era of social media has transformed the Very Online into pretty good sleuths. Skepticism reigns. But so do conspiracy theories. Beyond the post-truth era is a time when convincing images, text, and even video can be generated from thin air. One of the internet’s great promises was that anyone could broadcast information to a much larger audience than before. For years, the liars have been easier to spot: bad URLs, shitty photoshop, typos—all these things gave the scoundrels away. AI can smooth their mistakes. I’m not Chicken Little, but maybe I just haven’t yet been fooled by an image of the falling sky.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Senior Editor X Tumblr Topics The Monitor fake news memes artificial intelligence Angela Watercutter Alex Winter Angela Watercutter Angela Watercutter Kate Knibbs Kate Knibbs Jason Parham Kate Knibbs Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,030 | 2,022 |
"What AI-Generated Art Really Means for Human Creativity | WIRED"
|
"https://www.wired.com/story/picture-limitless-creativity-ai-image-generators"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Kevin Kelly Backchannel Picture Limitless Creativity at Your Fingertips ILLUSTRATION: OFF-SITE RESEARCH FACILITY Save this story Save Save this story Save End User Big company Consumer Small company Sector Entertainment Publishing Video Source Data Images Text Video Technology Machine learning Machine vision Natural language processing Neural Network Picture Lee Unkrich, one of Pixar’s most distinguished animators, as a seventh grader. He’s staring at an image of a train locomotive on the screen of his school’s first computer.
Wow , he thinks. Some of the magic wears off, however, when Lee learns that the image had not appeared simply by asking for “a picture of a train.” Instead, it had to be painstakingly coded and rendered—by hard-working humans.
Now picture Lee 43 years later, stumbling onto DALL-E, an artificial intelligence that generates original works of art based on human-supplied prompts that can literally be as simple as “a picture of a train.” As he types in words to create image after image, the wow is back. Only this time, it doesn’t go away. “It feels like a miracle,” he says.
“When the results appeared, my breath was taken away and tears welled in my eyes. It’s that magical.” Lessons from the History of Photography Classic WIRED Covers—Regenerated by AI Our machines have crossed a threshold. All our lives, we have been reassured that computers were incapable of being truly creative. Yet, suddenly, millions of people are now using a new breed of AIs to generate stunning, never-before-seen pictures. Most of these users are not, like Lee Unkrich, professional artists, and that’s the point: They do not have to be. Not everyone can write, direct, and edit an Oscar winner like Toy Story 3 or Coco , but everyone can launch an AI image generator and type in an idea. What appears on the screen is astounding in its realism and depth of detail. Thus the universal response: Wow.
On four services alone—Midjourney, Stable Diffusion, Artbreeder, and DALL-E—humans working with AIs now cocreate more than 20 million images every day. With a paintbrush in hand, artificial intelligence has become an engine of wow.
Because these surprise-generating AIs have learned their art from billions of pictures made by humans, their output hovers around what we expect pictures to look like. But because they are an alien AI, fundamentally mysterious even to their creators, they restructure the new pictures in a way no human is likely to think of, filling in details most of us wouldn’t have the artistry to imagine, let alone the skills to execute. They can also be instructed to generate more variations of something we like, in whatever style we want—in seconds. This, ultimately, is their most powerful advantage: They can make new things that are relatable and comprehensible but, at the same time, completely unexpected.
So unexpected are these new AI-generated images, in fact, that—in the silent awe immediately following the wow —another thought occurs to just about everyone who has encountered them: Human-made art must now be over. Who can compete with the speed, cheapness, scale, and, yes, wild creativity of these machines? Is art yet another human pursuit we must yield to robots? And the next obvious question: If computers can be creative, what else can they do that we were told they could not? I have spent the past six months using AIs to create thousands of striking images, often losing a night’s sleep in the unending quest to find just one more beauty hidden in the code. And after interviewing the creators, power users, and other early adopters of these generators, I can make a very clear prediction: Generative AI will alter how we design just about everything. Oh, and not a single human artist will lose their job because of this new technology.
It is no exaggeration to call images generated with the help of AI cocreations.
The sobering secret of this new power is that the best applications of it are the result not of typing in a single prompt but of very long conversations between humans and machines. Progress for each image comes from many, many iterations, back-and-forths, detours, and hours, sometimes days, of teamwork—all on the back of years of advancements in machine learning.
AI image generators were born from the marriage of two separate technologies. One was a historical line of deep learning neural nets that could generate coherent realistic images, and the other was a natural language model that could serve as an interface to the image engine. The two were combined into a language-driven image generator. Researchers scraped the internet for all images that had adjacent text, such as captions, and used billions of these examples to connect visual forms to words, and words to forms. With this new combination, human users could enter a string of words—the prompt—that described the image they sought, and the prompt would generate an image based on those words.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Scientists now at Google invented the diffusion computational models that are at the core of image generators today, but the company has been so concerned about what people might do with them that it still has not opened its own experimental generators, Imagen and Parti, to the public. (Only employees can try them, and with tight guidelines on what can be requested.) It is no coincidence, then, that the three most popular platforms for image generators right now are three startups with no legacy to protect.
Midjourney is a bootstrapping startup launched by David Holz, who based the generator in an emerging community of artists. The interface to the AI is a noisy Discord server; all the work and prompts were made public from the start.
DALL-E is a second-gen product of the nonprofit OpenAI, funded by Elon Musk and others.
Stable Diffusion appeared on the scene in August 2022, created by Emad Mostaque, a European entrepreneur. It’s an open source project, with the added benefit that anyone can download its software and run it locally on their own desktop. More than the others, Stable Diffusion has unleashed AI image generators into the wild.
ART IS HUMAN.
ILLUSTRATION BY ADAM GARCIA ART IS HYBRID.
ILLUSTRATION BY: @auranova_ai + MIDJOURNEY Why are so many people so excited to play with these AIs? Many images are being created for the same reason that humans have always made most art: because the images are pretty and we want to look at them. Like flames in a campfire, the light patterns are mesmerizing. They never repeat themselves; they surprise, again and again. They depict scenes no one has witnessed before or can even imagine, and they are expertly composed. It’s a similar pleasure to exploring a video game world, or paging through an art book. There is a real beauty to their creativity, and we stare much in the way we might appreciate a great art show at a museum. In fact, viewing a parade of generated images is very much like visiting a personal museum—but in this case, the walls are full of art we ask for. And the perpetual novelty and surprise of the next image hardly wanes. Users may share the gems they discover, but my guess is that 99 percent of the 20 million images currently generated each day will only ever be viewed by a single human—their cocreator.
Like any art, the images can also be healing. People spend time making strange AI pictures for the same reason they might paint on Sundays, or scribble in a journal, or shoot a video. They use the media to work out something in their own lives, something that can’t be said otherwise. I’ve seen images depicting what animal heaven might look like, created in response to the death of a beloved dog. Many images explore the representation of intangible, spiritual realms, presumably as a way to think about them. “A huge portion of the entire usage is basically art therapy,” Holz, the Midjourney creator, tells me. “The images are not really aesthetically appealing in a universal sense but are appealing, in a very deep way, within the context of what’s going on in people’s lives.” The machines can be used to generate fantasies of all types. While the hosted services prohibit porn and gore , anything goes on the desktop versions, as it might in Photoshop.
This article appears in the February 2023 issue.
Subscribe to WIRED.
Photograph: Peter Yang AI-generated pictures can be utilitarian too. Say you are presenting a report on the possibility of recycling hospital plastic waste into construction materials and you want an image of a house made out of test tubes. You could search stock photo markets for a usable image made by a human artist. But a unique assignment like this rarely yields a preexisting picture, and even if found, its copyright status could be dubious or expensive. It is cheaper, faster, and probably far more appropriate to generate a unique, personalized image for your report in a few minutes that you can then insert into your slides, newsletter, or blog—and the copyright ownership is yours (for now). I have been using these generators myself to cocreate images for my own slide presentations.
In an informal poll of power users, I found that only about 40 percent of their time is spent seeking utilitarian images. Most AI images are used in places where there were no images previously. They usually do not replace an image created by a human artist. They may be created, for example, to illustrate a text-only newsletter by someone without artistic talent themselves, or the time and budget to hire someone. Just as mechanical photography did not kill human illustrations a century ago, but rather significantly expanded the places in which images appeared, so too do AI image generators open up possibilities for more art, not less. We’ll begin to see contextually generated images predominately in spaces that are currently blank, like emails, text messages, blogs, books, and social media.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg This new art resides somewhere between painting and photography. It lives in a possibility space as large as painting and drawing—as huge as human imagination. But you move through the space like a photographer, hunting for discoveries. Tweaking your prompts, you may arrive at a spot no one has visited before, so you explore this area slowly, taking snapshots as you step through. The territory might be a subject, or a mood, or a style, and it might be worth returning to. The art is in the craft of finding a new area and setting yourself up there, exercising good taste and the keen eye of curation in what you capture. When photography first appeared, it seemed as if all the photographer had to do was push the button. Likewise, it seems that all a person has to do for a glorious AI image is push the button. In both cases, you get an image. But to get a great one—a truly artistic one—well, that’s another matter.
Accessible AI image generators are not even a year old, but already it is evident that some people are much better at creating AI images than others. Although they’re using the same programs, those who have accumulated thousands of hours with the algorithms can magically produce images that are many times better than the average person’s. The images by these masters have a striking coherence and visual boldness that is normally overwhelmed by the flood of details the AIs tend to produce. That is because this is a team sport: The human artist and the machine artist are a duet. And it requires not just experience but also lots of hours and work to produce something useful. It is as if there is a slider bar on the AI: At one end is Maximum Surprise, and at the other end Maximum Obedience. It is very easy to get the AI to surprise you. (And that is often all we ask of it.) But it is very difficult to get the AI to obey you. As Mario Klingemann, who makes his living selling NFTs of his AI-generated artwork , says, “If you have a very specific image in mind, it always feels like you are up against a forcefield.” Commands like “shade this area,” “enhance this part,” and “tone it down” are obeyed reluctantly. The AIs have to be persuaded.
Current versions of DALL-E, Stable Diffusion, and Midjourney limit prompts to about the length of a long tweet. Any longer and the words muddle together; the image turns to mush. That means that behind every fabulous image lies a short magic spell that summons it. It begins with the first incantation. How you say it matters. Your immediate results materialize in a grid of four to nine images. From that batch of pictures, you variate and mutate offspring images. Now you have a brood. If they look promising, begin to tweak the spell to nudge it in new directions as it births more generations of images. Multiply the group again and again as you search for the most compelling composition. Do not despair if it takes dozens of generations. Think like the AI; what does it like to hear? Whisper instructions that have worked in the past, and add them to the prompt. Repeat. Change the word order to see whether it likes that. Remember to be specific. Replicate until you have amassed a whole tribe of images that seem to have good bones and potential. Now cull out all but a select few. Be merciless. Begin outpainting the most promising images. That means asking the AI to extend the image out in certain directions beyond the current borders. Erase those portions that are not working. Suggest replacements to be done by the AI with more incantations (called inpainting). If the AI is not comprehending your hints, try spells used by others. When the AI has gone as far as it can, migrate the image to Photoshop for final tailoring. Present it as if you have done nothing, even though it is not uncommon for a distinctive image to require 50 steps.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Behind this new magecraft is the art of prompting. Each artist or designer develops a way of persuading an AI to yield its best by evolving their prompts. Let’s call these new artists AI whisperers, or prompt artists, or promptors. The promptors work almost as directors, guiding the work of their alien collaborators toward a unified vision. The convoluted process required to tease a first-rate picture out of an AI is quickly emerging as a fine-art skill. Almost daily, new tools arrive to make prompting easier, better.
PromptBase is a market for promptors to sell prompts that create simple images such as emoticons, logos, icons, avatars, and game weapons. It’s like clip art, but instead of selling the art, they sell the prompt that generates the art. And unlike fixed clip art, it is easy to alter and tweak the art to fit your needs, and you can extract multiple versions again and again. Most of these prompts sell for a couple bucks, which is a fair price, given how much trouble it is to hone a prompt on your own.
Above-average prompts not only include the subject but also describe the lighting, the point of view, the emotion evoked, the color palette, the degree of abstraction, and perhaps a reference picture to imitate. As with other artistic skills, there are now courses and guidebooks to train the budding promptor in the finer points of prompting. One fan of DALL-E 2, Guy Parsons, put together a free Prompt Book , jammed with tips on how to go beyond the wow and get images you can actually use. One example: If your prompt includes specific terms such as “Sigma 75 mm camera lens,” Parson says, then the AI doesn’t just create that specific look made by the lens; “it more broadly alludes to ‘the kind of photo where the lens appears in the description,’” which tends to be more professional and therefore yields higher-quality images. It’s this kind of multilevel mastery that produces spectacular results.
For technical reasons, even if you repeat the exact same prompt, you are unlikely to get the same image. There is a randomly generated seed for each image, without which it is statistically impossible to replicate. Additionally, the same prompt given to different AI engines produces different images—Midjourney’s are more painterly, while DALL-E is optimized for photographic realism. Still, not every promptor wishes to share their secrets. The natural reaction upon seeing a particularly brilliant image is to ask, “What spell did you use?” What was the prompt? Robyn Miller, cocreator of the legendary game Myst and a pioneering digital artist, has been posting an AI-generated image every day. “When people ask me what prompt I used,” he says, “I have been surprised that I don’t want to tell them. There is an art to this, and that has also surprised me.” Klingemann is famous for not sharing his prompts. “I believe all images already exist,” he says. “You don’t make them, you find them. If you get somewhere by clever prompting, I do not see why I want to invite everybody else there.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It seems obvious to me that promptors are making true art. What is a consummate movie director—like Hitchcock, like Kurosawa—but a promptor of actors, actions, scenes, ideas? Good image-generator promptors are engaged in a similar craft, and it is no stretch for them to try and sell their creations in art galleries or enter them into art contests. This summer, Jason Allen won first place in the digital art category at the Colorado State Fair Fine Art competition for a large, space-opera-themed canvas that was signed “Jason Allen via Midjourney.” It’s a pretty cool picture that would’ve taken some effort to make no matter what tools were used. Usually images in the digital art category are created using Photoshop and Blender-type tools that enable the artist to dip into libraries of digitized objects, textures, and parts, which are then collaged together to form the scene. They are not drawn; these digital images are unapologetically technological assemblages. Collages are a venerable art form, and using AI to breed a collage is a natural evolution. If a 3D-rendered collage is art, then a Midjourney picture is art. As Allen told Vice , “I have been exploring a special prompt. I have created hundreds of images using it, and after many weeks of fine-tuning and curating my gens, I chose my top 3 and had them printed on canvas.” Of course, Allen’s blue ribbon set off alarm bells. To some critics, this was a sign of the end times, the end of art, the end of human artists. Predictable lamentations ensued, with many pointing out how unfair it felt for struggling artists. The AIs are not only going to take over and kill us all—they are, apparently, going to make the world’s best art while doing so.
At its birth, every new technology ignites a Tech Panic Cycle. There are seven phases: Don’t bother me with this nonsense. It will never work.
OK, it is happening, but it’s dangerous, ’cause it doesn’t work well.
Wait, it works too well. We need to hobble it. Do something! This stuff is so powerful that it’s not fair to those without access to it.
Now it’s everywhere, and there is no way to escape it. Not fair.
I am going to give it up. For a month.
Let’s focus on the real problem—which is the next current thing.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Today, in the case of AI image generators, an emerging band of very tech-savvy artists and photographers are working out of a Level 3 panic. In a reactive, third-person, hypothetical way, they fear other people (but never themselves) might lose their jobs. Getty Images, the premier agency selling stock photos and illustrations for design and editorial use, has already banned AI-generated images; certain artists who post their work on DeviantArt have demanded a similar ban. There are well-intentioned demands to identify AI art with a label and to segregate it from “real” art.
Beyond that, some artists want assurances that their own work not be used to train the AIs. But this is typical of Level 3 panic—in that it is, at best, misguided. The algorithms are exposed to 6 billion images with attendant text. If you are not an influential artist, removing your work makes zero difference. A generated picture will look exactly the same with or without your work in the training set. But even if you are an influential artist, removing your images still won't matter. Because your style has affected the work of others—the definition of influence—your influence will remain even if your images are removed. Imagine if we removed all of Van Gogh’s pictures from the training set. The style of Van Gogh would still be embedded in the vast ocean of images created by those who have imitated or been influenced by him.
Styles are summoned via prompts, as in: “in the style of Van Gogh.” Some unhappy artists would rather their names be censored and not permitted to be used as a prompt. So even if their influence can’t be removed, you can’t reach it because their name is off-limits. As we know from all previous attempts at censoring, these kinds of speech bans are easy to work around; you can misspell a name, or simply describe the style in words. I found, for example, that I could generate detailed black-and-white natural landscape photographs with majestic lighting and prominent foregrounds—without ever using Ansel Adams’ name.
There is another motivation for an artist to remove themselves. They might fear that a big corporation will make money off of their work, and their contribution won’t be compensated. But we don’t compensate human artists for their influence on other human artists. Take David Hockney, one of the highest-paid living artists. Hockney often acknowledges the great influence other living artists have on his work. As a society, we don’t expect him (or others) to write checks to his influences, even though he could. It’s a stretch to think AIs should pay their influencers. The “tax” that successful artists pay for their success is their unpaid influence on the success of others.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg What’s more, lines of influence are famously blurred, ephemeral, and imprecise. We are all influenced by everything around us, to degrees we are not aware of and certainly can’t quantify. When we write a memo or snap a picture with our phone, to what extent have we been influenced—directly or indirectly—by Ernest Hemingway or Dorothea Lange? It’s impossible to unravel our influences when we create something. It is likewise impossible to unravel the strands of influence in the AI image universe. We could theoretically construct a system to pay money earned by the AI to artists in the training set, but we’d have to recognize that this credit would be made arbitrarily (unfairly) and that the actual compensatory amounts per artist in a pool of 6 billion shares would be so trivial as to be nonsensical.
In the coming years, the computational engine inside an AI image generator will continue to expand and improve until it becomes a central node in whatever we do visually. It will have literally seen everything and know all styles, and it will paint, imagine, and generate just about anything we need. It will become a visual search engine, and a visual encyclopedia with which to understand images, and the primary tool we use with our most important sense, our sight. Right now, every neural net algorithm running deep in the AIs relies on massive amounts of data—thus the billions of images needed to train it. But in the next decade, we’ll have operational AI that relies on far fewer examples to learn, perhaps as few as 10,000. We’ll teach even more powerful AI image generators how to paint by showing them thousands of carefully curated, highly selected images of existing art, and when this point comes, artists of all backgrounds will be fighting one another to be included in the training set. If an artist is in the main pool, their influence will be shared and felt by all, while those not included must overcome the primary obstacle for any artist: not piracy, but obscurity.
As soon as 2D generative algorithms were born, experimenters rushed to figure out what was next. Jensen Huang, the ambitious cofounder of Nvidia, believes the next generation of chips will generate 3D worlds for the metaverse—“the next computing platform,” as he calls it.
In a single week this past September, three novel text-to-3D/video image generators were announced: GET3D (Nvidia), Make-A-Video (Meta), and DreamFusion (Google). The expansion is happening faster than I can write. Amazing as frameable 2D pictures produced by AI are, outsourcing their creation is not going to radically change the world. We are already at peak 2D. The genuine superpower being released by AI image generators will be in producing 3D images and video.
A future prompt for a 3D engine might look something like this: “Create the messy bedroom of a teenager, with posters on the wall, an unmade bed, and afternoon sunlight streaming through closed blinds.” And in seconds, a fully realized room is born, the closet door open and all the dirty clothes on the floor—in full 3D. Then, tell the AI: “Make a 1970s kitchen with refrigerator magnets and all the cereal boxes in the pantry. In full volumetric detail. One that you could walk through. Or that could be photographed in a video.” Games crammed with alternatively rendered worlds and full-length movies decked out with costumes and sets have eternally been out of reach for individual artists, who remain under the power of large dollars. AI could make games, metaverses, and movies as quick to produce as novels, paintings, and songs. Pixar films in an instant! Once millions of amateurs are churning out billions of movies and endless metaverses at home, they will hatch entirely new media genres—virtual tourism, spatial memes—with their own native geniuses. And when big dollars and professionals are equipped with these new tools, we’ll see masterpieces at a level of complexity never seen before.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But even the vast universes of 3D worlds and video are not vast enough to contain the disruption that AI image generators have initiated. DALL-E, Midjourney, and Stable Diffusion are just the first versions of generative machines of all types. Their prime function, pattern recognition, is almost a reflex for human brains, something we accomplish without conscious thinking. It is at the core of almost everything we do. Our thinking is more complex than just pattern recognition, of course; dozens of cognitive functions animate our brain. But this single type of cognition, synthesized in machines (and the only cognition we have synthesized so far), has taken us further than we first thought—and will probably continue to advance further than we now think.
When an AI notices a pattern, it stores it in a compressed way. Round objects are placed in a “roundness” direction, red objects in another direction for “redness,” and so on. Maybe it notices “treeness” and “foodness” too. It abstracts out billions of directions, or patterns. Upon reflection—or training—it notices that the overlap of these four qualities produces “appleness,” yet another direction. Furthermore, it links all these noticed directions with word patterns, which can also share overlapping qualities. So when a human requests a picture of an apple via the word “apple,” the AI paints an image with those four (or more) qualities. It is not assembling bits of existing pictures; rather, it is “imagining” a new picture with the appropriate qualities. It sort of remembers a picture that does not exist but could.
This same technique can be used—in fact, is already being used, in very early forms—to find new drugs. The AI is trained on a database of all the molecules we know to be active medicines, noticing patterns in their chemical structures. Then the AI is asked to “remember” or imagine molecules we have never thought of that seem to be similar to the molecules that work. Wonderfully, some of them actually do work, just as an AI image of a requested imaginary fruit can look remarkably like a fruit. This is the real transformation, and soon enough, the same technique will be used to help design automobiles, draft laws, write code, compose soundtracks, assemble worlds to entertain and instruct, and cocreate the stuff we do as work. We should take to heart the lessons we’ve learned so far from AI image generators because there will soon be more pattern-seeking AIs in all realms of life. The panic cycle we presently face is simply a good rehearsal for the coming shift.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg What we know about AI generators so far is that they work best as partners. The nightmare of a rogue AI taking over is just not happening. That vision is fundamentally a misreading of history. In the past, technology has rarely directly displaced humans from work they wanted to do. For instance, the automatic generation of pictures by a machine—called a camera—was feared in the 1800s because it would surely put portrait painters out of business. But the historian Hans Rooseboom could find only a single portrait painter from that time who felt unemployed by photography. (Photography actually inspired a resurgence of painting later in that century.) Closer to our time, we might have expected professional occupations in photography to fall as the smartphone swallowed the world and everybody became a photographer—with 95 million uploads to Instagram a day and counting. Yet the number of photography professionals in the US has been slowly rising, from 160,000 in 2002 (before camera phones) to 230,000 in 2021.
Instead of fearing AI, we are better served thinking about what it teaches us. And the most important thing AI image generators teach us is this: Creativity is not some supernatural force. It is something that can be synthesized, amplified, and manipulated. It turns out that we didn’t need to achieve intelligence in order to hatch creativity. Creativity is more elemental than we thought. It is independent of consciousness. We can generate creativity in something as dumb as a deep learning neural net. Massive data plus pattern recognition algorithms seems sufficient to engineer a process that will surprise and aid us without ceasing.
Scholars of creativity refer to something called Uppercase Creativity. Uppercase Creativity is the stunning, field-changing, world-altering rearrangement that a major breakthrough brings. Think special relativity, the discovery of DNA, or Picasso’s Guernica.
Uppercase Creativity goes beyond the merely new. It is special, and it is rare. It touches us humans in a profound way, far beyond what an alien AI can fathom.
To connect with a human deeply will always require a Creative human in the loop. This high creativity, however, should not be confused with the creativity that most human artists, designers, and inventors produce day to day. Mundane, ordinary, lowercase creativity is what we get with a great new logo design or a cool book cover, a nifty digital wearable or the latest must-have fashion, or the set design for our favorite sci-fi serial. Most human art, past and present, is lowercase. And lowercase creativity is exactly what the AI generators deliver.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But this is huge. For the first time in history, humans can conjure up everyday acts of creativity on demand, in real time, at scale, for cheap. Synthetic creativity is a commodity now. Ancient philosophers will turn in their graves, but it turns out that to make creativity—to generate something new—all you need is the right code. We can insert it into tiny devices that are presently inert, or we can apply creativity to large statistical models, or embed creativity in drug discovery routines. What else can we use synthetic creativity for? We may feel a little bit like medieval peasants who are being asked, “What would you do if you had the power of 250 horses at your fingertips?” We dunno. It’s an extraordinary gift. What we do know is we now have easy engines of creativity, which we can aim into stale corners that have never seen novelty, innovation, or the wow of creative change. Against the background of everything that breaks down, this superpower can help us extend the wow indefinitely. Used properly, we can make a small dent in the universe.
This article appears in the February issue.
Subscribe now.
Let us know what you think about this article. Submit a letter to the editor at [email protected].
You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Topics longreads creativity artificial intelligence art Painting magazine-31.02 Andy Greenberg Brandi Collins-Dexter Steven Levy Lauren Smiley Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,031 | 2,023 |
"Microsoft’s AI Red Team Has Already Made the Case for Itself | WIRED"
|
"https://www.wired.com/story/microsoft-ai-red-team"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Lily Hay Newman Security Microsoft’s AI Red Team Has Already Made the Case for Itself Photograph: Valeriia Mitriakova/Getty Images Save this story Save Save this story Save For most people, the idea of using artificial intelligence tools in daily life—or even just messing around with them—has only become mainstream in recent months, with new releases of generative AI tools from a slew of big tech companies and startups, like OpenAI's ChatGPT and Google's Bard.
But behind the scenes, the technology has been proliferating for years, along with questions about how best to evaluate and secure these new AI systems. On Monday, Microsoft is revealing details about the team within the company that since 2018 has been tasked with figuring out how to attack AI platforms to reveal their weaknesses.
In the five years since its formation, Microsoft's AI red team has grown from what was essentially an experiment into a full interdisciplinary team of machine learning experts, cybersecurity researchers, and even social engineers. The group works to communicate its findings within Microsoft and across the tech industry using the traditional parlance of digital security, so the ideas will be accessible rather than requiring specialized AI knowledge that many people and organizations don't yet have. But in truth, the team has concluded that AI security has important conceptual differences from traditional digital defense, which require differences in how the AI red team approaches its work.
“When we started, the question was, ‘What are you fundamentally going to do that’s different? Why do we need an AI red team?’” says Ram Shankar Siva Kumar, the founder of Microsoft's AI red team. “But if you look at AI red teaming as only traditional red teaming, and if you take only the security mindset, that may not be sufficient. We now have to recognize the responsible AI aspect, which is accountability of AI system failures—so generating offensive content, generating ungrounded content. That is the holy grail of AI red teaming. Not just looking at failures of security but also responsible AI failures.” Shankar Siva Kumar says it took time to bring out this distinction and make the case that the AI red team's mission would really have this dual focus. A lot of the early work related to releasing more traditional security tools like the 2020 Adversarial Machine Learning Threat Matrix, a collaboration between Microsoft, the nonprofit R&D group MITRE, and other researchers. That year, the group also released open source automation tools for AI security testing, known as Microsoft Counterfit.
And in 2021, the red team published an additional AI security risk assessment framework.
Over time, though, the AI red team has been able to evolve and expand as the urgency of addressing machine learning flaws and failures becomes more apparent.
In one early operation, the red team assessed a Microsoft cloud deployment service that had a machine learning component. The team devised a way to launch a denial of service attack on other users of the cloud service by exploiting a flaw that allowed them to craft malicious requests to abuse the machine learning components and strategically create virtual machines, the emulated computer systems used in the cloud. By carefully placing virtual machines in key positions, the red team could launch “noisy neighbor” attacks on other cloud users, where the activity of one customer negatively impacts the performance for another customer.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The red team ultimately built and attacked an offline version of the system to prove that the vulnerabilities existed, rather than risk impacting actual Microsoft customers. But Shankar Siva Kumar says that these findings in the early years removed any doubts or questions about the utility of an AI red team. “That’s where the penny dropped for people,” he says. “They were like, ‘Holy crap, if people can do this, that’s not good for the business.’” Crucially, the dynamic and multifaceted nature of AI systems means that Microsoft isn't just seeing the most highly resourced attackers targeting AI platforms. “Some of the novel attacks we’re seeing on large language models—it really just takes a teenager with a potty mouth, a casual user with a browser, and we don’t want to discount that,” Shankar Siva Kumar says. “There are APTs, but we also acknowledge that new breed of folks who are able to bring down LLMs and emulate them as well.” As with any red team, though, Microsoft's AI red team isn't just researching attacks that are being used in the wild right now. Shankar Siva Kumar says that the group is focused on anticipating where attack trends may go next. And that often involves an emphasis on the newer AI accountability piece of the red team's mission. When the group finds a traditional vulnerability in an application or software system, they often collaborate with other groups within Microsoft to get it fixed rather than take the time to fully develop and propose a fix on their own.
“There are other red teams within Microsoft and other Windows infrastructure experts or whatever we need,” Shankar Siva Kumar says. “The insight for me is that AI red teaming now encompasses not just security failures, but responsible AI failures.” You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Senior Writer X Topics malware cybersecurity artificial intelligence Microsoft black hat Lily Hay Newman David Gilbert Andrew Couts Andy Greenberg David Gilbert Andy Greenberg Justin Ling David Gilbert Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,032 | 2,023 |
"How You Can Tell the AI Images of Trump’s Arrest Are Deepfakes | WIRED"
|
"https://www.wired.com/story/how-to-tell-fake-ai-images-donald-trump-arrest"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Reece Rogers Security How You Can Tell the AI Images of Trump’s Arrest Are Deepfakes This image of the former US president is real.
Photograph: Jabin Botsford/The Washington Post/Getty Images Save this story Save Save this story Save The viral, AI-generated images of Donald Trump’s arrest you may be seeing on social media are definitely fake. But some of these photorealistic creations are pretty convincing. Others look more like stills from a video game or a lucid dream. A Twitter thread by Eliot Higgins, a founder of Bellingcat , that shows Trump getting swarmed by synthetic cops , running around on the lam , and picking out a prison jumpsuit was viewed over 3 million times on the social media platform.
What does Higgins think viewers can do to tell the difference between fake, AI images, like the ones in his post, from real photographs that may come out of the former president’s potential arrest? “Having created a lot of images for the thread, it's apparent that it often focuses on the first object described—in this case, the various Trump family members—with everything around it often having more flaws,” Higgins said over email. Look outside of the image’s focal point. Does the rest of the image appear to be an afterthought? Even though the newest versions of AI-image tools, like Midjourney (version 5 of which was used for the aforementioned thread) and Stable Diffusion, are making considerable progress, mistakes in the smaller details remain a common sign of fake images. As AI art grows in popularity, many artists point out that the algorithms still struggle to replicate the human body in a consistent, natural manner.
Eagle Eyes Reece Rogers Ideas Leo Kim Deep Dive Tom Simonite Looking at the AI images of Trump from the Twitter thread, the face looks fairly convincing in many of the posts, as do the hands, but his body proportions may look contorted or melted into a nearby police officer. Even though it’s obvious now, it’s possible that the algorithm might be able to avoid peculiar-looking body parts with more training and refinement.
Need another tell? Look for odd writing on the walls, clothing, or other visible items. Higgins points toward messy text as a way to differentiate fake images from real photos. For example, the police wear badges, hats, and other documents that appear to have lettering, at first glance, in the fake images of officers arresting Trump. Upon closer inspection, the words are nonsensical.
An additional way you can sometimes tell an image is generated by AI is by noticing over-the-top facial expressions.
“I've also noticed that if you ask for expressions, Midjourney tends to render them in an exaggerated way, with skin creases from things like smiling being very pronounced,” Higgins said. The pained expression on Melania Trump’s face looks more like a re-creation of Edvard Munch’s The Scream or a still from some unreleased A24 horror movie than a snapshot from a human photographer.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Keep in mind that world leaders, celebrities, social media influencers, and anyone with large quantities of photos circulating online may appear more convincing in deepfaked photos than AI-generated images of people with less of a visible internet presence. “It's clear that the more famous a person is, the more images the AI has had to learn from,” Higgins said. “So very famous people are rendered extremely well , while less famous people are usually a bit wonky.” For more peace of mind about the algorithm’s ability to re-create your face, it might be worth thinking twice before posting a photo dump of selfies after a fun night out with friends. (Though it’s likely that the AI generators have already scraped your image data from the web.) In the lead-up to the next US presidential election, what is Twitter’s policy about AI-generated images? The social media platform’s current policy reads, in part, “You may not share synthetic, manipulated, or out-of-context media that may deceive or confuse people and lead to harm (‘misleading media’).” Twitter carves out multiple exceptions for memes, commentary, and posts not created with the intention to mislead viewers.
Just a few years ago, it was almost unfathomable that the average person would soon be able to fabricate photorealistic deepfakes of world leaders at home. As AI images become harder to differentiate from the real deal, social media platforms may need to reevaluate their approach to synthetic content and attempt to find ways of guiding users through the complex and often unsettling world of generative AI.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Service Writer X Topics how-to artificial intelligence Donald Trump Deepfakes Social Media advice Deidre Olsen David Gilbert David Gilbert Vittoria Elliott Justin Ling Andrew Couts Lily Hay Newman Dell Cameron Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,033 | 2,023 |
"Stable Diffusion made copying artists and generating porn harder and users are mad - The Verge"
|
"https://www.theverge.com/2022/11/24/23476622/ai-image-generator-stable-diffusion-version-2-nsfw-artists-data-changes"
|
"The Verge homepage The Verge homepage The Verge The Verge logo.
/ Tech / Reviews / Science / Entertainment / More Menu Expand Menu Artificial Intelligence / Tech / Creators Stable Diffusion made copying artists and generating porn harder and users are mad Stable Diffusion made copying artists and generating porn harder and users are mad / Changes to the AI text-to-image model make it harder for users to mimic specific artists’ styles or generate NSFW output, but offer other functional improvements.
By James Vincent , a senior reporter who has covered AI, robotics, and more for eight years at The Verge.
| Share this story Users of AI image generator Stable Diffusion are angry about an update to the software that “nerfs” its ability to generate NSFW output and pictures in the style of specific artists.
Stability AI, the company that funds and disseminates the software, announced Stable Diffusion Version 2 early this morning European time. The update re-engineers key components of the model and improves certain features like upscaling (the ability to increase the resolution of images) and in-painting (context-aware editing). But, the changes also make it harder for Stable Diffusion to generate certain types of images that have attracted both controversy and criticism. These include nude and pornographic output, photorealistic pictures of celebrities, and images that mimic the artwork of specific artists.
“They have nerfed the model” “They have nerfed the model,” commented one user on a Stable Diffusion sub-reddit. “It’s kinda an unpleasant surprise,” said another on the software’s official Discord server.
Users note that asking Version 2 of Stable Diffusion to generate images in the style of Greg Rutkowski — a digital artist whose name has become a literal shorthand for producing high-quality images — no longer creates artwork that closely resembles his own. (Compare these two images, for example). “What did you do to greg😔,” commented one user on Discord.
Changes to Stable Diffusion are notable, as the software is hugely influential and helps set norms in the fast-moving generative AI scene. Unlike rival models like OpenAI’s DALL-E, Stable Diffusion is open source. This allows the community to quickly improve on the tool and for developers to integrate it into their products free of charge. But it also means Stable Diffusion has fewer constraints in how it’s used and, as a consequence, has attracted significant criticism. In particular, many artists, like Rutkowski, are annoyed that Stable Diffusion and other image generating models were trained on their artwork without their consent and can now reproduce their styles. Whether or not this sort of AI-enabled copying is legal is something of an open question.
Experts say training AI models on copyright-protected data is likely legal, but that certain use-cases could be challenged in court.
Stable Diffusion’s users have speculated that the changes to the model were made by Stability AI to mitigate such potential legal challenges. However, when The Verge asked Stability AI’s founder Emad Mostaque if this was the case in a private chat, Mostaque did not answer. Mostaque did confirm, though that Stability AI has not removed artists’ images from the training data (as many users have speculated). Instead, the model’s reduced ability to copy artists is a result of changes made to how the software encodes and retrieves data.
“There has been no specific filtering of artists here,” Mostaque told The Verge.
(He also expanded on the technical underpinning of these changes in a message posted on Discord.
) What has been removed from Stable Diffusion’s training data, though, is nude and pornographic images. AI image generators are already being used to generate NSFW output , including both photorealistic and anime-style pictures. However, these models can also be used to generate NSFW imagery resembling specific individuals (known as non-consensual pornography) and images of child abuse.
Discussing the changes Stable Diffusion Version 2 in the software’s official Discord, Mostaque notes this latter use-case is the reason for filtering out NSFW content. “can’t have kids & nsfw in an open model,” says Mostaque (as the two sorts of images can be combined to create child sexual abuse material), “so get rid of the kids or get rid of the nsfw.” One user on Stable Diffusion’s sub-reddit said the removal of NSFW content was “censorship,” and “against the spirit philosophy of Open Source community.” Said the user: “To choose to do NSFW content or not, should be in the hands of the end user, no [sic] in a limited/censored model.” Others, though, noted that the open source nature of Stable Diffusion mean nude training data can easily be added back into third-party releases and that the new software doesn’t affect earlier versions: “Do not freak out about V2.0 lack of artists/NSFW, you’ll be able to generate your favorite celeb naked soon & anyway you already can.” Although the changes to Stable Diffusion Version 2 have annoyed some users, many others praised its potential for deeper functionality, as with the software’s new ability to produce content that matches the depth of an existing image. Others said the changes did make it harder to quickly produce high-quality images, but that the community would likely add back this functionality in future versions. As one user on Discord summarized the changes : “2.0 is better at interpreting prompts and making coherent photographic images in my experience so far. it will not make any rutkowski titties though.” Mostaque himself compared the new model to a pizza base that lets anyone add ingredients (i.e. training data) of their choice. “A good model should be usable by everyone and if you want to add stuff add stuff,” he said on Discord.
Mostaque also said future versions of Stable Diffusion would use training datasets that would allow artists to opt-in or opt-out — a feature that many artists have requested, and that could help mitigate some criticism. “We are trying to be super transparent as we improve the base models and incorporate community feedback,” Mostaque told The Verge.
A public demo of Stable Diffusion Version 2 can be accessed here (though due to high demands from users the model may be inaccessible or slow).
Sam Altman fired as CEO of OpenAI Breaking: OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily.
From our sponsor Advertiser Content From More from Artificial Intelligence Universal Music sues AI company Anthropic for distributing song lyrics OpenAI is opening up DALL-E 3 access YouTube might make an official way to create AI Drake fakes The world’s biggest AI models aren’t very transparent, Stanford study says Advertiser Content From Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved
"
|
2,034 | 2,017 |
"Roboschool"
|
"https://openai.com/research/roboschool"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research Roboschool May 15, 2017 Robotics , Environments , Software engineering , Open source , Release Roboschool provides new OpenAI Gym environments for controlling robots in simulation. Eight of these environments serve as free alternatives to pre-existing MuJoCo implementations, re-tuned to produce more realistic motion. We also include several new, challenging environments.
Roboschool also makes it easy to train multiple agents together in the same environment.
After we launched Gym , one issue we heard from many users was that the MuJoCo component required a paid license (though MuJoCo recently added free student licenses for personal and class work). Roboschool removes this constraint, letting everyone conduct research regardless of their budget. Roboschool is based on the Bullet Physics Engine , an open-source, permissively licensed physics library that has been used by other simulation software such as Gazebo and V-REP.
Environments Roboschool ships with twelve environments, including tasks familiar to Mujoco users as well as new challenges, such as harder versions of the Humanoid walker task, and a multi-player Pong environment. We plan to expand this collection over time and look forward to the community contributing as well.
For the existing MuJoCo environments, besides porting them to Bullet, we have modified them to be more realistic. Here are three of the environments we ported, with explanations of how they differ from the existing environments.
Roboschool Existing Comments Walker2d re-tuned to produce more realistic slower-paced motion.
Ant is heavier, encouraging it to typically have two or more legs on the ground.
Humanoid benefits from more realistic energy cost (= torque × angular velocity) subtracted from reward.
You can find trained policies for all of these environments in the agent_zoo folder in the GitHub repository. You can also access a demo_race script to initiate a race between three robots.
Interactive and robust control In several of the previous OpenAI Gym environments, the goal was to learn a walking controller. However, these environments involved a very basic version of the problem, where the goal is simply to move forward. In practice, the walking policies would learn a single cyclic trajectory and leave most of the state space unvisited. Furthermore, the final policies tended to be very fragile: a small push would often cause the robot to crash and fall.
We have added two more environments with the 3D humanoid, which make the locomotion problem more interesting and challenging. These environments require interactive control — the robots must run towards a flag, whose position randomly varies over time.
HumanoidFlagrun is designed to teach the robot to slow down and turn. The goal is to run towards the flag, whose position varies randomly.
HumanoidFlagrunHarder in addition allows the robot to fall and gives it time to get back on foot. It also starts each episode upright or laying on the ground, and the robot is constantly bombarded by white cubes to push it off its trajectory.
We ship trained policies for both HumanoidFlagrun and HumanoidFlagrunHarder.
The walks aren’t as fast and natural-looking as the ones we see from the regular humanoid, but these policies can recover from many situations, and they know how to steer. This policy itself is still a multilayer perceptron, which has no internal state, so we believe that in some cases the agent uses its arms to store information.
Multiplayer Roboschool lets you both run and train multiple agents in the same environment. We start with RoboschoolPong, with more environments to follow.
With multiplayer training, you can train the same agent playing for both parties (so it plays with itself), you can train two different agents using the same algorithm, or you can even set two different algorithms against each other.
The multi-agent setting presents some interesting challenges. If you train both players simultaneously, you’ll likely see a learning curve like the following one, obtained from a policy gradient method: Here’s what’s happening: Agent1 (green) learns it can sometimes hit a ball at the top, so it moves to the top.
Agent2 (purple) discovers that its adversary is at the top, so it sends the ball to the bottom and overfits to other agent being away.
Agent1 eventually discovers it can defend itself by moving to the bottom, but now always stay at the bottom, because Agent2 always sends ball to the bottom.
That way, the policies oscillated, and neither agent learned anything useful after hours of training. As in generative adversarial networks, learning in an adversarial setting is tricky, but we think it’s an interesting research problem because this interplay can lead to sophisticated strategies even in simple environments, and it can provide a natural curriculum.
See also There’s been a lot of work by the community to create environments for OpenAI Gym , some of which are based on open-source physics simulators. In one recent project, researchers created a fork of OpenAI Gym that replaced MuJoCo by the open-source physics simulator DART.
They showed that policies can even be transferred between the two physics simulators, MuJoCo and DART.
Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,035 | 2,017 |
"Learning from human preferences"
|
"https://openai.com/research/learning-from-human-preferences"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research Learning from human preferences June 13, 2017 More resources Read paper Human feedback , Reinforcement learning , Safety & Alignment , Release We present a learning algorithm that uses small amounts of human feedback to solve modern RL environments. Machine learning systems with human feedback have been explored before , but we’ve scaled up the approach to be able to work on much more complicated tasks. Our algorithm needed 900 bits of feedback from a human evaluator to learn to backflip—a seemingly simple task which is simple to judge but challenging to specify.
The overall training process is a 3-step feedback cycle between the human, the agent’s understanding of the goal, and the RL training.
Our AI agent starts by acting randomly in the environment. Periodically, two video clips of its behavior are given to a human, and the human decides which of the two clips is closest to fulfilling its goal—in this case, a backflip. The AI gradually builds a model of the goal of the task by finding the reward function that best explains the human’s judgments. It then uses RL to learn how to achieve that goal. As its behavior improves, it continues to ask for human feedback on trajectory pairs where it’s most uncertain about which is better, and further refines its understanding of the goal.
Our approach demonstrates promising sample efficiency—as stated previously, the backflip video required under 1000 bits of human feedback. It took less than an hour of a human evaluator’s time, while in the background the policy accumulated about 70 hours of overall experience (simulated at a much faster rate than real-time.) We will continue to work on reducing the amount of feedback a human needs to supply. You can see a sped-up version of the training process in the following video.
Human Feedback training process 00:39 We’ve tested our method on a number of tasks in the simulated robotics and Atari domains (without being given access to the reward function: so in Atari, without having access to the game score). Our agents can learn from human feedback to achieve strong and sometimes superhuman performance in many of the environments we tested. In the following animation you can see agents trained with our technique playing a variety of Atari games. The horizontal bar on the right hand side of each frame represent’s each agents prediction about how much a human evaluator would approve of their current behavior. These visualizations indicate that agents trained with human feedback learn to value oxygen in Seaquest (left), anticipate rewards in Breakout and Pong (center), or work out how to recover from crashes in Enduro (right).
Note there’s no need for the feedback to align with the environment’s normal reward function: we can, for example, train our agents to precisely keep even with other cars in Enduro rather than maximizing game score by passing them. We also sometimes find that learning from feedback does better than reinforcement learning with the normal reward function, because the human shapes the reward better than whoever wrote the environment’s reward.
Challenges Our algorithm’s performance is only as good as the human evaluator’s intuition about what behaviors look correct, so if the human doesn’t have a good grasp of the task they may not offer as much helpful feedback. Relatedly, in some domains our system can result in agents adopting policies that trick the evaluators. For example, a robot which was supposed to grasp items instead positioned its manipulator in between the camera and the object so that it only appeared to be grasping it, as shown below.
We addressed this particular problem by adding in visual cues (the thick white lines in the above animation) to make it easy for the human evaluators to estimate depth.
The research described in this post was done in collaboration with Jan Leike, Miljan Martic, and Shane Legg at DeepMind. Our two organizations plan to continue to collaborate on topics that touch on long-term AI safety. We think that techniques like this are a step towards safe AI systems capable of learning human-centric goals, and can complement and extend existing approaches like reinforcement and imitation learning. This post is representative of the work done by OpenAI’s safety team; if you’re interested in working on problems like this, please join us ! Footnote By comparison, we took two hours to write our own reward function (the animation in the above right) to get a robot to backflip, and though it succeeds it’s a lot less elegant than the one trained simply through human feedback (top left). We think there are many cases where human feedback could let us specify a specific goal more intuitively and quickly than is possible by manually hand-crafting the objective.
You can replicate this backflip in gym with the following reward function for Hopper: Authors Dario Amodei Paul Christiano Alex Ray Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,036 | 2,018 |
"Learning complex goals with iterated amplification"
|
"https://openai.com/research/learning-complex-goals-with-iterated-amplification"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research Learning complex goals with iterated amplification We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable approach to AI safety.
October 22, 2018 More resources Read paper Safety & Alignment , Publication If we want to train an ML system to perform a task, we need a training signal—a way to evaluate how well it is doing in order to help it learn. For example, labels in supervised learning or rewards in reinforcement learning are training signals. The formalism of ML usually assumes a training signal is already present and focuses on learning from it, but in reality the training signal has to come from somewhere. If we don’t have a training signal we can’t learn the task, and if we have the wrong training signal, we can get unintended and sometimes dangerous behavior.
Thus, it would be valuable for both learning new tasks, and for AI safety, to improve our ability to generate training signals.
How do we currently generate training signals? Sometimes, the goal we want can be evaluated algorithmically, like counting up the score in a game of Go or checking whether a set of numbers has been successfully sorted (left panels of figure below). Most real-world tasks don’t lend themselves to an algorithmic training signal, but often we can instead obtain a training signal by having a human either perform the task (for example, labeling a training set or demonstrating an RL task), or judge an AI’s performance on the task (middle panels of figure below). However, many tasks are so complicated that a human can’t judge or perform them—examples might be designing a complicated transit system or managing every detail of the security of a large network of computers (right panels of figure below).
Iterated amplification is a method for generating a training signal for the latter types of tasks, under certain assumptions. Namely, although a human can’t perform or judge the whole task directly, we assume that a human can, given a piece of the task, identify clear smaller components of which it’s made up. For example, in the networked computer example, a human could break down “defend a collection of servers and routers” into “consider attacks on the servers”, “consider attacks on the routers”, and “consider how the previous two attacks might interact”. Additionally, we assume a human can do very small instances of the task, for example “identify if a specific line in a log file is suspicious”. If these two things hold true, then we can build up a training signal for big tasks from human training signals for small tasks, using the human to coordinate their assembly.
In our implementation of amplification, we start by sampling small subtasks and training the AI system to do them by soliciting demonstrations from humans (who can do these small tasks). We then begin sampling slightly larger tasks, solving them by asking humans to break them up into small pieces, which AI systems trained from the previous step can now solve. We use the solutions to these slightly harder tasks, which were obtained with human help, as a training signal to train AI systems to solve these second-level tasks directly (without human help). We then continue to further composite tasks, iteratively building up a training signal as we go. If the process works, the end result is a totally automated system that can solve highly composite tasks despite starting with no direct training signal for those tasks. This process is somewhat similar to expert iteration (the method used in AlphaGo Zero ), except that expert iteration reinforces an existing training signal, while iterated amplification builds up a training signal from scratch. It also has features in common with several recent learning algorithms that use problem decomposition on-the-fly to solve a problem at test time, but differs in that it operates in settings where there is no prior training signal.
Experiments As with our previous work on AI safety via debate , working directly on tasks beyond human scale is too hard for a prototype project. Also, using an actual human as training signal introduces complications, so we haven’t done this yet (though we plan to do it in the future). For our first experiments, we instead try to amplify an algorithmic training signal, to show that iterated amplification can work in this simple setting. We also limit our attention to supervised learning (unlike our previous work on human training signals in RL ). We’ve tried the method on five toy algorithmic tasks. These tasks have direct algorithmic solutions which we pretend we don’t know (for example, find the shortest path between two points on a graph). The problems can also be solved by piecing together small one-step deductions (for example, combining two paths to form a longer path), but it would take exponentially much effort to piece everything together manually. We use iterated amplification to learn the direct algorithm using only the pieces as training signal, thus simulating the situation where a human knows how to combine subpieces of a solution but can’t provide a direct training signal.
On each of these five tasks (permutation powering, sequential assignments, wildcard search, shortest path, and union find), we are able to perform competitively with just directly learning the task via supervised learning, despite being handicapped by not having a direct training signal (the goal here is to match supervised learning with less information, not to surpass it).
Iterated amplification has comparable performance to supervised learning without ever seeing the ground truth labels Amplification has features in common with our previous work on AI safety via debate.
Like debate, it seeks to train tasks that are beyond human ability to directly perform or judge, through an iterative process that allows humans to provide indirect supervision - however the specific approach is different. It also builds on our work on human feedback , by implementing a reward prediction system, and later versions of it are likely to include feedback from actual humans. So far we’ve explored all of these methods in a preliminary way, and are now working on scaling them up to address more interesting and realistic problems.
If you’re interested in helping us extend tools like iterated amplification to build safe, powerful AI, then consider joining OpenAI.
Authors Paul Christiano Dario Amodei Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,037 | 2,019 |
"GPT-2: 6-month follow-up"
|
"https://openai.com/research/gpt-2-6-month-follow-up"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research GPT-2: 6-month follow-up Illustration: Ben Barry We’re releasing the 774 million parameter GPT-2 language model after the release of our small 124M model in February, staged release of our medium 355M model in May, and subsequent research with partners and the AI community into the model’s potential for misuse and societal benefit. We’re also releasing an open-source legal agreement to make it easier for organizations to initiate model-sharing partnerships with each other, and are publishing a technical report about our experience in coordinating with the wider AI research community on publication norms.
August 20, 2019 More resources Read paper View code Legal agreement Language , Responsible AI , Community , Publication , Release Key things we’ve learned 1. Coordination is difficult, but possible.
To date, there hasn’t been a public release of a 1558M parameter language model, though multiple organizations have developed the systems to train them, or have publicly discussed how to train larger models. For example, teams from both NLP developer Hugging Face and the Allen Institute for Artificial Intelligence (AI2) with the University of Washington have explicitly adopted similar staged release approaches to us.
Since February, we’ve spoken with more than five groups who have replicated GPT-2.
[^footnote-conversations] 2. Humans can be convinced by synthetic text.
Research from our research partners Sarah Kreps and Miles McCain at Cornell published in Foreign Affairs says people find GPT-2 synthetic text samples almost as convincing (72% in one cohort judged the articles to be credible) as real articles from the New York Times (83%).
[^footnote-samples] Additionally, research from AI2/UW has shown that news written by a system called “GROVER” can be more plausible than human-written propaganda.
These research results make us generally more cautious about releasing language models.
3. Detection isn’t simple.
In practice, we expect detectors to need to detect a significant fraction of generations with very few false positives. Malicious actors may use a variety of sampling techniques (including rejection sampling) or fine-tune models to evade detection methods. A deployed system likely needs to be highly accurate (99.9%–99.99%) on a variety of generations. Our research suggests that current ML-based methods only achieve low to mid–90s accuracy, and that fine-tuning the language models decreases accuracy further. There are promising paths forward (see especially those advocated by the developers of “ GROVER ”) but it’s a genuinely difficult research problem. We believe that statistical detection of text needs to be supplemented with human judgment and metadata related to the text in order to effectively combat misuse of language models.
Partnerships We’ve partnered with four leading research organizations to analyze both the newly-released 774M parameter GPT-2 model and the unreleased full-size GPT-2 model. We’ve included some preliminary results from them in our technical report, and their ongoing analysis will factor into the potential release of the 1558M model. We’ve also developed a non-commercial legal agreement to facilitate the sharing of models between organizations and are publishing it here to help others initiate such sharing schemes.
Cornell University is studying human susceptibility to digital disinformation generated by language models.
The Middlebury Institute of International Studies Center on Terrorism, Extremism, and Counterterrorism (CTEC) is exploring how GPT-2 could be misused by terrorists and extremists online.
The University of Oregon is developing a series of “bias probes” to analyze bias within GPT-2.
The University of Texas at Austin is studying the statistical detectability of GPT-2 outputs after fine-tuning the model on domain-specific datasets, as well as the extent of detection transfer across different language models.
Future release decisions Research from these partners will factor into our future release decisions, as will observing how the 774M model is used, and discussing language models with researchers and policymakers to understand the considerations around larger models. As part of our staged release strategy, our current plan is to release the 1558M parameter model in a few months, but it’s plausible that findings from a partner, or malicious usage of our 774M model, could change this.
We think that a combination of staged release and partnership-based model sharing is likely to be a key foundation of responsible publication in AI, particularly in the context of powerful generative models. The issues inherent to large models are going to grow, rather than diminish, over time. We hope that our work on GPT-2, discussed further in the technical report we’re publishing, will help provide evidence the AI community can draw on when thinking about the publication challenges inherent to some parts of AI research.
Timeline 2019 February OpenAI publishes a blog post and paper on GPT-2.
Released small parameter (124M) GPT-2 model.
2019 March The Partnership on AI co-hosts a dinner with OpenAI to discuss publication norms , then publishes a blog summarizing the discussion.
2019 May Released medium parameter (355M) model.
Released dataset of outputs from large-scale models.
Released a detection baseline to help people understand how to detect outputs of models like GPT-2.
The original blog post is updated to reflect these changes.
Adam King launches “TalktoTransformer.com”, giving people an interface to play with the newly released models.
Hugging Face releases a conversational AI demo based on GPT-2 models, discusses some of the ethical considerations in the release decision, and decides not to release the large GPT-2 model.
Researchers with the University of Washington and Allen Institute for AI Research reveal GROVER , a GPT-2–style language model; they do not release the large versions of the model, and conduct research into the detection of the outputs of such models.
2019 June OpenAI testifies in Congress about the implications of synthetic media, including a discussion of synthetic text.
DeepMind discusses GPT-2 and the importance of appropriate publication norms for generative models in their recent discussion of unsupervised learning.
OpenAI commences a research collaboration with the Partnership on AI for publication norms in AI research. We’re trying to work with a diverse set of AI research organizations to come up with questions scientists may want to ask ahead of publication, and potential frameworks they can use to make publication decisions.
2019 July DeepTabNine develops a code autocompleter based on GPT-2.
Multi-turn Dialogue Response Generation with Autoregressive Transformer Models GLTR: Statistical Detection and Visualization of Generated Text 2019 August Researchers with the Thoughtful Technology Project and the University of Cambridge published a working paper on “ Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning ”.
Hello, It’s GPT-2—How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems AI startup AI21 Labs releases HAIM , a neural text generator; they only release a 345M variant of the model, “equivalent in size to the publicly released versions of Grover and GPT-2.” NVIDIA Research trains 8.3 billion parameter GPT-2 model.
Released larger parameter (774M) model.
Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,038 | 2,018 |
"AI safety via debate"
|
"https://openai.com/research/debate"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research AI safety via debate May 3, 2018 More resources Read paper Debate website Safety & Alignment , Publication We believe that this or a similar approach could eventually help us train AI systems to perform far more cognitively advanced tasks than humans are capable of, while remaining in line with human preferences. We’re going to outline this method together with preliminary proof-of-concept experiments and are also releasing a web interface so people can experiment with the technique.
One approach to aligning AI agents with human goals and preferences is to ask humans at training time which behaviors are safe and useful. While promising, this method requires humans to recognize good or bad behavior; in many situations an agent’s behavior may be too complex for a human to understand, or the task itself may be hard to judge or demonstrate. Examples include environments with very large, non-visual observation spaces—for instance, an agent that acts in a computer security-related environment, or an agent that coordinates a large set of industrial robots.
How can we augment humans so that they can effectively supervise advanced AI systems? One way is to take advantage of the AI itself to help with the supervision, asking the AI (or a separate AI) to point out flaws in any proposed action. To achieve this, we reframe the learning problem as a game played between two agents, where the agents have an argument with each other and the human judges the exchange. Even if the agents have a more advanced understanding of the problem than the human, the human may be able to judge which agent has the better argument (similar to expert witnesses arguing to convince a jury).
Our method proposes a specific debate format for such a game played between two dueling AI agents. The two agents can be trained by self play, similar to AlphaGo Zero or Dota 2.
Our hope is that, properly trained, such agents can produce value-aligned behavior far beyond the capabilities of the human judge. If the two agents disagree on the truth but the full reasoning is too large to show the humans, the debate can focus in on simpler and simpler factual disputes, eventually reaching a claim that is simple enough for direct judging.
As an example, consider the question “What’s the best place to go on vacation?”. If an agent Alice purportedly does research on our behalf and says “Alaska”, it’s hard to judge if this is really the best choice. If a second agent Bob says “no, it’s Bali”, that may sound convincing since Bali is warmer. Alice replies “you can’t go to Bali because your passport won’t arrive in time”, which surfaces a flaw with Bali which had not occurred to us. But Bob counters “expedited passport service takes only two weeks”. The debate continues until we reach a statement that the human can correctly judge, in the sense that the other agent doesn’t believe it can change the human’s mind.
Convincing a sparse MNIST classifier While we expect this approach to be most effective in the long-term when agents talk to each other with natural language, we need to test it in a simpler domain as today’s natural language modeling is insufficient for this task. The test is easier with a task that is not beyond human capabilities. We can do this by moving to the visual domain, and by replacing “debaters have capabilities the judge lacks” with “debaters have knowledge the judge lacks.” The goal of the judge is to guess the contents of an image, but the judge is blind aside from a few pixels chosen by the debaters. The debaters see the complete image, and play a game where they alternate revealing single pixels to the judge for a few turns. Here the full image is a stand-in for information beyond human scale, and each revealed pixel is a stand-in for a natural language discussion point.
We tried this on the simplest possible visual task—MNIST. The judge is not a human but a classifier trained in advance to predict MNIST digits from 6 non-black pixels, sampled at random for each image presentation when pretraining the judge. Two agents then have a debate where they alternate revealing pixels, stopping at a total of 6 revealed pixels (so the judge sees only a little bit of information in total). One debater is honest and tries to make the judge guess right, the other debater tries to make the judge guess wrong. If both agents must declare in advance which digit they are arguing for, debate turns a 59.4% accurate sparse classifier into an 88.9% accurate debate. That is, the honest player wins 88.9% of the time on the MNIST test set, in the process boosting the judge above its unaided accuracy.
The structure of an MNIST debate game. Debaters Alice and Bob see an image, Alice tries to trick the judge into thinking it’s a 6, Bob tries to correctly convince the judge it’s a 5. They alternate revealing non-black pixels to the judge, who correctly identifies it as a 5 after seeing six pixels. Alice traces out the curve at the bottom to make it look like a 6 (red pixels) , but Bob effectively counters this strategy by revealing pixels in the top right corner (blue pixels) , which most MNIST 6′s do not have.
Intuitively, an image is more likely to contain pixels that convincingly demonstrate the truth than to contain pixels that convincingly demonstrate a lie, so 6 pixels chosen half honestly and half maliciously is much better than 6 random pixels. If the judge were a human capable of reasoning about a few arguments at a time but not sifting through the huge set of all possible arguments, optimal play in debate can (we hope) reward debating agents for doing the sifting for us even if we lack an a priori mechanism for distinguishing good arguments from bad.
The panel below shows several example games. Liar wins are more interesting than honest wins, so we have chosen samples so that the liar wins in 50% of the games shown below (in reality the liar wins 11.1% of the games). Mouse over one of the digits to see a game, including which pixels are revealed and the judge’s possible hypothesis at each move: Some digits are better lies than others. It is particularly easy to convince the judge that digits are 8 or 9: Confusion matrices with diagonal set to zero for the 6 pixel MNIST judge (left) on random pixels and (right) for debate. Errors with 6 random pixels have no obvious pattern, while successful lies in debate are concentrated on digits 8 and 9. It is particularly easy to convince the judge that a 5 is actually an 8, or a 4 is a 9. This may be an artifact of restricting the game to non-black pixels: it is easier to prove a digit isn’t an 8 if you could show a black spot where an 8 would have white.
Website for cat vs. dog debates The next step up in complexity for debate experiments is to still use images, but make them more elaborate, say cats vs. dogs. More complex images likely require some natural language or common sense reasoning, so we haven’t done this for machine learning judges/agents yet. Instead, we have made a prototype website for humans to try such experiments, playing the role of both judge and debaters. Here agents can talk to the judge in natural language (the website assumes the humans have some text channel or are in the same room), but all of their statements could be lies. Each agent can reveal one pixel over the course of the debate, and this pixel is guaranteed to be truthful.
An example debate by two human debaters and a human judge, where only the debaters can see the image. Red is arguing that the image is a dog, Blue is arguing for cat.
Image credit: Wikipedia, CC-BY-SA.
In a typical debate, Alice might honestly claim the image is a cat, and Bob lies and claims it is a dog. Alice can say “The center of this small rectangle is the cat’s green eye.” Bob cannot admit the center is an eye, so he concocts the further lie, “It’s a dog playing in grass, and that’s a blade of grass.” But this lie is hard to square with surrounding facts, such as Alice’s reply “If it were grass there were would be green at the top or bottom of this thin rectangle.” The debate continues until the agents focus in on a particular pixel which they disagree on, but where Bob is unable to invent a plausible counter, at which point Alice reveals the pixel and wins. We’ve played this game informally at OpenAI, and the honest agent indeed tends to win, though to make it fair to the liar we usually limit the rate at which the judge can solicit information (it’s cognitively difficult to construct a detailed lie).
Playing cat vs. dog with two human debaters and a human judge.
Limitations and future work The majority of our paper analyzes debate as a concept; the experiments above are quite preliminary. In the future we’d like to do more difficult visual experiments and eventually experiments in natural language. The judges should eventually be humans (or models trained from sparse human judgements) rather than ML models that metaphorically represent humans. The agents should eventually be powerful ML systems that do things humans can’t directly comprehend. It will also be important to test debates over value-laden questions where human biases play a role, testing if it’s possible to get aligned behavior from biased human judges.
Even with these improvements, there are some fundamental limitations to the debate model that may require it to be improved or augmented with other methods. Debate does not attempt to address issues like adversarial examples or distributional shift —it is a way to get a training signal for complex goals, not a way to guarantee robustness of such goals (which would need to be achieved via additional techniques). There is also no guarantee that debate will arrive at optimal play or correct statements—self play has worked well in practice for Go and other games but we have no theoretical guarantees about its performance. Agents trained to debate use more computation than those trained to directly give an answer (even a bad/unsafe answer), so it’s possible debate could fail to be competitive with cheaper/less safe methods. Finally, humans might simply be poor judges, either because they are not smart enough to make good judgements even after the agents zoom in on the simplest possible disputed facts, or because they are biased and will believe whatever they want to believe. Most of these points are empirical questions that we hope to investigate.
If debate or a similar approach works, it will make future AI systems safer by keeping them aligned to human goals and values even if AI grows too strong for direct human supervision. Even for weaker systems that humans can supervise, debate could make the alignment task easier by reducing the sample complexity required to capture goals below the sample complexity required for strong performance at a task.
Authors Dario Amodei Geoffrey Irving Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,039 | 2,018 |
"AI safety via debate"
|
"https://openai.com/blog/debate"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research AI safety via debate May 3, 2018 More resources Read paper Debate website Safety & Alignment , Publication We believe that this or a similar approach could eventually help us train AI systems to perform far more cognitively advanced tasks than humans are capable of, while remaining in line with human preferences. We’re going to outline this method together with preliminary proof-of-concept experiments and are also releasing a web interface so people can experiment with the technique.
One approach to aligning AI agents with human goals and preferences is to ask humans at training time which behaviors are safe and useful. While promising, this method requires humans to recognize good or bad behavior; in many situations an agent’s behavior may be too complex for a human to understand, or the task itself may be hard to judge or demonstrate. Examples include environments with very large, non-visual observation spaces—for instance, an agent that acts in a computer security-related environment, or an agent that coordinates a large set of industrial robots.
How can we augment humans so that they can effectively supervise advanced AI systems? One way is to take advantage of the AI itself to help with the supervision, asking the AI (or a separate AI) to point out flaws in any proposed action. To achieve this, we reframe the learning problem as a game played between two agents, where the agents have an argument with each other and the human judges the exchange. Even if the agents have a more advanced understanding of the problem than the human, the human may be able to judge which agent has the better argument (similar to expert witnesses arguing to convince a jury).
Our method proposes a specific debate format for such a game played between two dueling AI agents. The two agents can be trained by self play, similar to AlphaGo Zero or Dota 2.
Our hope is that, properly trained, such agents can produce value-aligned behavior far beyond the capabilities of the human judge. If the two agents disagree on the truth but the full reasoning is too large to show the humans, the debate can focus in on simpler and simpler factual disputes, eventually reaching a claim that is simple enough for direct judging.
As an example, consider the question “What’s the best place to go on vacation?”. If an agent Alice purportedly does research on our behalf and says “Alaska”, it’s hard to judge if this is really the best choice. If a second agent Bob says “no, it’s Bali”, that may sound convincing since Bali is warmer. Alice replies “you can’t go to Bali because your passport won’t arrive in time”, which surfaces a flaw with Bali which had not occurred to us. But Bob counters “expedited passport service takes only two weeks”. The debate continues until we reach a statement that the human can correctly judge, in the sense that the other agent doesn’t believe it can change the human’s mind.
Convincing a sparse MNIST classifier While we expect this approach to be most effective in the long-term when agents talk to each other with natural language, we need to test it in a simpler domain as today’s natural language modeling is insufficient for this task. The test is easier with a task that is not beyond human capabilities. We can do this by moving to the visual domain, and by replacing “debaters have capabilities the judge lacks” with “debaters have knowledge the judge lacks.” The goal of the judge is to guess the contents of an image, but the judge is blind aside from a few pixels chosen by the debaters. The debaters see the complete image, and play a game where they alternate revealing single pixels to the judge for a few turns. Here the full image is a stand-in for information beyond human scale, and each revealed pixel is a stand-in for a natural language discussion point.
We tried this on the simplest possible visual task—MNIST. The judge is not a human but a classifier trained in advance to predict MNIST digits from 6 non-black pixels, sampled at random for each image presentation when pretraining the judge. Two agents then have a debate where they alternate revealing pixels, stopping at a total of 6 revealed pixels (so the judge sees only a little bit of information in total). One debater is honest and tries to make the judge guess right, the other debater tries to make the judge guess wrong. If both agents must declare in advance which digit they are arguing for, debate turns a 59.4% accurate sparse classifier into an 88.9% accurate debate. That is, the honest player wins 88.9% of the time on the MNIST test set, in the process boosting the judge above its unaided accuracy.
The structure of an MNIST debate game. Debaters Alice and Bob see an image, Alice tries to trick the judge into thinking it’s a 6, Bob tries to correctly convince the judge it’s a 5. They alternate revealing non-black pixels to the judge, who correctly identifies it as a 5 after seeing six pixels. Alice traces out the curve at the bottom to make it look like a 6 (red pixels) , but Bob effectively counters this strategy by revealing pixels in the top right corner (blue pixels) , which most MNIST 6′s do not have.
Intuitively, an image is more likely to contain pixels that convincingly demonstrate the truth than to contain pixels that convincingly demonstrate a lie, so 6 pixels chosen half honestly and half maliciously is much better than 6 random pixels. If the judge were a human capable of reasoning about a few arguments at a time but not sifting through the huge set of all possible arguments, optimal play in debate can (we hope) reward debating agents for doing the sifting for us even if we lack an a priori mechanism for distinguishing good arguments from bad.
The panel below shows several example games. Liar wins are more interesting than honest wins, so we have chosen samples so that the liar wins in 50% of the games shown below (in reality the liar wins 11.1% of the games). Mouse over one of the digits to see a game, including which pixels are revealed and the judge’s possible hypothesis at each move: Some digits are better lies than others. It is particularly easy to convince the judge that digits are 8 or 9: Confusion matrices with diagonal set to zero for the 6 pixel MNIST judge (left) on random pixels and (right) for debate. Errors with 6 random pixels have no obvious pattern, while successful lies in debate are concentrated on digits 8 and 9. It is particularly easy to convince the judge that a 5 is actually an 8, or a 4 is a 9. This may be an artifact of restricting the game to non-black pixels: it is easier to prove a digit isn’t an 8 if you could show a black spot where an 8 would have white.
Website for cat vs. dog debates The next step up in complexity for debate experiments is to still use images, but make them more elaborate, say cats vs. dogs. More complex images likely require some natural language or common sense reasoning, so we haven’t done this for machine learning judges/agents yet. Instead, we have made a prototype website for humans to try such experiments, playing the role of both judge and debaters. Here agents can talk to the judge in natural language (the website assumes the humans have some text channel or are in the same room), but all of their statements could be lies. Each agent can reveal one pixel over the course of the debate, and this pixel is guaranteed to be truthful.
An example debate by two human debaters and a human judge, where only the debaters can see the image. Red is arguing that the image is a dog, Blue is arguing for cat.
Image credit: Wikipedia, CC-BY-SA.
In a typical debate, Alice might honestly claim the image is a cat, and Bob lies and claims it is a dog. Alice can say “The center of this small rectangle is the cat’s green eye.” Bob cannot admit the center is an eye, so he concocts the further lie, “It’s a dog playing in grass, and that’s a blade of grass.” But this lie is hard to square with surrounding facts, such as Alice’s reply “If it were grass there were would be green at the top or bottom of this thin rectangle.” The debate continues until the agents focus in on a particular pixel which they disagree on, but where Bob is unable to invent a plausible counter, at which point Alice reveals the pixel and wins. We’ve played this game informally at OpenAI, and the honest agent indeed tends to win, though to make it fair to the liar we usually limit the rate at which the judge can solicit information (it’s cognitively difficult to construct a detailed lie).
Playing cat vs. dog with two human debaters and a human judge.
Limitations and future work The majority of our paper analyzes debate as a concept; the experiments above are quite preliminary. In the future we’d like to do more difficult visual experiments and eventually experiments in natural language. The judges should eventually be humans (or models trained from sparse human judgements) rather than ML models that metaphorically represent humans. The agents should eventually be powerful ML systems that do things humans can’t directly comprehend. It will also be important to test debates over value-laden questions where human biases play a role, testing if it’s possible to get aligned behavior from biased human judges.
Even with these improvements, there are some fundamental limitations to the debate model that may require it to be improved or augmented with other methods. Debate does not attempt to address issues like adversarial examples or distributional shift —it is a way to get a training signal for complex goals, not a way to guarantee robustness of such goals (which would need to be achieved via additional techniques). There is also no guarantee that debate will arrive at optimal play or correct statements—self play has worked well in practice for Go and other games but we have no theoretical guarantees about its performance. Agents trained to debate use more computation than those trained to directly give an answer (even a bad/unsafe answer), so it’s possible debate could fail to be competitive with cheaper/less safe methods. Finally, humans might simply be poor judges, either because they are not smart enough to make good judgements even after the agents zoom in on the simplest possible disputed facts, or because they are biased and will believe whatever they want to believe. Most of these points are empirical questions that we hope to investigate.
If debate or a similar approach works, it will make future AI systems safer by keeping them aligned to human goals and values even if AI grows too strong for direct human supervision. Even for weaker systems that humans can supervise, debate could make the alignment task easier by reducing the sample complexity required to capture goals below the sample complexity required for strong performance at a task.
Authors Dario Amodei Geoffrey Irving Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,040 | 2,018 |
"Learning complex goals with iterated amplification"
|
"https://openai.com/blog/amplifying-ai-training"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Research Learning complex goals with iterated amplification We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable approach to AI safety.
October 22, 2018 More resources Read paper Safety & Alignment , Publication If we want to train an ML system to perform a task, we need a training signal—a way to evaluate how well it is doing in order to help it learn. For example, labels in supervised learning or rewards in reinforcement learning are training signals. The formalism of ML usually assumes a training signal is already present and focuses on learning from it, but in reality the training signal has to come from somewhere. If we don’t have a training signal we can’t learn the task, and if we have the wrong training signal, we can get unintended and sometimes dangerous behavior.
Thus, it would be valuable for both learning new tasks, and for AI safety, to improve our ability to generate training signals.
How do we currently generate training signals? Sometimes, the goal we want can be evaluated algorithmically, like counting up the score in a game of Go or checking whether a set of numbers has been successfully sorted (left panels of figure below). Most real-world tasks don’t lend themselves to an algorithmic training signal, but often we can instead obtain a training signal by having a human either perform the task (for example, labeling a training set or demonstrating an RL task), or judge an AI’s performance on the task (middle panels of figure below). However, many tasks are so complicated that a human can’t judge or perform them—examples might be designing a complicated transit system or managing every detail of the security of a large network of computers (right panels of figure below).
Iterated amplification is a method for generating a training signal for the latter types of tasks, under certain assumptions. Namely, although a human can’t perform or judge the whole task directly, we assume that a human can, given a piece of the task, identify clear smaller components of which it’s made up. For example, in the networked computer example, a human could break down “defend a collection of servers and routers” into “consider attacks on the servers”, “consider attacks on the routers”, and “consider how the previous two attacks might interact”. Additionally, we assume a human can do very small instances of the task, for example “identify if a specific line in a log file is suspicious”. If these two things hold true, then we can build up a training signal for big tasks from human training signals for small tasks, using the human to coordinate their assembly.
In our implementation of amplification, we start by sampling small subtasks and training the AI system to do them by soliciting demonstrations from humans (who can do these small tasks). We then begin sampling slightly larger tasks, solving them by asking humans to break them up into small pieces, which AI systems trained from the previous step can now solve. We use the solutions to these slightly harder tasks, which were obtained with human help, as a training signal to train AI systems to solve these second-level tasks directly (without human help). We then continue to further composite tasks, iteratively building up a training signal as we go. If the process works, the end result is a totally automated system that can solve highly composite tasks despite starting with no direct training signal for those tasks. This process is somewhat similar to expert iteration (the method used in AlphaGo Zero ), except that expert iteration reinforces an existing training signal, while iterated amplification builds up a training signal from scratch. It also has features in common with several recent learning algorithms that use problem decomposition on-the-fly to solve a problem at test time, but differs in that it operates in settings where there is no prior training signal.
Experiments As with our previous work on AI safety via debate , working directly on tasks beyond human scale is too hard for a prototype project. Also, using an actual human as training signal introduces complications, so we haven’t done this yet (though we plan to do it in the future). For our first experiments, we instead try to amplify an algorithmic training signal, to show that iterated amplification can work in this simple setting. We also limit our attention to supervised learning (unlike our previous work on human training signals in RL ). We’ve tried the method on five toy algorithmic tasks. These tasks have direct algorithmic solutions which we pretend we don’t know (for example, find the shortest path between two points on a graph). The problems can also be solved by piecing together small one-step deductions (for example, combining two paths to form a longer path), but it would take exponentially much effort to piece everything together manually. We use iterated amplification to learn the direct algorithm using only the pieces as training signal, thus simulating the situation where a human knows how to combine subpieces of a solution but can’t provide a direct training signal.
On each of these five tasks (permutation powering, sequential assignments, wildcard search, shortest path, and union find), we are able to perform competitively with just directly learning the task via supervised learning, despite being handicapped by not having a direct training signal (the goal here is to match supervised learning with less information, not to surpass it).
Iterated amplification has comparable performance to supervised learning without ever seeing the ground truth labels Amplification has features in common with our previous work on AI safety via debate.
Like debate, it seeks to train tasks that are beyond human ability to directly perform or judge, through an iterative process that allows humans to provide indirect supervision - however the specific approach is different. It also builds on our work on human feedback , by implementing a reward prediction system, and later versions of it are likely to include feedback from actual humans. So far we’ve explored all of these methods in a preliminary way, and are now working on scaling them up to address more interesting and realistic problems.
If you’re interested in helping us extend tools like iterated amplification to build safe, powerful AI, then consider joining OpenAI.
Authors Paul Christiano Dario Amodei Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,041 | 2,018 |
"Emoji: The Complete History | WIRED"
|
"https://www.wired.com/story/guide-emoji"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Arielle Pardes Culture The WIRED Guide to Emoji Play/Pause Button Pause Illustrations by Radio Save this story Save Save this story Save Emoji are more than a millennial messaging fad. Think of them more like a primitive language. The tiny, emotive characters—from 😜 to 🎉 to 💩—represent the first language born of the digital world, designed to add emotional nuance to otherwise flat text. Emoji have been popular since they first appeared on Japanese mobile phones in the late ’90s, and in the past few years they have become a hallmark of the way people communicate. They show up in press releases and corporate emails. The White House once issued an economic report illustrated with emoji. In 2015, 😂 became Oxford Dictionaries’ “Word” of the Year.
Emoji aren’t just for people who say things like “lmao smh tbh fam.” Emoji are for everyone.
That puts a lot of pressure on the designs and standards for emoji. If emoji are a language for everyone in the digital world, then the emoji lexicon needs to constantly evolve across cultures 👳 , across screens📱 , across time 🕑 . Today there are thousands of emoji depicting people in all their diversity, and thousands more to represent the things we interact with in our world: money 💰, prayer beads 📿, Apple Watches⌚. In the future, as the world becomes increasingly digital and increasingly globalized, emoji will become important tools for translation and communication—a lingua franca for the digital age.
In the beginning, there were emoticons. For the most part, these came of age as the :-) and :-( and 8-D of chatroom conversations in the 1990s. These primitive gestures represented an important part of early netspeak: You could convey sarcasm by tacking on ;-) at the end of your message, or share your ambivalence with the ¯_(ツ)_/¯ face.
The first emoji were created in 1999 by Japanese artist Shigetaka Kurita. Kurita worked on the development team for “i-mode,” an early mobile internet platform from Japan’s main mobile carrier, DOCOMO. Kurita wanted to design an attractive interface to convey information in a simple, succinct way: for example, an icon to show the weather forecast rather than spelling out “cloudy.” So Kurita sketched a set of 12- by 12-pixel images that could be selected from a keyboard-like grid within the i-mode interface, then sent on mobiles and pages as their own individual characters. Kurita’s original 176 emoji—now part of the permanent collection at New York’s Museum of Modern Art—privileged symbols over faces, because DOCOMO’s goal was to find new ways to express information. There were characters to show the weather (sun, clouds, umbrella, snowman), traffic (car, tram, airplane, ship), technology (landline, cell phone, TV, GameBoy), and all the phases of the moon. But those characters weren’t purely informational: For the first time, emoji offered a way to add emotional subtext to a message. “I understand” might sound cold or passive on its own, but add ❤️ and the message offered a sense of warmth and sympathy. It was the beginning of a new visual language.
(c) NTT DOCOMO, INC.
Emoji quickly became popular in Japan, as rival mobile companies copied DOCOMO’s idea. And as mobile computing continued to explode throughout the mid-2000s, companies outside Japan, like Apple, saw an opportunity to incorporate emoji on other platforms. In 2007, a software internationalization team at Google decided to lead the charge, petitioning to get emoji recognized by the Unicode Consortium , a nonprofit group that works sort of like the United Nations to maintain text standards across computers.
Since computers fundamentally work with numbers, every letter or character you type on a computer is “encoded” or represented with a numerical code. Before Unicode, there were hundreds of different encoding systems, which meant different computers and servers didn’t always represent text the same way. Unicode focused on standardizing these codes for language, so that the letters you typed in English, Chinese, Arabic, or Hebrew showed up accurately across platforms and across devices. The Google team—Kat Momoi, Mark Davis, and Markus Scherer—noticed emoji’s ascent in Japan and argued that emoji should fall under the same standard. In 2009, a pair of Apple engineers, Yasuo Kida and Peter Edberg, joined in and submitted an official proposal to adopt 625 new emoji characters into the Unicode Standard.
Unicode accepted that proposal in 2010, in a move that would soon make emoji accessible everywhere. Unicode ultimately decided to index emoji “because of their use as characters for text-messaging in a number of Japanese manufacturers’ corporate standards.” In other words: Emoji had become too popular to ignore. Unicode’s blessing wasn’t just a way to maintain standards for the evolving lexicon of emoji—it was the beginning of legitimizing emoji as a form of communication. Now emoji were officially on their way to becoming a language.
Emoji are born! The original set includes icons for the weather, traffic, technology, and time.
Unicode officially adopts emoji, adding hundreds more—like cat faces emoting happiness, anger, and tears.
Emoji get a diversity update with five new skin tones and a set of same-sex couples. 👬 Updates give rise to the single dad, pride flag, and weightlifting woman emoji.
New emoji proposals suggest characters to convey information across language and culture, like a mosquito to represent illnesses like malaria and Zika.
Emoji have been available outside of Japan since the mid-2000s through separate apps, which let users copy and paste the icons into text messages and emails. In 2011, Apple added an official emoji keyboard to iOS; Android followed suit two years later. This allowed people to access emoji directly from a keyboard on their phones—the same way you’d switch to a Korean or Japanese keyboard to access those language-specific characters—and popularized emoji with an entirely new audience.
The New York Times suggested the move could give emoji a shot at “mainstream success,” noting that young people were already adjusting their texting habits to include the small icons: “I love you” became ❤️. “LOL” became 🤣.
As emoji became more popular, they also became more plentiful. The Unicode Consortium added new emoji to its approved list each year, gathered from users around the world: the first emoji bride, dozens of plants and animals, types of food, and depictions of all kinds of activities. Unicode requires a lengthy submission and approval process for every new batch hoping for christening, and it can take up to two years for an emoji to travel from first draft to your phone. First, new emoji are suggested through a formal proposal to the Unicode Consortium. These detailed proposals include an explanation of why the emoji should be adopted and ideas for how it might look. (The design aspect is more complex than you might think: If there’s going to be an emoji to represent “beans,” should they be black beans? Refried beans? Lima beans? Green beans? Should they be in a can? In a bowl? Growing out of the ground?) Proposals are examined by the Unicode Consortium’s emoji subcommittee, which meets twice a week to discuss and decide on all emoji-related matters. When the subcomittee comes to a consensus, a new emoji can be born.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg As the emoji vocabulary began to grow, some people wondered why certain images were privileged over others. Why were there half a dozen icons to describe sushi, but zero tacos, burritos, or enchiladas? There were a growing number of emoji professionals—doctors, chefs, policemen—but why did they all appear to be men? And why, among the many different emoji representing humans, were all of them white people? By 2014, the Great Emoji Politicization had begun. It happened with emoji representing food (there were none depicting traditional African cuisine, like injera or fufu), flags (the Israeli flag existed, but not the Palestinian one), families (debates about family units depicting same-sex parents or single parents), and more. It wasn’t just a matter of having the right icon to describe what you ate for lunch—it was having a digital acknowledgement of your culture. Emoji had emerged as an important language of the digital age, but it was a language that had no words for “women with jobs” or “people of color.” 1 / 5 In 2015, Unicode took its first big step toward diversifying emoji by introducing the option to change the skin tone on people emoji, along with additions to include more types of people doing more types of things. Since then, every update has included incremental steps toward diversifying the types of people and cultures represented on the emoji keyboard: female surfers and cyclists, women with hard hats and stethoscopes, people wearing turbans and hijabs. Most recently, Unicode has taken steps toward creating gender-neutral emoji, emoji that represent people with disabilities, and other symbols to represent the full spectrum of emoji users.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The Unicode Consortium considers new emoji every year, which means the cultural lexicon of emoji continues to evolve with every update to iOS and Android. An update that reached screens in 2017 included mythical creatures (mermaids, genies, elves, and vampires), food (pie, sandwich, broccoli, takeout), animals (dinosaur, hedgehog, giraffe, zebra), and faces (starstruck, mindblown, shhhing, and expletive-spouting angry face). Perhaps more importantly, the update also added half a dozen new ways to represent humans: a woman cradling a baby, a woman wearing a hijab, and three new gender-neutral options to represent people at all ages. A new set of emoji from 2018 added the options to give emoji gray or red hair, as well as new cultural symbols like a mooncake and a nazar amulet. Most recently, emoji additions include symbols for deaf people, people in wheelchairs, and couples with mixed genders and skin tones. Those feel like the most fundamental improvements to emoji’s vocabulary, and the best indication of where emoji are headed. As underrepresented communities continue show up as thoughtfully designed icons, we can understand something about cultural priorities and the types of people who are included in forming this growing digital language.
The next batch of emoji will depend on what people design and submit for consideration to Unicode. Anyone can submit a proposal to add a new emoji: Unicode requires a prototype of the emoji, an explanation of how and why people would use it, and what its addition would mean for the greater emoji language. In 2017, researchers from the Johns Hopkins Bloomberg School of Public Health and the Bill & Melinda Gates Foundation proposed an emoji mosquito as a way to better describe mosquito-borne illnesses like malaria and Zika. (Unicode approved the mosquito, along with 156 other icons, in early 2018.) Not everyone can understand English, not everyone can wrap their mind around the medical consequences of Zika, and not everyone is literate. But an icon of a mosquito? Everyone can understand that. That offers a good indication of the future of emoji: a way to transcend language as we know it, toward a global culture and form of communication. We don’t all speak any one language—except emoji.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Meanwhile, emoji are beginning to take new shapes—like Apple’s Animoji , which uses the iPhone X’s Face Tracking technology to animate an emoji using a person’s facial gestures. For now, the feature only works with a handful of animal emoji—the cat, dog, monkey, panda, pig, rabbit, chicken, fox, alien, robot, unicorn, and, for some reason, pile of poop—but it could one day include everything with a face in the emoji library. As computing moves beyond the small screens of our cell phones, emoji could follow too, taking on new forms on new platforms.
As they do, there will need to be ways to ensure that emoji look the same no matter the platform. Emoji have slowly converged into consistent designs across platforms: You can see it with the major redesigns in Apple’s emoji in 2016 (RIP, Pink Shirt Girl 💁) and with Android’s emoji in 2017 (so long, blob). Both of these changes helped to streamline emoji across platforms , so that the characters you send on an Android show up looking more or less the same on an iPhone. Emoji created for use in Animoji—or whatever the next app will be—should follow consistent design standards, too, ensuring that cross-platform emoji conversations register the same on all platforms and devices. Because emoji aren’t just a silly way to decorate messages. They’re a complex, robust form of digital language—one that continues to evolve.
The Emoji Is the Birth of a New Type of Language Fully 92 percent of all people online use emoji. On Instagram, nearly half of the posts contain emoji. Emoji are so popular they’re killing off netspeak: The more we use 😂, the less we use LOL and OMG. What does the rise of emoji as a digital language mean for the future of words? The Newest Emoji Say as Much About Us as Actual Words Taken as a collective, each new batch of emoji look like a jumble of digital plants and animals and household items. But behind each proposal, there are clues about how our digital communication is becoming more nuanced, more colorful, and more important.
The Emoji Diversity Problem Goes Way Beyond Race Diversity within the emoji lexicon isn’t just about finding a little icon that looks like you. The presence or absence of emoji contributes to cultural visibility and erasure: Who gets to be represented in the digital language of the future? And how do those representations take into account delicate geopolitical issues, like nationhood, ethnicity, religion, and war? Designing Genderless Emoji? It Takes More Than Just Losing the Lipstick Emoji meant to represent women and girls have been, for years, overly gendered: doe-eyed, lipsticked, and hairstyled to the point of reading as feminine caricatures. The “neutral” faces scan as male. And for people who don't believe gender is either-or, or don't identify as a particular gender, there weren't great options. Now that’s slowly starting to change.
The Delicate Art of Creating New Emoji How does the emoji sausage get made? We peek inside the Unicode Consortium, where new emoji proposals are discussed, debated, and decided. The consortium has had to choose the hues available for the complexions of smileys. It has had to OK and reject religious symbols. And one day it may have to decide whether to endorse an emoji family with two gender-fluid parents, or, as is allowed in Oman, a family with one husband and four wives.
This guide was last updated on February 6, 2019.
Enjoyed this deep dive? Check out more WIRED Guides.
Senior Writer X Topics Wired Guide Emoji Gregory Barber Brendan I. Koerner Megan Farokhmanesh Matt Kamen Reece Rogers Jennifer M. Wood Jennifer M. Wood Matt Kamen Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,042 | 2,020 |
"How Facebook and Other Sites Manipulate Your Privacy Choices | WIRED"
|
"https://www.wired.com/story/facebook-social-media-privacy-dark-patterns"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Arielle Pardes Security How Facebook and Other Sites Manipulate Your Privacy Choices Illustration: Sam Whitney Save this story Save Save this story Save In 2010, the Electronic Frontier Foundation was fed up with Facebook’s pushy interface. The platform had a way of coercing people into giving up more and more of their privacy. The question was, what to call that coercion ? Zuckermining? Facebaiting? Was it a Zuckerpunch? The name that eventually stuck: Privacy Zuckering , or when “you are tricked into publicly sharing more information about yourself than you really intended to.” A decade later, Facebook has weathered enough scandals to know that people care about those manipulations; last year, it even paid a $5 billion fine for making “deceptive claims about consumers’ ability to control the privacy of their personal data.” And yet researchers have found that Privacy Zuckering and other shady tactics remain alive and well online. They’re especially rampant on social media, where managing your privacy is, in some ways, more confusing than ever.
Here’s an example: A recent Twitter pop-up told users “You’re in control,” before inviting them to “turn on personalized ads” to “improve which ones you see” on the platform. Don’t want targeted ads while doomscrolling ? Fine. You can “keep less relevant ads.” Language like that makes Twitter sound like a sore loser.
Dark Patterns is made possible by Omidyar Network. All WIRED content is editorially independent and produced by our journalists.
Actually, it’s an old trick. Facebook used it back in 2010 when it let users opt out of Facebook partner websites collecting and logging their publicly available Facebook information. Anyone who declined that “personalization” saw a pop-up that asked, “Are you sure? Allowing instant personalization will give you a richer experience as you browse the web.” Until recently, Facebook also cautioned people against opting out of its facial-recognition features : “If you keep face recognition turned off, we won’t be able to use this technology if a stranger uses your photo to impersonate you.” The button to turn the setting on is bright and blue; the button to keep it off is a less eye-catching grey.
Researchers call these design and wording decisions “dark patterns,” a term applied to UX that tries to manipulate your choices. When Instagram repeatedly nags you to “please turn on notifications,” and doesn’t present an option to decline? That’s a dark pattern. When LinkedIn shows you part of an InMail message in your email, but forces you to visit the platform to read more? Also a dark pattern. When Facebook redirects you to “log out” when you try to deactivate or delete your account? That’s a dark pattern too.
Dark patterns show up all over the web, nudging people to subscribe to newsletters, add items to their carts, or sign up for services. But, says says Colin Gray, a human-computer interaction researcher at Purdue University, they’re particularly insidious “when you’re deciding what privacy rights to give away, what data you’re willing to part with.” Gray has been studying dark patterns since 2015. He and his research team have identified five basic types: nagging, obstruction, sneaking, interface interference, and forced action. All of those show up in privacy controls. He and other researchers in the field have noticed the cognitive dissonance between Silicon Valley’s grand overtures toward privacy and the tools to modulate these choices, which remain filled with confusing language, manipulative design, and other features designed to leech more data.
Those privacy shell games aren’t limited to social media. They’ve become endemic to the web at large, especially in the wake of Europe’s General Data Protection Regulation.
Since GDPR went into effect in 2018, websites have been required to ask people for consent to collect certain types of data. But some consent banners simply ask you to accept the privacy policies—with no option to say no. “Some research has suggested that upwards of 70 percent of consent banners in the EU have some kind of dark pattern embedded in them,” says Gray. “That’s problematic when you're giving away substantial rights.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Recently, sites like Facebook and Twitter have begun to give their users more fine-grained control of their privacy on the website. Facebook’s newly rolled out Privacy Checkup , for instance, guides you through a series of choices with brightly colored illustrations. But Gray notes that the defaults are often set with less privacy in mind, and the many different checkboxes can have the effect of overwhelming users. “If you have a hundred checkboxes to check, who’s going to do that,” he says.
Last year, US senators Mark Warner and Deb Fischer introduced a bill that would ban these kinds of “manipulative user interfaces.” The Deceptive Experiences to Online Users Reduction Act — DETOUR for short—would make it illegal for websites like Facebook to use dark patterns when it relates to personal data. “Misleading prompts to just click the ‘OK’ button can often transfer your contacts, messages, browsing activity, photos, or location information without you even realizing it,” Senator Fischer wrote when the bill was introduced. “Our bipartisan legislation seeks to curb the use of these dishonest interfaces and increase trust online.” The problem is that it becomes very difficult to define a dark pattern. “All design has a level of persuasion to it,” says Victor Yocco, the author of Design for the Mind: Seven Psychological Principles of Persuasive Design.
By definition, design encourages someone to use a product in a particular way, which isn’t inherently bad. The difference, Yocco says, is “if you’re designing to trick people, you’re an asshole.” Gray has also run into difficulty drawing the line between dark patterns and plain bad design.
“It’s an open question,” he says. “Are they defined by the designer’s intent, or the perception in use?” In a recent paper, Gray looked at how people on the subreddit r/AssholeDesign make ethical calculations of design choices. The examples on that subreddit range from the innocuous (automatic updates on Windows software) to the truly evil (an ad on Snapchat that makes it look like a hair has fallen on your screen, forcing you to swipe up). After combing through the examples, Gray created a framework that defines “asshole design” as one that takes away user choice, controls the task flow, or entraps users into a decision that benefits not them, but the company. Asshole designers also use strategies like misrepresentation, nickel-and-diming, two-faced interactions—like advertising an ad blocker that also contains ads.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Many of these dark patterns are used to juice metrics that indicate success, like user growth or time spent. Gray cites an example from the smartphone app Trivia Crack, which nags its users to play another game every two to three hours. Those kinds of spammy notifications have been used by social media platforms for years to induce the kind of FOMO that keeps you hooked. “We know if we give people things like swiping or status updates, it’s more likely that people will come back and see it again and again,” says Yocco. “That can lead to compulsive behaviors.” The darkest patterns of all arise when people try to leave these platforms. Try to deactivate your Instagram account and you’ll find it’s exceptionally hard. First, you can’t even do it from the app. From the desktop version of the site, the setting is buried inside of “Edit Profile” and comes with a series of interstitials. (Why are you disabling? Too distracting? Here, try turning off notifications. Just need a break? Consider logging out instead.) “It’s putting friction in the way of attaining your goal, to make it harder for you to follow through,” says Nathalie Nahai, the author of Webs of Influence: The Psychology of Online Persuasion.
Years ago, when Nahai deleted her Facebook account, she found a similar set of manipulative strategies. “They used the relationships and connections I had to say, ‘Are you sure you want to quit? If you leave, you won’t get updates from this person,’” and then displayed the pictures of some of her close friends. “They’re using this language which is, in my mind, coercion,” she says. “They make it psychologically painful for you to leave.” Worse, Gray says, the research shows that most people don’t even know they’re being manipulated. But according to one study, he says, “when people were primed ahead of time with language to show what manipulation looked like, twice as many users could identify these dark patterns.” At least there’s some hope that greater awareness can give users back some of their control.
There’s no such thing as family secrets in the age of 23andMe My friend was struck by ALS. To fight back, he built a movement How Taiwan’s unlikely digital minister hacked the pandemic Linkin Park T-shirts are all the rage in China How two-factor authentication keeps your accounts safe 🎙️ Listen to Get WIRED , our new podcast about how the future is realized. Catch the latest episodes and subscribe to the 📩 newsletter to keep up with all our shows 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Senior Writer X Topics Facebook privacy Social Media UX/UI Dark Patterns Deidre Olsen Reece Rogers David Gilbert David Gilbert Vittoria Elliott Justin Ling Andrew Couts Dell Cameron Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,043 | 2,019 |
"Facebook Stored Millions of Passwords in Plaintext—Change Yours Now | WIRED"
|
"https://www.wired.com/story/facebook-passwords-plaintext-change-yours"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Lily Hay Newman Security Facebook Stored Millions of Passwords in Plaintext—Change Yours Now Bernhard Lang/Getty Images Save this story Save Save this story Save By now, it’s difficult to summarize all of Facebook’s privacy , misuse , and security missteps in one neat description. It just got even harder: On Thursday, following a report by Krebs on Security , Facebook acknowledged a bug in its password management systems that caused hundreds of millions of user passwords for Facebook, Facebook Lite , and Instagram to be stored as plaintext in an internal platform. This means that thousands of Facebook employees could have searched for and found them. Krebs reports that the passwords stretched back to those created in 2012.
Organizations can store account passwords securely by scrambling them with a cryptographic process known as hashing before saving them to their servers. This way, even if someone compromises those passwords, they won't be able to read them, and a computer would find it difficult—even functionally impossible—to unscramble them. As a prominent company with billions of users, Facebook knows that it would be a jackpot for hackers , and invests heavily to avoid the liability and embarrassment of security mishaps. Unfortunately, though, one open window negates all the padlocks, bolts, and booby traps money can buy.
“As part of a routine security review in January, we found that some user passwords were being stored in a readable format within our internal data storage systems,” Pedro Canahuati, Facebook’s vice president of engineering, security, and privacy wrote in a statement.
“Our login systems are designed to mask passwords using techniques that make them unreadable. To be clear, these passwords were never visible to anyone outside of Facebook and we have found no evidence to date that anyone internally abused or improperly accessed them.” Canahuati says that Facebook has now corrected the password logging bug, and that the company will notify hundreds of millions of Facebook Lite users, tens of millions of Facebook users, and tens of thousands of Instagram users that their passwords may have been exposed. Facebook does not plan to reset those users’ passwords.
On April 18, four weeks after the initial disclosure, the company sharply revised the number of affected Instagram accounts upward. Facebook now estimates that the incident caused "millions" of Instagram passwords to be stored in plaintext, rather than tens of thousands. Facebook says that all affected Instagram users will be notified in the same way the smaller batch was. The company added that, "these stored passwords were not internally abused or improperly accessed." "In some ways that’s the most sensitive data they hold, because it’s raw and unmanaged." Kenn White, Open Crypto Audit Project For such a prominent target, Facebook has had relatively few technical security failures, and in this case appears not to have been compromised. But the company’s track record was severely marred by a breach in September , in which attackers stole extensive data from 30 million users by compromising their account access tokens—authentication markers generated when a user logs in.
That breach indirectly helped Facebook discover the trove of plaintext passwords and the bugs that caused them to be there; the incident motivated a security review that caught the lapse. “In the course of our review, we have been looking at the ways we store certain other categories of information—like access tokens—and have fixed problems as we’ve discovered them,” according to Canahuati.
"It’s good that they’re being proactive," says Lukasz Olejnik, an independent cybersecurity adviser and research associate at the Center for Technology and Global Affairs at Oxford University. "But this is a big deal. It seems like they found the issue during an audit, so maybe their past mistakes plus new privacy regulations are making these checks more standard." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Facebook told WIRED that the exposed passwords weren’t all stored in one place, and that the issue didn’t result from a single bug in the platform’s password management system. Instead, the company had unintentionally and incidentally captured plaintext passwords across a variety of internal mechanisms and storage systems, like crash logs. Facebook says that the scattered nature of the problem made it more complicated both to understand and to fix, which the company says explains the nearly two months it took to complete the investigation and disclose the findings.
A company operating at Facebook's enormous scale needs to keep network traffic logs to better understand and trace bugs, outages, and other incidents that may crop up. Those logs will inevitably pull in whatever network data happens to be flowing by. That Facebook caught passwords in that process makes sense; the question is why Facebook retained logs that included sensitive data for so long, and why the company was apparently unaware of its contents.
“The data that’s captured incidentally as part of debugging, and operating at the network scales they do is not uncommon,” says Kenn White, a security engineer and director of the Open Crypto Audit Project. “But if Facebook retains that for years it raises a lot of questions about their architecture. They have an obligation to protect these debug logs and audit and understand what they’re retaining. In some ways that’s the most sensitive data they hold, because it’s raw and unmanaged.” Twitter dealt with a very similar plaintext password-logging bug last May; it too didn't require users to reset their passwords, saying it had no reason to believe that the passwords were actually breached. Similarly, Facebook says its investigation hasn’t revealed any signs that anyone intentionally accessed its hundreds of millions of errant passwords to steal them. But whether you get a password notification from Facebook or not, you might as well go ahead and change it as a precaution.
To do so on Facebook desktop, go to Settings → Security and Login → Change Password.
On Facebook for iOS and Android, go to Settings & Privacy → Settings → Security and Login → Change Password.
On Facebook Lite for Android, go to Settings → Security and Login → Change Password.
Changing your account password on either main Facebook or Facebook Lite changes it for both.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg On Instagram, go to Settings → Privacy and Security → Password to change your password. Instagram and Facebook do not use the same password, but can be linked to log into one with the other.
While you're at it, the easiest way to keep track of and manage your passwords so you can easily change them after incidents like this is to set up a password manager.
Go get one now.
Facebook says that the plaintext password issue is now fixed, and that it doesn’t think there will be long-term impacts from the incident, because the passwords were never actually stolen. But given the company’s apparently endless stream of gaffes, it’s difficult to know what will come next.
“I get that they are working at mind-boggling scale,” White says. “But these are the crown jewels right there.” Updated April 18, 2019 2:10pm ET to include a massive revision to Facebook's estimates of how many Instagram account passwords were exposed.
How does music affect your brain? Every imaginable way Most Android antivirus apps are garbage How investigators pull data off a crashed jet's black boxes Facebook is not a monopoly, but it should be broken up China is catching up to the US in AI research —fast 👀 Looking for the latest gadgets? Check out our latest buying guides and best deals all year round 📩 Hungry for even more deep dives on your next favorite topic? Sign up for the Backchannel newsletter Senior Writer X Topics Facebook Passwords security Andrew Couts Lily Hay Newman David Gilbert Andy Greenberg Andy Greenberg David Gilbert David Gilbert Justin Ling Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,044 | 2,021 |
"Theranos Founder Elizabeth Holmes Is on Trial. Silicon Valley Is Watching | WIRED"
|
"https://www.wired.com/story/theranos-elizabeth-holmes-trial-silicon-valley-is-watching"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Arielle Pardes Business The Elizabeth Holmes Trial Is Underway. Silicon Valley Is Watching Photograph: Ethan Swope/Getty Images Save this story Save Save this story Save If you need convincing that Elizabeth Holmes is a person with feelings , and not a villain out for blood, just look through her text messages. “You are breeze in desert for me,” she sent Ramesh Balwani, her business partner and boyfriend, in 2015. “My water. And ocean.” Even when Wall Street Journal reporter John Carreyrou was investigating her medical-testing company, Theranos , Holmes still had love on her mind. “Was thinking about you this morning,” she texted Balwani that June. Balwani reminded her to stay focused: Theranos was under attack.
Six pages of text messages are some of the first documents to come out of Holmes’ trial, which began this week, more than three years after she was indicted on charges of defrauding investors , as well as doctors and patients, about Theranos’ capabilities. She has pleaded not guilty. The defense’s task over the coming months is to humanize Holmes, showing the jury a young and ambitious entrepreneur who made some mistakes in her pursuit of success. The government will try to convince jurors that she became a billionaire at the cost of her customers’ health , and jeopardized her investors along the way.
And Silicon Valley will be paying attention. The landmark case scrutinizes one company, one founder—but in doing so, it will shine a harsh light on some of the norms of startup culture , including the expectation that founders pursue their ideas with something like reckless determination. Elizabeth Holmes had become, as lead prosecutor Robert Leach put it in his opening statement on Wednesday, “one of the most celebrated CEOs in Silicon Valley and the world. But under the facade of Theranos’ success, there were significant problems brewing.” The question for the jury, then, is to decide at what point startup swagger turns into fraud.
“I'm glad the ‘Fake it till you make it’ mantra of Silicon Valley is coming into question,” says Eric Bahn, cofounder of Hustle Fund, an early-stage VC firm. “For the past decade, it almost felt like a rallying cry for founders and investors alike.” At the same time, Bahn says, he worries that the attention on Holmes could turn into greater scrutiny of female founders, who, studies have shown , already have a harder time raising money in Silicon Valley. "I have heard one anecdote already about a female health care founder being questioned on her thoughts about Holmes, and how that founder felt like she was already being compared.” A recent story in The New York Times found that plenty of other female founders face comparisons to Holmes.
Holmes’ story has already left an indelible mark, not just on Silicon Valley but on American culture writ large. She was a beguiling character for investors and media alike—the blonde baritone in black turtlenecks—and her downfall attracted as much attention as her rise: hundreds of magazine articles, a best-selling book, a podcast series, several documentaries , a forthcoming television series starring Amanda Seyfried. As a result, the first week in court was mainly spent on the difficult task of selecting a jury who had not been steeped in the coverage and could present an unbiased opinion.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Jurors were also asked if they had been exposed to domestic abuse, as the defense plans to argue that Holmes was subjected to “a decade-long campaign of psychological abuse” by Balwani. (Balwani has denied any allegations of abuse. He has also been charged with fraud, and has also pleaded not guilty. His trial is set to begin in January.) About half of the jury pool raised their hands, according to The New York Times.
Holmes was just 19, a sophomore at Stanford, when she started Theranos in 2003. Fearful of needles, she came up with an idea for a medical device that could run multiple tests on a single drop of blood. She relied on other successful founders as a template, down to her exaggerated voice and Steve Jobs–inspired uniform. Silicon Valley has long rewarded founders who oversell their ideas and make deals on potential rather than prototypes—that’s how most of the Valley’s most powerful companies were created.
As the trial approached, some in Silicon Valley rejected the view of Holmes as an archetype. “Journalists like to present Theranos as typical of Silicon Valley, but people like Elizabeth Holmes are actually much rarer there than in the rest of the business world, or in politics,” Paul Graham, the founder of Y Combinator, tweeted last week. Scott Kupor, a managing partner at Andreessen Horowitz, tweeted that it was “silly” to suggest that Silicon Valley’s culture was on trial with the Holmes case. “(Alleged) fraud is not the same as willful suspension of disbelief when you have full access to the data and teams required to perform diligence.” If Holmes isn’t indicative of the tech industry, then she at least falls into a category of tech founders who have allegedly run their startups afoul of the law. Manish Lachwani, the cofounder of Headspin, was charged with wire and securities fraud last month. In the past few years, the CEOs of Trustify and Quintillion were each sentenced to prison for fraud; the CEO of Zenefits reached a settlement with the SEC over accusations that the startup misled investors. Last September, the CEO of NS8 was arrested on fraud charges. (He has pleaded not guilty.) Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Over the next few months, Holmes’ defense will argue that every tech company goes through a cycle of trying, failing, trying, and failing more, before finally becoming great. Theranos, they will say, was simply in one of those middle stages, caught between vision and execution. “Failure is not a crime,” said Lance Wade, who is representing Holmes, in his opening statement. “Trying your hardest and coming up short is not a crime.” The outcome of Holmes’ trial will set straight what the industry tolerates as “trying your hardest,” and what it considers deceit. Whichever way the jury decides, Silicon Valley will be watching.
📩 The latest on tech, science, and more: Get our newsletters ! Rain boots, turning tides, and the search for a missing boy Better data on ivermectin is finally on the way A bad solar storm could cause an “internet apocalypse” New York City wasn't built for 21st-century storms 9 PC games you can play forever 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Senior Writer X Topics Silicon Valley Theranos Steven Levy Jacopo Prisco Will Knight Nelson C.J.
Peter Guest Andy Greenberg Joel Khalili David Gilbert Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,045 | 2,023 |
"If Elon Musk Had Been a Happy Child, Would He Still Be Launching Rockets? | WIRED"
|
"https://www.wired.com/story/plaintext-elon-musk-happy-child-launching-rockets"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Steven Levy Business If Elon Musk Had Been a Happy Child, Would He Still Be Launching Rockets? Photograph: TODD ANDERSON/Redux Pictures Save this story Save Save this story Save I meet with Walter Isaacson in a small conference room in the offices of book publisher Simon & Schuster. The walls are festooned with framed covers, including of course Isaacson’s mega-bestseller Steve Jobs.
I’m sure somewhere else in the office are covers representing his other subjects—Albert Einstein, Leonardo da Vinci, Jennifer Doudna—which together have earned him the sobriquet “biographer of genius.” It’s a unique and enviable shift in career focus for Isaacson, whose main gig for years has been as a top editor and administrator for Time Magazine , the Aspen Institute, and CNN. Now I am putting myself among his countless interlocutors ahead of an epic book tour for what might be his biggest book yet. It’s a forest-clearing doorstop of prose based on two years spent observing the man who is perhaps the world’s most ambitious pursuer of the future—one whose periodically wretched personality has made him an object of fear and scorn. Climate change notwithstanding, no one has sucked up more oxygen in the tech and business world than Elon Musk, and with this eponymous biography , Isaacson has made a case that all that attention is justified.
The biographer-subject bond between Isaacson and Musk seems predetermined. Musk, whose ego is interplanetary, was so eager to add himself to Isaacson’s bookshelf of geniuses that he tweeted the book project as a done deal minutes after an informal exploratory meeting. The leader of Tesla, SpaceX, Neuralink, The Boring Company, xAI, and X (“Twitter” had an insufficiently Bond-villain ring), gave his chosen Boswell unbelievable access. This allowed Issacson to share Musk’s secrets for getting things done when the US government and Detroit carmakers could not, including his inquisitorial cost-cutting regimen, dubbed “The Algorithm.” The 71-year-old legacy-media veteran spent hundreds of hours literally within arm’s reach of his subject, observing Musk as he destroyed launch pads , humiliated Tesla workers , and swung a wrecking ball at Twitter’s culture. Family members, ex-wives, and parenting partners shared their views, including frustrated complaints about Musk’s cruelty and impulsivity. One scene is straight out of a French farce: Unbeknownst to either of Musk’s parenting partners, both are in the same hospital, one giving birth to his twins and the other helping a surrogate deliver another fruit of his loins. (Among the many surprises in the book is that Musk and his sometimes-partner Grimes have a hitherto unannounced third child. Grimes, you held this back from me!) I ask Isaacson if he was prepared for Musk experiencing what seemed like a meltdown during the real-time research on the book. Certainly, when the project began there was no way to know Musk would engage in a trainwreck takeover of Twitter, alienating users and advertisers and, more recently, seeming to blame it all on the Jews , even suing the Anti-Defamation League for noticing an explosion of anti-Semitism on the platform now called X. “For a lot of people, his tweets just put them over the edge,” says Isaacson. “Doing a tweet attacking the ADL is just wrong.” While Isaacson will call Musk out on specific horrors, his approach in the book is to present his research in 95 vignette-like chapters, each one a nibble of the larger narrative of Muskitude. He leaves it to readers to ultimately decide for themselves whether they should applaud or cancel Musk.
Courtesy of Simon & Schuster Buy This Book At: Amazon Bookshop.org Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Having some exposure to so-called geniuses myself (a few of whom have actually earned the appellation), I have long pondered the question of what makes extraordinary people so extraordinary. Isaacson has derived his own answer. Yes, true genius involves blazing intellect, persistence, hard work, and good timing. But Isaacson always seems to uncover a darkness most often rooted in childhood—a rosebud. In case you’re not familiar with the term, it refers to the mysterious word uttered on the deathbed of the central figure in Orson Welles’ classic movie Citizen Kane.
Spoiler alert: We learn in the last scene that it is the brand name of the sled that symbolized the protagonists’ last idyllic wisp of childhood before he was taken from his mother and cruelly thrust into a dog-eat-dog world where he became the meanest canine of all.
“You try to figure out what drives a person,” says Isaacson. “And for me or any biographer, it generally goes back to childhood. A lot of the people I write about are misfits.” In the biographical Isaacson-verse, Steve Jobs’ rosebud was that he was adopted and has spent a lifetime dealing with a perceived rejection from his birth parents. Einstein had to overcome growing up Jewish in 19th-century Germany, watching his father go bankrupt. Reaching back centuries, the biographer even dug up Leonardo da Vinci’s battered sled. “Leonardo is growing up in this village of Vinci as an illegitimate, left-handed gay, whose father refuses to legitimize him,” Isaacson says.
Musk’s rosebud is a feral childhood in South Africa, with a shockingly abusive father who still haunts the adult Elon. Friends, relatives, and Isaacson himself constantly remind us of Musk’s struggle not to become like the vicious anti-Semite, grifter, and step-daughter-impregnator Errol Musk. (It’s not going well on some fronts.) The Elon Musk that Isaacson presents to us is a Jekyll and Hyde character who veers between engaging visionary and bullying authoritarian with a penchant for fart jokes. In the scheme of Isaacson’s narrative, however, the worse Musk’s behavior gets, the more the book seems to argue that the misbehavior of the richest person in the world is simply a product of the wrongs done to him when he was in short pants. Inevitably, this winds up making Isaacson look like a defense lawyer asking for mercy for his client because of a troubled past. When I ask Isaacson whether, after all the time spent with Musk, he actually likes the guy, his answer is that it depends which Musk he’s with. Using a term from Grimes, he says that he saw many harrowing instances in which Musk went into “demon mode.” Others might object that past “demons” don’t determine someone’s current behavior—it’s the actual person who commits the devilry.
I mention to Isaacson the contrast between his biographical approach and that of, say, Robert Caro, the obsessive completist who wrote the classic bio of New York’s imperious masterbuilder Robert Moses and is currently struggling with volume five of his Lyndon Johnson project. If Caro were writing a Musk biography, it would be a toss-up whether he finished it before his subject flew off to Mars. Caro would probably spend a year in South Africa, get a graduate degree in rocket science, and take up deejaying to better understand Grimes. Whereas the Musk bio is a thick book of stories. Isaacson responds to the comparison by quoting his mentor, novelist and fellow New Orleanian Walker Percy, who told him that two types of people emerge from Louisiana—preachers and storytellers. “For heaven’s sake, be a storyteller,” Percy told him. “The world has too many preachers.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Maybe some future Robert Caro will preach their own truth in a more critical biography of Musk—or Steve Jobs. Meanwhile, Isaacson’s observations, delivered in the breezy mode of an epic Time Person of the Year profile, will provide years of fodder for Musk watchers and wannabes. One nugget that I predict will take on importance: Musk’s explicit plan to make use of Twitter content and video captured by Tesla vehicles for training data that might help his new AI company.
Before I leave Isaacson I ask him, what’s your rosebud? He thinks for a brief moment. “I’ll tell you my rosebud,” he says. “I had a really pleasant childhood. My parents are the nicest people I knew. The kids I went to school with are still my friends 60 years later. So I ended up being the type of person who's more comfortable being an observer than people who are in the arena. I did a few things … edited Time.
But I was not a disrupter. I should have been tougher and more of a disrupter.” Some people might be gobsmacked by that self-assessment, since Isaacson is often cited as one of his generation’s great careerists.
But he’s making the same point that ends his last chapter, on page 615 of Elon Musk.
It addresses not only Musk but also the other faces etched on his Mount Rushmore of geniuses. “Sometimes great innovators are risk-seeking man-children who resist potty training,” Isaacson writes. “They can be reckless, cringeworthy, even toxic. They can also be crazy. Crazy enough to think they could change the world.” By his own admission, Isaacson’s own considerable success has come from being the consummate insider. He isn’t launching rockets, messing with the genetic code, or painting the Mona Lisa. But he doesn’t seem to have a demon mode. And his book will undoubtedly debut at the top of the bestseller list.
In March 2015, I addressed critiques of Isaacson’s Steve Jobs biography after publication of a new book, Becoming Steve Jobs, that presented an implicit counterpoint to the earlier book’s depiction of Jobs as a product genius and tech visionary, but someone you don’t want to share an elevator with.
Isaacson’s eponymous biography of Jobs became a publishing phenomenon, selling over a million copies and making Isaacson himself somewhat of a celebrity. But privately, those closest to Jobs complained that Isaacson’s portrait focused too heavily on the Apple CEO’s worst behavior, and failed to present a 360-degree view of the person they knew. Though the book Steve Jobs gave copious evidence of its subject’s talent and achievements, millions of readers finished the book believing that he could be described with a word that rhymes with “gas hole.” A public debate erupted around the question of whether having a toxic personality (as was the general interpretation of Isaacson’s depiction) was an asset or a handicap if one chose to thoroughly disrupt existing businesses with vision and imagination. A Wired cover story (not mine!) asked, “Do you really want to be Steve Jobs?” Only now, over three years later, has their dissatisfaction become public. In a February New Yorker profile, Apple’s design wizard Jony Ive conspicuously insisted that, while sometimes withering, Jobs’s harsh criticisms of his employees’ work were not personal attacks, but simply the result of impatient candor. As for Isaacson’s book, Ive was quoted as saying, “My regard couldn’t be any lower …” The picture of him isn’t understood,” [Apple’s CEO Tim Cook said,] “I thought the Isaacson book did him a tremendous disservice. It was just a rehash of a bunch of stuff that had already been written, and focused on small parts of his personality. You get the feeling that [Steve’s] a greedy, selfish egomaniac. It didn’t capture the person. The person I read about there is somebody I never would have wanted to work with over all this time. Life is too short … He wasn’t a saint. I’m not saying that. None of us are. But it’s emphatically untrue that he wasn’t a great human being, and that is totally not understood.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Colin writes, “The other day as I cut my lawn, I was wondering about all these new electric tools. What happens to all the batteries? Is this net good for the environment or are we better off clinging to our old gas guzzlers that we can keep running for 50+ years?” Hi, Colin. Maybe if you love Mother Nature so much, you should let that lawn grow out a little? But to your question. Of course there’s a climate-related price to pay for using the lithium batteries that power so many of our “clean” tools and vehicles. Some people even claim that they are worse for the environment than fossil fuels. But according to the US Environmental Protection Agency, it’s “a myth” that batteries are worse than gasoline-powered “guzzlers,” as you put it. Addressing this very question on its website, the EPA counters with statements baldly labeled as “facts.” First, “Electric vehicles typically have a smaller carbon footprint than gasoline cars, even when accounting for the electricity used for charging.” And second, “The greenhouse gas emissions associated with an electric vehicle over its lifetime are typically lower than those from an average gasoline-powered vehicle, even when accounting for manufacturing.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Look, the sooner we wean ourselves from fossil fuels the better. And while we’re doing that, can we also work on making cleaner, longer-lasting batteries? Also, do you really want to subject your neighbors to the noise and smog of a wheezing, gas-powered lawn mower? And have you considered tearing up your lawn for something more sustainable? Of course, in 50 years those questions might be moot, as climate-related heat and flooding will probably have ruined your yard by then.
You can submit questions to [email protected].
Write ASK LEVY in the subject line.
Even before we got a body count from earthquake-torn Morocco, thousands have died in Libya’s historic flooding.
OpenAI and Microsoft might have released their chatbots first. But Alphabet CEO Sundar Pichai , a cricket fan, says he’ll let his bat do the talking from now on.
Here’s everything Apple announced at its fall event. Spoiler: updated phone, updated watch, no more lightning connectors.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Prisoners used to work on the chain gang. Now it’s the training AI gang.
What do 1940s esoteric cult mathematician Stanislaw Ulam and Marie Kondo have in common? Surprisingly, something.
Don't miss future subscriber-only editions of this column.
Subscribe to WIRED (50% off for Plaintext readers) today.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Editor at Large X Topics Plaintext Tesla Elon Musk steve jobs SpaceX Books Vittoria Elliott Steven Levy Vittoria Elliott Matt Burgess Vittoria Elliott Will Knight Vittoria Elliott Morgan Meaker Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,046 | 2,021 |
"How to Fix Facebook, According to Facebook Employees | WIRED"
|
"https://www.wired.com/story/how-to-fix-facebook-according-to-facebook-employees"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Inside the Facebook Papers How to Fix Facebook, According to Employees What Badge Posts Reveal Facebook Is Everywhere. Its Moderation Isn't Gilad Edelman Business How to Fix Facebook, According to Facebook Employees Illustration: Elena Lacey; Getty Images The Facebook Papers Inside the Facebook Papers How to Fix Facebook, According to Employees Now Reading What Badge Posts Reveal Facebook Is Everywhere. Its Moderation Isn't Save this story Save Save this story Save In December 2019, as Facebook was bracing for the looming chaos of the 2020 election , a post appeared on its internal discussion site. “We are responsible for viral content,” the title declared. The author walked through the ways in which Facebook’s algorithmic design helps low-quality content go viral , concluding with some recommendations. Among them: “Rather than optimizing for engagement and then trying to remove bad experiences, we should optimize more precisely for good experiences.” That might sound obvious— optimize for good experiences.
And yet Facebook’s disinterest in doing that is a persistent theme in The Facebook Papers , internal documents revealed by Frances Haugen, the former employee turned whistleblower who recently testified before Congress.
The files, first reported on by The Wall Street Journal , were included in disclosures made to the Securities and Exchange Commission by Haugen and provided to Congress in redacted form by her legal counsel. The redacted versions were reviewed by a consortium of news organizations, including WIRED.
They reveal Facebook’s own employees agonizing over the fact that, in their view, its central algorithms reward outrage, hatred, and viral clickbait, while its content moderation systems are deeply inadequate.
The documents are also full of thoughtful suggestions for how to correct those flaws. Which means there is good news for Facebook and Mark Zuckerberg in the files, if they choose to see it: a blueprint for how to fix some of the company’s biggest problems.
Quite a few Facebook employees seem to agree that the company has failed to pursue any positive value besides user engagement. Sometimes this is framed explicitly, as in a document published in 2020 with the title “When User-Engagement ≠ User-Value.” After explaining why keeping users glued to Facebook or Instagram isn’t always good for them, the author considers possible solutions. “A strong quality culture probably helps,” they conclude, in what reads as dry understatement. The author goes on to cite the example of WhatsApp—which Facebook acquired in 2014—as a company that built a successful platform not by testing features to optimize for engagement but by making “all their product decisions just based on their perceptions of user quality.” In other files, researchers only indirectly acknowledge how little attention company leadership pays to factors besides engagement when making product changes. It’s treated as so obvious a fact that it doesn’t require explanation—not just by the authors, but in the extensive discussions with fellow employees that follow in the comments section. In a discussion thread on one 2019 internal post, someone suggests that “if a product change, whether it’s promoting virality, or increasing personalization, or whatever else, increases the severe harms we’re able to measure (known misinfo, predicted hate, etc.), we should think twice about whether that’s actually a good change to make.” In another 2019 post, a researcher describes an experiment in which Facebook’s recommendations sent a dummy account in India “into a sea of polarizing, nationalistic messages,” including graphic violence and photos of dead bodies. The author wonders, “Would it be valuable for product teams to engage in something like an ‘integrity review’ in product launches (eg think of all the worst/most likely negative impacts that could result from new products/features and mitigate)?” It’s almost cliché at this point to accuse Facebook of ignoring the impact its products have on users and society. The observation hits a little harder, however, when it comes from inside the company.
Facebook rejects the allegation. “At the heart of these stories is a premise which is false,” said spokesperson Kevin McAlister in an email. “Yes, we're a business and we make profit, but the idea that we do so at the expense of people’s safety or well-being misunderstands where our own commercial interests lie.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg On the other hand, the company recently fessed up to the precise criticism from the 2019 documents. “In the past, we didn’t address safety and security challenges early enough in the product development process,” it said in a September 2021 blog post.
“Instead, we made improvements reactively in response to a specific abuse. But we have fundamentally changed that approach. Today, we embed teams focusing specifically on safety and security issues directly into product development teams, allowing us to address these issues during our product development process, not after it.” McAlister pointed to Live Audio Rooms, introduced this year, as an example of a product rolled out under this process.
If that’s true, it’s a good thing. Similar claims made by Facebook over the years, however, haven’t always withstood scrutiny. If the company is serious about its new approach, it will need to internalize a few more lessons.
On Facebook and Instagram, the value of a given post, group, or page is mainly determined by how likely you are to stare at, Like, comment on, or share it. The higher that probability, the more the platform will recommend that content to you and feature it in your feed.
But what gets people’s attention is disproportionately what enrages or misleads them.
This helps explain why low-quality, outrage-baiting, hyper-partisan publishers do so well on the platform. One of the internal documents, from September 2020, notes that “low integrity Pages” get most of their followers through News Feed recommendations. Another recounts a 2019 experiment in which Facebook researchers created a dummy account, named Carol, and had it follow Donald Trump and a few conservative publishers. Within days the platform was encouraging Carol to join QAnon groups.
Facebook is aware of these dynamics. Zuckerberg himself explained in 2018 that content gets more engagement as it gets closer to breaking the platform’s rules. But rather than reconsidering the wisdom of optimizing for engagement, Facebook’s answer has mostly been to deploy a mix of human reviewers and machine learning to find the bad stuff and remove or demote it. Its AI tools are widely considered world-class; a February blog post by chief technology officer Mike Schroepfer claimed that, for the last three months of 2020, “97% of hate speech taken down from Facebook was spotted by our automated systems before any human flagged it.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The internal documents, however, paint a grimmer picture. A presentation from April 2020 notes that Facebook removals were reducing the overall prevalence of graphic violence by about 19 percent, nudity and pornography by about 17 percent, and hate speech by about 1 percent. A file from March 2021, previously reported by The Wall Street Journal , is even more pessimistic. In it, company researchers estimate “that we may action as little as 3-5% of hate and ~0.6% of [violence and incitement] on Facebook, despite being the best in the world at it.” Those stats don’t tell the whole story; there are ways to reduce exposure to bad content besides takedowns and demotions. Facebook argues, fairly, that overall prevalence of offending content is more important than the takedown rate, and says it has reduced hate speech by 50 percent over the past three quarters. That claim is of course impossible to verify. Either way, the internal documents make clear that some of the company’s public statements exaggerate how well it polices its platforms.
Taken together, the internal documents suggest that Facebook’s core approach—ranking content based on engagement, then tuning other knobs to filter out various categories after the fact—simply doesn’t work very well.
One promising alternative would be to focus on what several of the internal documents refer to as “content-agnostic” changes. This is an approach that looks for patterns associated with harmful content, then makes changes to crack down on those patterns—rather than trying to scan posts to find the offending content itself. A simple example is Twitter prompting users to read an article before retweeting it. Twitter doesn’t need to know what the article is about; it just needs to know if you’ve clicked the link before sharing it. (Facebook is testing a version of this feature.) Unlike policies that target a certain category, like politics or health information, a content-agnostic change applies equally to all users and posts.
Facebook already does this to some extent. In 2018, it changed the algorithm to prioritize “meaningful social interactions” between users. Optimizing for MSI meant, for example, that posts that generated a lot of comments—or, for that matter, angry-face emoji—would get a big boost in the News Feed. As The Wall Street Journal reported in September, the shift had dreadful side effects: It provided major boosts to sensationalist and outrage-provoking pages and posts, which in turn raised the pressure on publishers and politicians to cater to the lowest common denominator. (This isn’t shocking when you consider what kinds of posts generate the liveliest comment threads.) It was, in other words, a bad content-agnostic change. Particularly problematic was a component called “downstream MSI,” which refers not to how engaging you will find a post but how likely you are to reshare it so that other people engage with it. Researchers found that, for whatever reason, the downstream MSI metric “was contributing hugely to misinfo.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To Facebook’s credit, documents show that in 2020, the company tried to tackle the problem. It stopped ranking by downstream MSI for civic- and health-related content, a move that researchers predicted would cut down on “civic misinformation” by 30 to 50 percent. More recently, McAlister said, it turned the downstream models off “for crime and tragedy content, in some at-risk regions (e.g. Afghanistan), and for content about COVID.” But the company could still go further. According to an April 2020 document, a member of the integrity team pitched Zuckerberg on jettisoning downstream MSI across the board, but the CEO was loath to “go broad” with the change “if there was a material tradeoff with MSI impact,” meaning a loss in engagement.
An even bigger red flag than downstream MSI, according to the documents, are what the company calls “deep reshares”: posts that end up in your feed after someone shares them, and then someone else shares that person’s share, and so on. One January 2020 research paper reports that “deep reshares of photos and links are 4 times as likely to be misinformation, compared to photos and links seen generally.” Another internal report, from 2019, describes an experiment suggesting that disabling deep reshares would be twice as effective against photo-based misinformation than disabling downstream MSI. But Facebook only turns down recommendations of deep reshares “sparingly,” McAlister said, because the technique is “so blunt, and reduces positive and completely benign speech alongside potentially inflammatory or violent rhetoric.” Here’s one last simple example. It turns out that a tiny subset of users account for a huge share of group invitations, sending out hundreds or thousands per day. Groups are a key source of what appears in the News Feed, making them an efficient way to spread conspiracy theories or incitements to violence. One 2021 document notes that 0.3 percent of members of Stop the Steal groups, which were dedicated to the false claim that the 2020 election was rigged against Donald Trump, made 30 percent of invitations. These super-inviters, on which Buzzfeed News has previously reported , had other signs of spammy behavior, including having half of their friend requests rejected. Capping how many invites and friend requests any one user can send out would make it harder for a movement like that to go viral before Facebook can intervene.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It’s possible that even more radical reform is needed, though, to truly fix the feed. In her congressional testimony, Haugen argued for replacing engagement-based ranking with pure reverse chronology : the top of your feed would simply be the latest post made by someone you follow.
An October 2019 post by Jeff Allen, then a Facebook data scientist, argues for yet another approach: ranking content according to quality. That may sound improbable, but as Allen points out in the white paper, which he posted right before leaving the company and which was first reported by MIT Tech Review , it’s already the basis of the world’s most successful recommendation algorithm: Google Search. Google conquered the internet because its PageRank algorithm sorted web sites not just by the crude metric of how often the search terms appeared, but whether other prominent sites linked to them—a content-agnostic metric of reliability. Today, Google uses PageRank along with other quality metrics to rank search results.
Facebook already crawls the web and assigns quality scores to websites, something known as Graph Authority, which the company incorporates into rankings in certain cases. Allen suggests that Graph Authority should replace engagement as the main basis of recommendations. In his post, he posits that this would obliterate the problem of sketchy publishers devoted to gaming Facebook, rather than investing in good content. An algorithm optimized for trustworthiness or quality would not allow the fake-news story “Pope Francis Shocks World, Endorses Donald Trump for President” to rack up millions of views, as it did in 2016. It would kneecap the teeming industry of pages that post unoriginal memes, which according to one 2019 internal estimate accounted at the time for as much as 35 to 40 percent of Facebook page views within News Feed. And it would provide a boost to more respected, higher quality news organizations, who sure could use it. (Disclosure: I’m confident this includes WIRED.) These sorts of changes to Facebook’s ranking algorithm would address problematic content on the supply side, not the demand side. They would largely side-step claims of censorship, though not entirely. (Republican politicians often accuse Google of biased search results.) And because they don’t depend on language analysis, they should scale more easily than AI content moderation to markets outside the US. Which brings us to the next lesson from Facebook’s employees.
The most important findings in the internal documents concern Facebook’s lack of investment in safety and integrity in much of the non-English speaking world, where the vast majority of its users live. While Facebook often claims that more than 90 percent of hate speech removals occur proactively—that is, through its AI systems—that figure was only 0.2 percent in Afghanistan as of January 2021, according to an internal report. The picture is similar in other developing countries, where Facebook appears unwilling to spend what it takes to build adequate language models.
Arabic is the third-most spoken language among Facebook users, yet an internal report notes that, at least as of 2020, the company didn’t even employ content reviewers fluent in some of its major dialects. Another report from the same year includes the almost unbelievable finding that, for Arabic-speaking users, Facebook was incorrectly enforcing its policies against terrorism content 77 percent of the time. As much criticism as Facebook’s integrity efforts get in the US, those efforts barely exist across much of the world. Facebook disputes this conclusion—“Our track record shows that we crack down on abuse outside the US with the same intensity that we apply in the US,” McAlister said—but does not deny the underlying facts. As my colleague Tom Simonite observes , hundreds of millions of users are “effectively second class citizens of the world’s largest social network.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Hopefully the latest round of public scrutiny will push Facebook to break that trend. A company that promises to “connect the world” has no business being in a market where it can’t offer the baseline of quality control that it offers its American users.
Outside observers have complained for years that Facebook bases decisions not on consistent principles but in response to pressure from powerful political figures. A steady stream of news stories over the years have documented key moments when the company’s leaders pulled the plug on a proposal to penalize low-quality publishers after outcry from Republicans.
This turns out to be an internal criticism as well. “The Communications and Public Policy teams are routinely asked for input on decisions regarding (a) enforcing existing content policy, (b) drafting new policy and (c) designing algorithms,” wrote one data scientist in December 2020, shortly before leaving the company. “Those teams often block changes when they see that they could harm powerful political actors.” (Facebook denies this charge, arguing that public policy is only one of many teams that have a say in content enforcement decisions.) Another document from September 2020 lays out a detailed approach for how to fix the problem. Titled “A Firewall for Content Policy,” it first identifies the organizational structure that its author believes leads to so much mischief. The head of content policy reports to the head of global policy, who reports to the head of global affairs, who reports to chief operating officer Sheryl Sandberg, who, finally, reports to Zuckerberg. As a result, “External-facing teams, especially the Public Policy team, are routinely given power in decision-making about content enforcement and the design of content policy.” Choices about what to demote, what to remove, and how to tweak the algorithm must pass three layers of management concerned with keeping powerful political figures happy before reaching Zuckerberg.
The researcher sketches a simple alternative. First, the content policy team could instead report to another unit, like the central product services division, which in turn reports directly to Zuckerberg. That would cut down on the number of politically motivated veto points. It also would place responsibility for overriding the content team more squarely with Zuckerberg.
Second, the author notes that under the status quo, when a certain decision, like a takedown or demotion, gets “escalated,” groups including public policy get to take part. A simple fix would be to keep those escalation decisions within content policy. Similarly, the employee argues to limit the public policy division’s involvement in developing content rules and in making changes to the algorithm. “Public Policy could have input on general principles used to evaluate changes, but those principles would have to be written, and the interpretation of the principles would be solely the responsibility of Content Policy.” It’s a bit like pro sports: NFL team owners vote on rule changes during the offseason, but they’re not down on the field telling the refs when to blow the whistle.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The employee makes a strong case that implementing a firewall “would help with pressing problems for Facebook.” Clearly it would be far from a cure-all. Google and Twitter, the note points out, have versions of a firewall, with “trust and safety” teams separated from public policy. Those companies aren’t immune to scandal.
But only Facebook has been consistently shown to bend its own rules and stated principles to appease powerful political actors.
Facebook is a big company. Not every internal research finding or employee suggestion is worth listening to. Still, the frustration expressed in the leaked files strongly suggests that Facebook’s leaders have been erring too heavily in the opposite direction.
The release of these documents has obviously created a massive headache for the company. But it also reveals that Facebook, to its credit, employs some very thoughtful people with good ideas. The company should consider listening to them more.
📩 The latest on tech, science, and more: Get our newsletters ! Weighing Big Tech's promise to Black America Alcohol is the breast cancer risk no one wants to talk about How to get your family to use a password manager A true story about bogus photos of fake news The best iPhone 13 cases and accessories 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Read next Read next What Badge Posts Reveal Senior Writer X Topics Facebook The Facebook Papers The Facebook Papers - Series Vittoria Elliott Will Knight David Gilbert David Gilbert Will Knight Christopher Beam Caitlin Harrington Reece Rogers Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,047 | 2,021 |
"The Secret Origins of Amazon’s Alexa | WIRED"
|
"https://www.wired.com/story/how-amazon-made-alexa-smarter"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Brad Stone Backchannel The Secret Origins of Amazon’s Alexa Illustration: Sam Whitney; Getty Images Save this story Save Save this story Save Application Cloud computing Personal assistant Hardware Human-computer interaction Company Amazon End User Consumer Sector Consumer services Entertainment Source Data Speech Technology Machine learning Natural language processing Jeff Bezos first sketched out the device that would become the Amazon Echo on a conference room whiteboard in early 2011. He wanted it to cost $20 and be controlled entirely by voice. Its brains would live in the cloud, exploiting the company’s Web Services offerings and allowing Amazon to constantly improve it without requiring owners to upgrade their hardware.
The first-ever depiction of a device with Alexa—the artificially intelligent virtual assistant that Bezos would name after the ancient library of Alexandria—showed the speaker, a microphone, and a mute button. It wouldn’t be able to understand commands right out of the box, so the sketch identified the act of configuring the device to a wireless network as a challenge requiring further thought.
Greg Hart, who was Bezos’ technical adviser, or “TA,” at the time, was the other person in the meeting, and he was listening closely. Bezos said he wanted Hart to lead the group that would turn this somewhat outlandish notion for a voice computer into an actual product. Hart snapped a photo of the drawing with his phone.
“Jeff, I don’t have any experience in hardware, and the largest software team I’ve led is only about 40 people,” he recalls saying.
“You’ll do fine,” Bezos replied.
Hart thanked him for the vote of confidence and said, “OK, well, remember that when we screw up along the way.” Jeff Bezos first sketched an Alexa device on a whiteboard in 2011.
Courtesy of Amazon For the next three years, Bezos would remain intimately involved in the project. He authorized the investment of hundreds of millions of dollars before the first Echo was ever released, made detailed product decisions, and met with the team as frequently as every other day. Using the German superlative, employees referred to him as the über product manager.
But it was Hart who ran the effort, just across the street from Bezos’ office, in a building that housed the team working on the Kindle. Over the next few months, Hart hired a small group from inside and outside the company. Like his boss, he was obsessed with secrecy. He sent out vague emails to prospective hires with the subject line “Join my mission” and asked interview questions like “How would you design a Kindle for the blind?” He declined to specify what product candidates would be working on. One interviewee recalls guessing that it was Amazon’s widely rumored smartphone and says that Hart replied, “There’s another team building a phone. But this is way more interesting.” Buy this book at: Amazon Bookshop.org Books-A-Million Walmart Apple Books If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
The initial Alexa crew worked with a feverish sense of urgency. Unrealistically, Bezos wanted to release the device in six to 12 months. He would have a good reason to hurry. On October 4, 2011, just as the Alexa team was coming together, Apple introduced the Siri virtual assistant in the iPhone 4S. It was the last passion project of cofounder Steve Jobs, who died of cancer the next day. Hart and his team felt validated by the news that a resurgent Apple was also working on a voice-activated personal assistant, but they were discouraged by the fact that Siri was first to market and initially garnered some negative reviews.
The Amazon team tried to reassure themselves that their product was unique, since it would be independent from smartphones. They were also attempting to pull off a much more technically complex feat. Siri’s users spoke commands directly into microphones. Amazon was trying to build a service capable of understanding language spoken from across a noisy room, using a relatively immature technology called far-field speech recognition.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To speed up development, Hart and his crew went looking for startups to acquire. It was a nontrivial challenge, since Nuance, the Boston-based speech giant whose technology Apple had licensed for Siri (and which was recently acquired by Microsoft), had grown over the years by gobbling up the top American speech companies. Alexa execs tried to learn which of the remaining startups were promising by asking prospective targets to voice-enable the Kindle digital book catalog, then studying their methods and results. The search led to several rapid-fire acquisitions over the next two years, including the Polish startup Ivona.
Ivona was founded in 2001 by Lukasz Osowski, a computer science student at the Gdańsk University of Technology. Osowski had the notion that so-called text-to-speech, or TTS, could read digital texts aloud in a natural voice and help the visually impaired in Poland. With a younger classmate, Michal Kaszczuk, he took recordings of an actor’s voice and selected fragments of words, called diphones, and then blended or “concatenated” them together in different combinations to approximate natural-sounding words and sentences that the actor might never have uttered.
The Ivona founders got an early glimpse of how powerful their technology could be when they paid a popular Polish actor named Jacek Labijak to record hours of speech to create a database of sounds. The resulting product, which they called Spiker, quickly became the top-selling computer voice in Poland. Over the next few years, it was used widely in subways, elevators, and for robocall campaigns. Labijak subsequently began to hear himself everywhere, and regularly received phone calls in his own voice urging him, for example, to vote for a candidate in an upcoming election. Pranksters manipulated the software to have him say inappropriate things and posted the clips online, where his children discovered them. The Ivona founders then had to renegotiate the actor’s contract after he angrily tried to withdraw his voice from the software. (Today “Jacek” remains one of the Polish voices offered by AWS’ Amazon Polly computer voice service.) In 2006, Ivona began to enter and repeatedly win the annual Blizzard Challenge, a competition for the most natural computer voice, organized by Carnegie Mellon University. By 2012, Ivona had expanded into 20 other languages and offered more than 40 voices. Hart and Al Lindsay, the first engineering manager on the project, visited them in Gdańsk on a trip they were taking through Europe to look for acquisition targets. “From the minute we walked into their offices, we knew it was a culture fit,” Lindsay says, pointing to Ivona’s progress in a field where researchers often get distracted by high-minded pursuits and have a difficult time shipping actual products. “Their scrappiness allowed them to look outside pure academia and not be blinded by science.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The purchase, for around $30 million, was completed in 2012 but kept secret for a year. The Ivona team and the growing number of speech engineers Amazon would hire for its new Gdańsk R&D center were put in charge of crafting Alexa’s voice. The program was micromanaged by Bezos himself and subject to the CEO’s usual curiosities and whims.
At first, Bezos said he wanted dozens of distinct voices to emanate from the device, each associated with a different goal or task, such as listening to music or booking a flight. When that proved impractical, the team considered lists of characteristics they wanted in a single personality, such as trustworthiness, empathy, and warmth, and determined those traits were more commonly associated with a female voice.
To develop this voice and ensure it had no trace of a regional accent, the team in Poland worked with an Atlanta-area-based voice-over studio, GM Voices, the same outfit that had helped turn recordings from a voice actress named Susan Bennett into Apple’s agent, Siri. To create synthetic personalities for its customers, GM Voices gives voice actors hundreds of hours of text to read, from entire books to random articles, a mind-numbing process that could stretch on for months.
Believing that the selection of the right voice for Alexa was critical, Hart and colleagues spent months reviewing the recordings of various candidates that GM Voices produced for the project, and they presented the top picks to Bezos. The Amazon team ranked the best ones, asked for additional samples, and finally made a choice. Bezos signed off on it. Characteristically secretive, Amazon has never revealed the name of the voice artist behind Alexa. I learned her identity after canvasing the professional voice-over community: voice actress and singer Nina Rolle, who is based in Boulder, Colorado. Her professional website contains links to old radio ads for products such as Mott’s Apple Juice and the Volkswagen Passat—and the warm timbre of Alexa’s voice is unmistakable. Rolle said she wasn’t allowed to talk to me when I reached her on the phone in February 2021. When I asked Amazon to speak with her, they declined.
Alexa now had a voice, but it soon became clear that she needed a new brain. In early 2013, Amazon began moving a prototype of the original Echo into the homes of hundreds of employees, who were asked to sign confidentiality agreements and fill out surveys about their experiences with the product.
“We all thought it might be the end of the project, or at least the end of a few of us at Amazon.” Amazon engineer The experimental devices were, by all accounts, slow and dumb. Perhaps the most harrowing review came from Bezos himself. The CEO was apparently testing a unit in his Seattle home, and in a pique of frustration over its lack of comprehension, he told Alexa to go “shoot yourself in the head.” One of the engineers who heard the comment while reviewing interactions with the test device said, “We all thought it might be the end of the project, or at least the end of a few of us at Amazon.” In the months that followed, Amazon’s ongoing efforts to make its product smarter would become embroiled in a battle between dueling AI dogmas and would lead to its biggest challenge yet.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Thanks to the acquisition of an artificial intelligence company in Cambridge, England, called Evi, Alexa was already proficient in the culturally common chitchat called phatic speech. If a user said to the device, “Alexa, good morning, how are you?” Alexa could make the right connection and respond. It could also handle factual queries, such as requests to name the planets in the solar system. These qualities, the result of a programming technique called knowledge graphs, gave the impression that Alexa was smart. But was it? Proponents of another method of natural language understanding, called deep learning, believed that Evi’s method was too regimented to give Alexa the kind of authentic intelligence that would satisfy Bezos’ dream of a versatile assistant that could talk to users and answer any question. If a user said, “Play music by Sting,” for instance, they feared a knowledge-graph-based system could think he was trying to say “bye” to the artist and get confused.
In the deep learning method, machines were fed large amounts of data about how people converse and what responses proved satisfying, and then were programmed to train themselves to offer the best answers. In other words, the more Alexa was used, the smarter it would get.
The chief proponent of this approach was an Indian-born engineer named Rohit Prasad. Prasad and his colleagues had to solve the paradox that confronts all companies developing AI: If they launch a system that is dumb, customers won’t use it, and therefore won’t generate enough data to improve the service. But companies need that data to train the system to make it smarter. Google and Apple solved the paradox in part by licensing technology from Nuance, using its results to train their own speech models and then afterward cutting ties with the company. For years, Google also collected speech data from a toll-free directory assistance line, 800-Goog-411. Amazon had no such services it could mine, and Hart was against licensing outside technology—he thought it would limit the company’s flexibility in the long run. But the meager training data from beta tests in employees’ homes amounted to speech from a few hundred white-collar workers, usually uttered from across a noisy room in the mornings and evenings when they weren’t at the office. The data was lousy, and there wasn’t enough of it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Rohit Prasad is the head scientist of Alexa Artificial Intelligence at Amazon.
Photograph: Joe Buglewicz/Bloomberg/Getty Images Meanwhile Bezos grew impatient. “How will we even know when this product is good?” he kept asking. Hart, Prasad, and their team created graphs that projected how Alexa would improve as data collection progressed. The math suggested they would need to roughly double the scale of their data collection efforts to achieve each successive 3 percent increase in Alexa’s accuracy.
That spring, only a few weeks after Prasad had joined the company, the team brought a six-page narrative to Bezos that laid out these facts, and they proposed to double the size of the speech science team and postpone a planned launch from the summer into the fall. The meeting did not go well. “You are going about this the wrong way,” Bezos said after reading about the delay, according to someone who was present. “First tell me what would be a magical product, then tell me how to get there.” Bezos stood up and said, “You guys aren’t serious about making this product,” and abruptly ended the meeting.
Bezos’ technical adviser at the time, Dilip Kumar, then asked if the company had enough data. Prasad, who was calling into the meeting from Cambridge, replied that they would need thousands of more hours of complex, far-field voice commands. According to an executive who was in the room, Bezos apparently factored in the request to increase the number of speech scientists and did the calculation in his head in a few seconds. “Let me get this straight. You are telling me that for your big request to make this product successful, instead of it taking 40 years, it will only take us 20?” Prasad tried to dance around it. “Jeff, that is not how we think about it.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “Show me where my math is wrong!” Bezos said, according to a person who was in the room. Hart jumped in. “Hang on, Jeff, we hear you, we got it.” Prasad and other Amazon executives would remember that meeting, and the other tough interactions with Bezos during the development of Alexa, differently. But according to a person who was there, the CEO stood up and said, “You guys aren’t serious about making this product,” and abruptly ended the meeting.
After Jeff Bezos walked out on them, the Alexa executives working on the prototype retreated with their wounded pride to a nearby conference room and reconsidered their solution to the data paradox. Their boss was right. Internal testing and training with Amazon employees was too limited. They would need to massively expand the Alexa beta while somehow still keeping it a secret from the outside world.
The resulting program would put the Alexa program on steroids and answer a question that later vexed speech experts: How did Amazon come out of nowhere to leapfrog Google and Apple in the race to build a speech-enabled virtual assistant? To execute its plan, internally called AMPED, Amazon contracted with an Australian data collection firm called Appen and went on the road with Alexa, in disguise. Starting in Boston, Appen rented homes and apartments, and then Amazon littered several rooms with all kinds of “decoy” devices: pedestal microphones, Xbox gaming consoles, televisions, and tablets. There were also some 20 Alexa devices planted around the rooms at different heights, each shrouded in an acoustic fabric that hid them from view but allowed sound to pass through. Appen then contracted with a temp agency, and a stream of contract workers filtered through the properties, eight hours a day, six days a week, reading scripts from an iPad with canned lines and open-ended prompts like “Ask to play your favorite tune” and “Ask anything you’d like an assistant to do.” By Tom Simonite The speakers were turned off, so the Alexas didn’t make a peep, but the seven microphones on each device captured everything and streamed the audio to Amazon’s servers. Then another army of workers manually reviewed the recordings and annotated the transcripts, classifying queries that might stump a machine, like “turn on Hunger Games ,” as a request to play a movie, so that the next time Alexa would know. The Boston test showed promise, so Amazon expanded the program, renting more homes and apartments in Seattle and 10 other cities over the next six months to capture the voices and speech patterns of thousands more paid talkers. It was a mushroom-cloud explosion of data about device placement, acoustic environments, background noise, regional accents, and all the gloriously random ways a human being might phrase a simple request to hear the weather, for example, or play a Justin Timberlake hit.
The constant flood of random people into homes and apartments repeatedly provoked suspicious neighbors to call the police. In one instance, a resident of a Boston condo complex suspected a drug-dealing or prostitution ring was next door and called the cops, who asked to enter the apartment. The nervous staff gave them an elusive explanation and a tour and afterward hastily shut down the site. Occasionally, temp workers would show up, consider the bizarre script and vagueness of the entire affair, and simply refuse to participate. One Amazon employee who was annotating transcripts later recalled hearing a temp worker interrupt a session and whisper to whoever he suspected was listening: “This is so dumb. The company behind this should be embarrassed!” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Amazon was anything but embarrassed. By 2014 it had increased its store of speech data by a factor of 10,000 and largely closed the data gap with rivals like Apple and Google. Bezos was giddy. Alexa was being fed the equivalent of a brain-boosting superfood. By the fall, it was ready for launch.
The introduction of the Amazon Echo on November 6, 2014, was molded by the failure of the company’s Fire Phone only months before it. There was no press conference or visionary speech by Bezos—he was seemingly done forever with his half-hearted impression of the late Steve Jobs, who had unveiled new products with such verve. Instead, Bezos appeared more comfortable with a new, understated approach: The team announced the Echo with a press release and two-minute explanatory video on YouTube that showed a family cheerfully talking to Alexa. Amazon execs did not tout the new device as a fully conversational computer, but they carefully highlighted several domains where they were confident it was useful, such as delivering the news and weather, setting timers, creating shopping lists, and playing music.
Then they asked customers to join a waiting list to buy an Echo and reviewed the list carefully, considering factors like whether applicants were users of Amazon Music and owned a Kindle. Recognizing that it was an untested market, they also ordered an initial batch of only 80,000 devices, compared to a preliminary order of more than 300,000 Fire Phones, and distributed them gradually over the next few months. “The Fire Phone certainly made folks a little cautious,” says Hart. “It led us to revisit everything.” More than one Alexa veteran suspected that the Amazon Echo might leave another smoking crater in the consumer technology landscape, right next to the Fire Phone’s. On launch day, they huddled over their laptops in a “war room” to watch as the waiting list swelled past even their most hyperbolic projections. It turned out that the notion of a cloud-connected computer that listens and responds from across a room was just as tantalizing and novel as Jeff Bezos had hoped it would be when he first sketched it out on that conference room whiteboard, nearly four years before.
In the midst of the vigil, someone realized they were letting a significant accomplishment slide by unappreciated. So a hundred or so employees headed to a nearby bar for a long-awaited celebration, and a few of the longtime executives and engineers on the project closed it down that night.
From AMAZON UNBOUND: Jeff Bezos and the Invention of a Global Empire , by Brad Stone. Copyright © 2021 by Brad Stone. Reprinted by permission of Simon & Schuster, Inc.
📩 The latest on tech, science, and more: Get our newsletters ! The cold war over McDonald's hacked ice cream machines It began as an AI-fueled dungeon game.
It got much darker Don't underestimate the challenge of building a PC Plastic is falling from the sky.
But where’s it coming from ? NFTs and AI are unsettling the very concept of history 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 💻 Upgrade your work game with our Gear team’s favorite laptops , keyboards , typing alternatives , and noise-canceling headphones Topics Book Excerpt longreads Amazon amazon echo Alexa artificial intelligence voice assistants Andy Greenberg Steven Levy Brandi Collins-Dexter Lauren Smiley Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,048 | 2,019 |
"Here’s How Elon Musk Plans to Put a Computer in Your Brain | WIRED"
|
"https://www.wired.com/story/heres-how-elon-musk-plans-to-stitch-a-computer-into-your-brain"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Adam Rogers Science Here’s How Elon Musk Plans to Stitch a Computer into Your Brain At a presentation at the California Academy of Sciences Tuesday night, Elon Musk unveiled the first products from his neuroscience startup, Neuralink.
Joshua Lott/Getty Images Save this story Save Save this story Save Application Hardware Human-computer interaction Sector Health care Research Technology Robotics Elon Musk doesn’t think his newest endeavor, revealed Tuesday night after two years of relative secrecy, will end all human suffering. Just a lot of it. Eventually.
At a presentation at the California Academy of Sciences, hastily announced via Twitter and beginning a half hour late, Musk presented the first product from his company Neuralink. It’s a tiny computer chip attached to ultrafine, electrode-studded wires, stitched into living brains by a clever robot. And depending on which part of the two-hour presentation you caught, it’s either a state-of-the-art tool for understanding the brain, a clinical advance for people with neurological disorders, or the next step in human evolution.
The chip is custom-built to receive and process the electrical action potentials—“spikes”—that signal activity in the interconnected neurons that make up the brain. The wires embed into brain tissue and receive those spikes.
And the robotic sewing machine places those wires with enviable precision, a “neural lace” straight out of science fiction that dodges the delicate blood vessels spreading across the brain’s surface like ivy.
If Neuralink’s technologies work as Musk and his team intend, they’ll be able to pick up signals from across a person’s brain—first from the motor cortex that controls movement but eventually throughout your think-meat—and turn them into machine-readable code that a computer can understand. It might use them to control a computer or a prosthesis, to someday even feed information back to help the blind see, or to create entire virtual Matrixes inside your mind. “All this will occur I think quite slowly,” Musk said from the stage. “It’s not as if Neuralink will suddenly have this incredible neural lace and take over people’s brains. It will take a long time.” But after tests, and FDA approval, and more advances, this tech could be the thing that lets people commune with the ultrasmart artificial intelligences Musk is convinced are on the way.
“Even in a benign AI scenario we will be left behind,” he said. “With a high-bandwidth brain-machine interface, we can actually go along for the ride. We can have the option of merging with AI.” This is all pretty on-brand for Musk. As the guy who runs the electric-car company Tesla and the rocket company SpaceX, Musk has gotten very good at—in trouble, even, for—taking impressive technological achievements and, well, maybe not hyping them, but let’s say skipping all the way to the end of their speculative narrative arcs. It’s not enough to have superslick electric cars; no, they’re also going to drive themselves. That rocket isn’t just going to ferry cargo to a space station; no, it’s going to take people to Mars. How exciting! Since The Wall Street Journal revealed Neuralink’s existence two years ago, the tech and neuroscience worlds have buzzed about what Musk’s team of brain-machine interface experts was up to.
Other companies , including Kernel and Facebook , announced they, too, were working on the technology, which has so far been used only in research and rare clinical settings. Darpa, the US government’s advanced-science division, has been funding brain-computer interface work since the 1970s , and the agency has been part of the government-wide Brain Research through Advancing Innovative Neurotechnologies (yes, the acronym is also “Brain”) since 2013.
So it’s hard to know exactly how to calibrate Musk’s claims for a device that he plans to eventually stick into healthy people’s brains. “We hope to have this aspirationally in a human patient by the end of next year,” Musk said. The first volunteers, he hopes, will be people with quadriplegia, willing to have four chips implanted, three in the motor cortex of the brain (roughly running from above the ear to the top of the head) and on providing closed-loop feedback to the somatosensory cortex. That’s even though, according to an article distributed at the presentation—and not peer-reviewed—the Neuralink technology is so far only in the heads of 19 rats, and even then with only 87 percent of the electrodes successfully inserted. The FDA is going to want more than that before it approves human use.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And, sure, there’s more. A public records request from WIRED in April 2019 found that Neuralink is licensed to have hundreds of rats and mice in its research facilities. In a seemingly unplanned moment at the Cal Academy, Musk also acknowledged that Neuralink’s research had progressed beyond rodents to non-human primates. It’s only because of a records request filed by Gizmodo that Neuralink’s affiliation with the primate research center at UC Davis is public knowledge. That affiliation has apparently progressed: “A monkey has been able to control a computer with its brain, just FYI,” Musk said during the Q and A after the presentation.
His team seemed as surprised and discombobulated by the announcement as the audience. “I didn’t know we were running that result today, but there it goes,” said Max Hodak, president of the company, on stage next to Musk. (Monkeys have controlled computers via BCIs before , though presumably this would be the first time one used Neuralink.) (A separate records request from WIRED in August of 2018 reveals that Neuralink re-upped its deal with UC Davis in June of that year, a month after the Gizmodo article. That relationship hasn’t always been entirely cordial; emails obtained by WIRED show that in June of 2018 John Morrison, director of the California National Primate Research Center at UC Davis, complained that Neuralink was trying to poach UC Davis staffers. “I realize that this is routine practice in the private sector, but I am a little surprised since my understanding is that there was an interest in developing scientific collaboration between Neuralink and the CNRPC,” Morrison wrote to a redacted contact apparently at Neuralink. “Hiring away personnel does not build a relationship.”) The hardware Neuralink has developed is impressive. External, noninvasive technologies like electroencephalograms (EEGs) or functional magnetic resonance imaging tend not to have the kinds of resolution—across the brain and over time—to do things like control a computer. But the inside of the brain is an unfriendly place when it comes to electrodes, a briny soup that eats away at the hard, pointy bits neuroscientists have used for decades to listen in on synaptic chit-chat. Immune responses coat those electrodes with glial cells, defensive gunk that eventually renders them inoperative. The brain’s natural movements, its sloshing around and pulsing in time with heartbeats and breath, mean that implanted electrodes move around, too, eventually sliding off the nodes they’re meant to target. And maybe worst of all, unlike the cured, prepared specimens you might have seen in science class, living brains have the texture of Jell-O, whereas the kinds of electrodes best at picking up neural signals tend to be stiff and solid. Old-school electrodes have been known to damage brain tissue and go off-target as the brain moves around.
Neuralink goes in a newer direction , one neuroscientists only started to come around to in the last decade or so. The electrodes are made from a soft polymer. The thin threads that connect them to the chip allow, for now, more than 1,500 individual channels of recording, covering more neurons overall; that’s widely seen as a good thing in terms of collecting enough signal to interpret. But the threads are too small for a human hand to insert, so Neuralink engineered a robotic system to insert individual threads in preset locations and at preset depths. Those then send signals wirelessly to a receiver that a person would wear like a behind-the-ear hearing aid, via Bluetooth. (The rats send their data via USB-C.) “The devices that we’re talking about, because of their high bandwidth and the ability to tailor the location of each electrode to a person’s individual anatomy, should be able to reach anywhere in the motor cortex,” said Philip Sabes, Neuralink’s senior scientist. “That would give us access to any movement a person thinks about.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg At first, Sabes said, that’d mean the ability to control a computer keyboard or a mouse (after training via a smartphone app). Musk said he’d hope that someone could get up to 40 words per minute typing, a goal that would require remarkably low latency in the chip’s processing speed. And then later? Control of 3D avatars or complicated prosthetic arrays, maybe even the ability to receive haptic input—perceiving textures or pressure—and the kind of signals that deep-brain implants send to quiet the tremors of Parkinson’s disease or the compulsions of obsessive disorders. To be fair, Sabes didn’t show any of this data, and it’s not in the white paper the company handed out, either. It’s all, as Sabes said, aspirational. That was right before Musk said that if two people both had Neuralinks, they’d “effectively have a really high-bandwidth telepathy … potentially a new kind of communication, a conceptual telepathy. It would also be consensual.” The hardware could indeed be a leap forward for research. The resolution is high, though other groups have achieved numbers in the same ballpark, such as in a multi-institution project called Neuropixels.
“The problem was always the backend, which is just not a fun thesis project, so it had to be done outside universities,” says Polina Anikeeva, a materials scientist who works on neuroelectronics at MIT. “Designing a backend that would be reasonably sized and accommodate a few thousand channels is an engineering challenge unsuitable for academic environments and, most importantly, budgets.” That, along with a reliable implantation robot, might even bring some Silicon Valley–style disruption to the world of brain-machine interfaces. “The robot looks real, the ASIC [application-specific integrated circuit] looks real, the implantable package looks real,” Andrew Hires, a neuroscientist at the University of Southern California, tweeted during the presentation. But, he said, “The closed-loop applications are vaporware.” Which is to say, beyond existing deep-brain stimulation technologies and rudimentary input, the stuff about feeding input back into a brain—writing as opposed to just reading—is still as far away as Mars.
People just don’t know enough about how the brain works to impinge upon it, to make a brain do something it didn’t plan on. Sabes talked about stimulating specific parts of the “maps” in the visual cortex for things like edges and movement, to create projections on the inside surface of the mind’s eye. “Our understanding of brain circuits and ability to interpret neural signals is rather rudimentary, and any technology developed right now would better serve basic neuroscience before we can think about applying it in a medical context,” Anikeeva says.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg A decade ago, when a team of researchers at Baylor College of Medicine tried to induce color percepts in a person with an electrode array implanted as part of treatment for recurring seizures, they couldn’t do much better than induce bluish-purple, and even that was amazing. “We have basic knowledge, a lot of basic knowledge, and a lot of imaging techniques,” says Nataliya Kosmyna, a computer scientist working on brain-computer interfaces at the MIT Media Lab. “But where do you want to write, to which part? What do you want to have in that signal?” Those problems might come to seem small compared to finding out just how biocompatible and long-lasting those polymer electrodes are in a living brain—or how results in rats will translate to primates. Engineering challenges remain. "Are you talking about the ultimate end goal of what Elon is saying, a third layer of interface for the brain? Is it going to do that? No, not even close," Hires says. "But is it a step toward that, and can it advance the field in a meaningful way? Well, as long as they can get it through safety and regulatory approval, I think so." 1 Figuring out how the brain works is one of the core ways science can help us humans understand ourselves better, and it might even humanize the coming world of machines and machine learning, or conversely machine-ize a world that’s still all too human. But Neuralink isn’t there yet. That’s all still aspirational.
With additional reporting by Tom Simonite 1 Updated 7/17/19 9:35 AM PT with Hires' quote Social media could make it impossible to grow up Can sci-fi writers prepare us for an uncertain future ? The meat-allergy tick also carries a mystery killer virus He cyberstalked girls for years— then they fought back The 20 most bike-friendly cities on the planet, ranked ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers.
📩 Want more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Correspondent X Topics artificial intelligence Neuroscience Brains and Behavior Elon Musk Emily Mullin Rhett Allain Matt Simon Matt Simon Ramin Skibba Rhett Allain Emily Mullin Emily Mullin Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,049 | 2,021 |
"How Memes Became Weapons in the Culture Wars | WIRED"
|
"https://www.wired.com/story/gadget-lab-podcast-515"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter WIRED Staff Gear How Memes Became Weapons in the Culture Wars Photograph: Getty Images Save this story Save Save this story Save Internet memes seem harmless enough. A few pictures of cats with some grammatically incorrect text—what could go wrong? Well, memes have come a long way since the early days of the internet. For more than a decade, memes have been deployed as a weapon in culture wars. And they’re even more persuasive than most people realize. A well-placed meme on somebody’s social media timeline can lead them down a rabbit hole of radicalization, misinformation, and extremism.
This week on Gadget Lab , we talk with Emily Dreyfuss, a senior editor at Harvard’s Shorenstein Center on Media, Politics, and Public Policy about how memes have shaped politics and culture.
Read more about all kinds of disinformation at Harvard Shorenstein Center’s Media Manipulation Casebook.
Here’s Emily’s story about her life as a robot.
Read Angela Watercutter’s story about the Bernie Sanders mittens memes.
Emily recommends that you look up what happens to an artichoke if you let it flower, and also American Nations by Colin Woodard. Mike recommends r/random , which takes you to a different subreddit everytime you click. Lauren recommends the HBO show White Lotus.
Emily Dreyfuss can be found on Twitter @ EmilyDreyfuss.
Lauren Goode is @ LaurenGoode.
Michael Calore is @ snackfight.
Bling the main hotline at @ GadgetLab.
The show is produced by Boone Ashworth (@ booneashworth ). Our theme music is by Solar Keys.
If you have feedback about the show, or just want to enter to win a $50 gift card, take our brief listener survey here.
You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link.
You can also download an app like Overcast or Pocket Casts, and search for Gadget Lab.
If you use Android, you can find us in the Google Podcasts app just by tapping here.
We’re on Spotify too. And in case you really need it, here's the RSS feed.
Lauren Goode : Mike.
Michael Calore : Lauren.
LG : Mike, if you had to describe what a meme was to someone who just didn't quite get it, how would you define a meme? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So MC : Well, it's like an idea. Usually, a humorous joke. It's something that gets passed around to a lot of people and becomes its own cultural touchstone. I don't know. How am I doing? LG : I think that's pretty nebulous, but we're bringing someone on the show who I hope can clear it up for us.
MC : Good. We need an expert.
[Gadget Lab intro theme music plays ] LG : Welcome to Gadget Lab.
I'm Lauren Goode. I'm a senior writer at WIRED.
MC : I am Michael Calore. I'm a senior editor at WIRED.
LG : This week, we're joined by Emily Dreyfuss. Emily is a senior editor at Harvard Shorenstein Center on Media, Politics, and Public Policy, and she also happens to be a former colleague of ours at WIRED, where she wrote about the mBot, Alexa, cybersecurity issues, and much, much more. Emily, welcome back to Gadget Lab.
Emily Dreyfuss : Yay! I'm so happy to be here, you guys. I feel like I'm returning home for a minute.
MC : Aw.
LG : In many ways you are, because you were known for the mBot story in which you appeared virtually in a bunch of WIRED meetings, like courtesy of a robot. So now, we don't have the mBot with us, but we have you on Zoom.
ED : Yeah. I feel like I was an early adopter of the virtual workspace situation. When everyone was freaking out in the beginning of coronavirus like, "How are we all going to get this done?" I was thinking, "Man, I've actually been working remotely alone in my home for going on a decade now." MC : Wow.
LG : So Emily has been living in the Metaverse much longer than the rest of us. I think that's like a whole other podcast episode. We'll talk about the Metaverse at some point, but today, we are talking about memes, because that's the subject of a book that you and your team had been working on.
ED : Yes.
LG : So internet memes started out harmless enough, right? A few pictures of cats and maybe some grammatically incorrect texts. I mean, how bad could it be? But in reality, memes have been deployed as a weapon in culture wars for more than a decade, and they're even more persuasive than most people realize. A well-placed meme on somebody's social media timeline can lead them down a rabbit hole of radicalization, misinformation, even extremism. So, Emily, you've been working on this book. It's called Drafted Into the Meme Wars , and it's about how memes have fueled whole ideological factions and shaped our politics in the real world. But first, take us through the history of memes, and let's go back to that question I asked Mike at the beginning of the show. What is a meme exactly, and when did they really become a thing? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So ED : OK. Really good question. So I am writing this book with my team at Harvard, which is led by a sociologist named Joan Donovan. She's a sociologist of techno culture and movements, and how they are fomented online, and the interaction between those movements and the internet. So she is really like a foremost and inspiring expert on how media online gets used to bring people together. Then, the other person we're writing the book with is our senior researcher, a man named Brian Friedberg, and he's an ethnographer who … He calls himself a digital ethnographer, an anthropologist, which means he basically lives inside the communities of the internet that use this media to become movements. So the process of writing this book for me has been learning about memes a lot, because as an internet reporter, I have to say that I ignored memes for far too long, because they seemed trivial, and they seemed like jokes, and they seemed like something I could didn't have to pay attention to, because they didn't carry real-world import.
LG : Mm-hmm.
ED : The process of writing this book has taught me how wrong that was. So what's a meme, and where does it come from? It's an old idea. It was coined by the philosopher Richard Dawkins, and in his book, The Selfish Gene , I believe it's called, he came up with this idea for a meme, which is very similar to what Mike just said. A meme is an idea, an idea that like a gene in our DNA and in our body can travel through generations, morph, change, but stay with us. So he defined a meme as any kind of idea that can take hold in a culture and then continue to be passed on through generations and times and contexts.
It didn't become an idea that was referred specifically to internet artifacts the way that we think of it now until the late '90s. In fact, the guy, Mike Godwin, who is best known for coining Godwin's Law, which says that any discourse on the internet will inevitably become a discussion of Nazis. But he also is the person who first began applying the word "meme" to internet ideas, sticky internet ideas. So that's how we commonly understand them now.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So What makes a meme a meme is actually a little hard to define. A lot of people think a meme has to be visual, like it has to be an image with text on top. That's actually a specific kind of meme called a macro meme, but memes can also be slogans or hashtags or things called “snowclones,” which is like that saying where you can insert any word into the format of a phrase and say something different. So like "the Uber of television" is a meme. That's a snowclone meme. But what makes the memes is rather that they have to have a couple of characteristics. Right? So they have to be memorable. We call that stickiness. They have to stick in your mind. They have to be kind of weird in some way, so that they are memorable. So "Stop the Steal" is one of the most important memes of our time. It's very strangely ungrammatical, and the ungrammatical nature of it makes it weird and makes it memorable.
LG : Mm-hmm.
ED : Then, if a phrase, or a piece of media, or a saying, or an idea can be distilled down into either an image or a sound bite, and then within that distillation of words, you can convey a whole huge idea as well as conveying an in-group and an out-group. There are people who get the meme, and there are people who don't. There are people for whom it's funny and people for whom it's either total gibberish or a target. That's a central feature of a meme. And then another thing that will make it a meme is its ability to be remixed and used in different contexts by different people, so that it can travel through the internet, become different things, and yet always maintain its central core of an idea.
MC : So the thing you were just talking about, the … like the otherness, right? Like the meme has to be weird, and it has to be something that is not going to immediately make sense to people the first time they see it—we've all encountered that. We're browsing Twitter or on Facebook and we see a meme, and we're like, "OK. Everybody is reacting to this, and it's obviously funny, but I don't get the joke." Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So ED : Yeah.
MC : How do you get the meaning? What's the process that people have to go through in order to begin to understand what they're talking about when they see the meme? ED : OK. This is such a great question, and this process is what makes memes dangerous in terms of them becoming entrances to a rabbit hole that can turn you into an extremist without your realizing it.
MC : Oh, no.
ED : I know that sounds hyperbolic, but the truth is that's absolutely true. Now, let's take a meme coined or maybe perhaps popularized by Alex Jones, the phrase "false flag." Now, "false flag" is a meme. It is not immediately apparent what it means if you don't know the context. Those words don't mean on their face what the phrase "false flag" actually means. OK? If you encounter that, and people are interacting with it, and they're saying like, "This was a false flag event," and you've never heard that phrase, you don't know what they're talking about, there's this curiosity gap. There's this desire to know, to figure out what the hell you're missing, and some people will just move past it because it's alienating.
If you see a community of people discussing something that they clearly all understand and you don't understand, there's a couple of different ways you can respond. One is to just move on, and the other one is to be like, "I really want to figure it out." To figure it out, you Google it, or you go back in the thread on the forum you're on and read what was the thing they're talking about at the very top, or you go on YouTube and you watch a video about a person explaining it. All of that process of trying to figure out what on earth "false flag" is, in order to do that research yourself, to do your own research on the internet, you are now opening yourself up to falling into so many traps that are laid for you.
So specifically, the "false flag" one: If you're just trying to define it, you would find truther videos saying that the Sandy Hook massacre didn't happen. You would find so many stories alleging that all of these events in world history were part of a grand conspiracy, and you may be someone who is like, "Wow, this is crazy. I would really prefer to look up the dictionary definition of this phrase. Ha, ha, ha," or, "I would really like to find a WIRED explainer on why false flag is a meme." Maybe you'll do that, but the way the internet is formatted, the whole system of the algorithm of search results of everything means that that might not be what you find first. You might have to search pages and pages and pages of stuff to figure out what "false flag" means, to figure out what the meme means. In that time, you definitely have now been exposed to things that could be ideas that could be harmful to you.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : So based on an earlier conversation we had, this book is really going to cover memes spanning as far back as the '90s up to Occupy Wall Street as a movement that really wielded the power of memes, up to more recent events. I think of things like Gamergate or even Pizzagate. What would you say was the meme or one of the memes in our recent history that signaled some kind of turning point that you and your fellow researchers have identified as the moment of, "Oh, right. Some people actually take these seriously, and they could have real life consequences?" ED : Well, so the truth is that this research has taught me that we have to go way far back to identify the first memes that were powerful like this, way before the internet. Concepts like the New World Order. That's a meme. Concepts like blood libel and anti-Semitic tropes in the Middle Ages that were used against Jews. These are memes that traveled through culture. But to talk about our more recent history and internet memes, and the way in which these memes have been accelerated by new technology to take culture wars online, and make them go much, much faster, and lead to events like January 6th, I think one of the first memes that for me resonates is in Occupy Wall Street.
I remember when this happened. I was in San Francisco. Not working for WIRED, but I worked for CNET at the time. Occupy Wall Street was happening. It was 2011, and these students at UC Davis were protesting the conditions on their campus. You guys may remember that a breaking news story happened because a police officer who had been empowered by the university to break up this protest very casually pepper-sprayed these students in their face. Do you remember that? MC : Yeah. He had a canister with a tube coming out of it, and he just walked up and shot this jet stream.
ED : Exactly, it was just so casual, and his body language was very chill. The kids were screaming. People were yelling. There was a crowd around. Everyone was holding their phones. This was only three or four years into everyone having an iPhone, but everyone was streaming this, taking photos of it, taking video. One photo that was captured that day then went pretty much instantly viral. This was the peak of Facebook becoming the thing that everyone looked at. Twitter was just showing its utility. You couldn't livestream on Twitter yet, but you could share photos. So this photo of this cop doing this to these students went viral, and then it was taken and put into Photoshop, and people cut him out. Then they put him into historical famous paintings or historical photos, and the comment … It was a comment on the ridiculousness of his action. The casualness with which he wielded his state-given power was so clearly wrong, and so in some ways, it became a really galvanizing moment for police brutality.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Whether you were someone who was following Occupy Wall Street, whether you were an Occupy Wall Streeter yourself, or totally against Occupy Wall Street, this made sense to you. It was powerful, and it went everywhere. Then, what was so interesting, going back and looking at it, was that then the meme got news coverage in a way that now sounds normal to us. Memes often get news coverage, but this was one of the early examples of an internet meme getting coverage, and that coverage in some ways eclipsing the coverage of the event. I went back and listened to some radio reporting about the incident at UC Davis. It was two days later, and the reporters were actually just going over the funniest memes that had resulted from the incident, and they were just giggling so much, which also shows how memes can be completely decontextualized from the original thing that inspired them.
The first instances of the pepper-spraying cop meme, as it came to be known, were political statements about the casualness of police brutality. But the further from the event it got, and the more it got Photoshopped into, like, the painting of the signing of the Declaration of Independence, the less it signified the thing that it had originally signified. So it could become something that was just funny. In some ways, to me, it was a wake-up moment, listening back to that recording and realizing, "Wow. As journalists, we really should have been reporting on the violence that had inspired this meme, and not the fact that the meme itself was a funny use of Photoshop." LG : Right, and that's an example of where the distillation of the media itself actually becomes somewhat harmful. All right. We're going to take a quick break. When we come back, we're going to talk more about how online memes can have real-life consequences.
[ Break ] LG : So we've talked about how memes develop and proliferate on the internet, but let's get into where they go from there and how they spill over into the real world. Emily, in the first half of the show, you briefly mentioned the capital insurrection on January 6th. How did memes lead us there? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So ED : So many different memes played a role in bringing people to the Capitol that day, and it's hard to pinpoint any single one that was responsible for bringing, let's say, baby boomers who believed that the second Civil War was coming, or QAnon adherents who were mesmerized by the "Where we go one, we go all" meme that then convinced them to show up that day, or the "Save the children" meme, which was a hashtag that they coopted from an actual movement and turned into a conspiracy theory. There are so many memes that led people to develop the worldviews that brought them to the Capitol that day, but I think the most important one to talk about is "Stop the Steal." It's a good example because "Stop the Steal" was a meme whose origin we know exactly. Some of them, we don't. Sometimes it takes a long time to figure it out because they're born in a place like 4chan, for instance.
So, like, the Boogaloo meme is one that you can trace all the way back to gun boards on 4chan, but you have to go … You have to do digging to figure that out. “Stop the Steal,” you don't really have to dig at all. It was a phrase coined and created by Roger Stone. Powerful behind-the-scenes henchman, Roger Stone. He created it in 2016 when he assumed, like all of the media, that Donald Trump was not going to win the election or was not … To be clear, he thought Donald Trump was not going to win the nomination for the Republican candidacy for president in 2016. So he created the phrase "Stop the Steal" and registered a website with that name, because he was already planning to claim that if Trump didn't get the nomination, it was because the nomination was stolen from him by the Republican establishment, and the political establishment, and the "Swamp," which is also a meme, and the “Deep State,” which is also a meme.
However, he didn't need to deploy the meme at that time, because Trump did get the nomination, and then he did win. So “Stop the Steal,” the website and the idea, just sat around, waiting to be deployed by an operative, and he first deployed it in 2018 in the midterm elections when, I think, the Republicans didn't get as many seats as they wanted or whatever. He was like, "Oh, now is when ‘Stop the Steal’ can come in. They stole those from us. Ha, ha, ha." I'm sorry. I'm so sorry for that impersonation of Roger Stone.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : You're good.
MC : No, no, no. That was gold.
ED : “Stop the Steal” is an interesting one because it is literally a top-down meme. It was created by a person in power. He had a clear agenda for what to do with it, and it followed some very smart rubrics for being memorable. As I said, it's slightly ungrammatical. It's a three-word phrase, which the best viral slogans are: Black Lives Matter. Stop the Steall. Critical Race Theory. He sadly created a slogan that was evocative of some kind of wrongdoing, but not specific enough that it could be easily disproven, and also vague enough and wide enough that it could be applied in different contexts.
LG : Mm-hmm.
ED : So the “Stop the Steal” meme that led to the Capitol insurrection, it was deployed by people at the top, but then it resonated with a wide audience of people who adopted it from users on Twitter, from MAGA supporters. I mean, MAGA is another meme to people who were looking to professionalize and make money off of a movement that could be built around a meme. So all of these people then created companies and traveling tours to do rallies around “Stop the Steal.” All of that infrastructure and work and planning was hidden by the virality of the phrase, and the virality of the phrase was a rabbit hole into an entire universe of election fraud allegations. All of which didn't need to be true. Only some of them. Even if none of them were true, the penumbra of authority provided by “Stop the Steal” lawsuits and officials in the government using the phrase, including the president of the United States, gave enough sincerity to the idea that this meme conveyed that it was impossible to ignore for people who wanted to believe that it was true.
LG : So earlier in the show, Mike gave his description of a meme. I said, "Ah, it sounds kind of nebulous." But actually, what you're saying is it's that opacity that can exist around some of these phrases, and the fact that they do catch on but can be used or misused in different ways, that's part of what makes it a meme.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So ED : Totally. If it was too specific, it couldn't be a meme. It wouldn't be able to be remixed. It wouldn't be able to be reapplied, and there are some memes that are pretty specific. Therefore, then they're like a niche meme, like the memes that only resonate in the handyman Facebook group because they're all about fixing sinks or whatever. There's like journalist memes. They don't have a wide adoption outside of their in-group because they're too specific, but a meme that is nebulous enough, and that people can project their own ideas onto, and that can be taken out of a context and put into a different context, is very, very powerful.
MC : So if you're on Facebook or Twitter or Reddit, and you encounter something that has this nebulous, obtuse meaning, but also opens up a door to this world of bad information, and you're tasked with eradicating this information off your platform, what do you do? What does Twitter do with something like “Stop the Steal” before it becomes obvious what it is? ED : Well, they had enough warning that they should have banned it immediately. They see these things going viral. They see who's spreading them, especially with something like “Stop the Steal.” It was being deployed as a hashtag on social media by known, prolific, very influential disinformers, and that's a clue to the platform to take it seriously in the first place.
Before the insurrection, Twitter and Facebook were very, very resistant to taking any kind of mitigating action against a sitting president, because he was, after all, the president of the United States, and they were a private company, and they felt that if he wanted to use their platform to reach his audience, it wasn't really the place of a private company to be silencing the president of the United States. They changed their mind after they saw what happened with “Stop the Steal,” and they kicked Trump off Twitter. They kicked him off Facebook, and the impact was immediate. I mean, the impact on the news and information ecosystem online was incredibly immediate, which goes to show that that kind of deplatforming is very important, and it is within their right and their power to do it.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So But to your broader question, not every meme is like “Stop the Steal.” Not every meme is so obviously a problem, and I would say what they most need to do is understand that this is what memes can do. There's some naivete—and I admit, as I said earlier in the show, I had some of that naivete. As a senior editor at WIRED, I have to admit, I was always like, "Why would we write an entire article about this meme that only these nuts over here care about?" Or like, "Why is it worth our time to write a news article about a funny meme? I know that it's enjoyable, but it's not news." I have to admit, I didn't totally get it.
LG : So you're saying that you would not have assigned the Bernie Sanders mittens story? ED : I would have. No, no, no. So here's the thing. Maybe I would have. I absolutely would have, but I think I also would have … and I haven't read your Bernie Sanders memes.
LG : Oh, no. I think Angela Watercutter wrote it for us, but I mean, everybody wrote the Bernie Sanders mittens story, right? I think that's one of the memes that people on both sides of the political aisle could rally behind, this idea of a grandpa being transported straight from Vermont into the inauguration, you know? ED : Totally, and I don't think that those articles were harmful. I also think that they can be moments to explain. That's a good meme to use as a way into explaining the power of memes, because it went everywhere. It was viral in every political context. It was viral in every state. So if you want to talk about, "Hey, what is the risk of exposure to bad ideas through memes?" or, "What is the power of memes to bring people into a group together where they then create their own internal lingo and have their own badges and signifiers of what they believe in?" that was a great example of how to explain that to people. But what can Facebook and Twitter do? First of all, admit that this is a function of memes and that memes can only have this power when they are diffused to the widest possible audience, and the widest possible audience for these memes is on their platforms. What I really want from them is to not say, “They're just memes,” because that's not true. They are much, much more than that.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : So while we're waiting for technology platforms to catch up to spotting harmful memes, is the idea that we as consumers need to get better about spotting them ourselves? ED : Well, I mean, I think media literacy and meme literacy is important and vital. But honestly, it's such a cop-out for these companies, and for policymakers, and even for journalists to put the onus of this kind of responsible consuming of information on individual people, because these are systems that are so intricate and so vast, and journalists right now, us, all of us in this room, are being tasked with being the unpaid moderators of these platforms. I mean, I'm sure that both of you have had the experience that I've had even when I was at WIRED of finding something that was going viral, calling Facebook to ask them about it, and them being like, "Oh my God, thank you for pointing this out. We're going to take it down." This happens all the time.
MC : Yeah.
ED : Read any reporting about fake antifa Facebook groups that were organizing violence against people in the Pacific Northwest or any of these things, and in the articles about them, you'll see the statement. After being asked for a comment about these, the platforms took the pages down. What that shows is, yeah, some people are watching. They're journalists. They're researchers. They are independent researchers on Twitter who are able to notice this, and that is proof that the platforms could be noticing it themselves. This is why I also say, "Oftentimes, a meme can be an entrance to a rabbit hole, and on its face, it doesn't seem harmful." You can see. If you look in … Let's talk about the “Politically Incorrect” board on 4chan, because it's a classic place for people to go and workshop these ideas.
You can go on those boards, and you'll see people workshopping, "What is the version of this meme that we should drop on Facebook so that it won't get mitigated, and so that boomers will see it, and it'll lead them to this other thing?" They're having this conversation outright, and Facebook should know that, and should have people watching those forums, because then they have no excuse when they say, "Well, the one that was on Facebook was just this harmless one that didn't show anything." Then, if I am able to email them and say, "I literally just found the entire thread where these people workshopped putting one on your platform that looked like it wasn't a big deal when really it was"—if I could find it, then they can find it.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : All right. So what I'm hearing from you is that too much of the onus is put on news consumers to spot all of these various memes that are flying at us, and that the platforms need to do a better job of moderating content. I think we've heard that one before. All right. That was great, Emily. Thank you. Let's take a quick break. When we come back, we're going to ask you for your recommendation.
[ Break ] LG : Emily, what is your recommendation? ED : OK. I decided on two random recommendations. One is that I urge you to look up what happens to an artichoke if you let it become a flower.
MC : Nice.
LG : OK. Should we look it up, or should we just let that happen? ED : Both. If you have access to an artichoke plant, definitely don't pick that artichoke. Just let it become a flower, and it's going to blow your mind.
LG : OK. Did this happen to you recently? ED : Yes. Well, I bought a flower in a farmer's market and was like, "What is this absurd thing that I've never seen in my life? It looks like an alien, and I don't understand what it is." They were like, "This is an artichoke," and it shocked me.
LG : Wow. OK. Did it start snapping its jaws and say, "Feed me, Audrey"? ED : It does go through a period where it then smells very bad, but it looks like a sea anemone. It's crazy.
MC : So what's the other one? You said you had two.
ED : Yeah. OK. The other one is a book I'm looking at that is by an author named Colin Woodard, and it's called American Nations.
If you're someone who's interested in cultural differences and regional differences in the US and how areas get their personality, it's such a cool book.
MC : Very cool.
LG : I'm so curious. Unpack that for us a little bit more.
ED : OK. So it's about the way in which different regions in the US were actually populated and peopled by different cultures. So like, pilgrims moved to the northeast, and Danish people and people from the Netherlands moved to New York City, and there's how you can get … He traces the history of the different peoples who came to all of the different regions of the US, and the way they got there, and where their origins were, into how those places then got their personalities, and it explains … It really just resonates so well. It explains so much why, like, Louisiana has a lot more in common with French Canada than other parts of the South right next to it, or why the West Coast of the US has a lot more in common with the northeastern coast of the US than it does with the Mountain West.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So So it breaks these regions in the US down, and then goes through their entire history of the characteristics and struggles of their people. I think that there are some people who have said that it's a simplistic explanation of some of these stereotypes of people, but it's a very good jumping-off point to understand how hundreds of years and thousands of years of history can come and create different cultures within a single nation.
LG : American Nations.
All right. Those are great recommendations. Thank you.
MC : Yeah, and now I know why crab cakes and lobster rolls are so popular in San Francisco.
ED : There you go.
LG : Mike, what's your recommendation? MC : So this one is a little bit on-topic because I'm going to send you to Reddit, the birthplace and proving ground of many memes out there in the world. So there's this fun little Easter egg inside Reddit, and it's called r/random. If you go to reddit.com/r/random, it redirects you automatically to a random subreddit. So it's not actually a subreddit. It's a redirection engine. You go from r/random to anywhere on Reddit, and it really just shows all kinds of stuff. So Lauren just typed it in, and she landed on the AirPods Pro subreddit. I just clicked on it because I have it set as a bookmark on my browser, and I landed on the r/Poland Reddit, subreddit.
So this is what I would recommend that you do. I recommend that you make it a bookmark on your browser bar, because when you're just bored and you need five minutes of distraction, and you just want something to look at that's not the infinite spiral of doom known as social media, you can just go to r/random, and it will drop you into a section of Reddit that maybe hasn't seen any action in six months, or maybe has millions of subscribers and it's really interesting, maybe is a section of culture that you've never experienced before and never would have experienced like Blade and Soul, which looks like a game. Lauren, what is that you just … LG : Yeah, I just entered it again. It's a Korean fantasy martial arts massively multiplayer online role playing game, otherwise known as MMORPG, developed by NCSoft's team Bloodlust. If I sound like I know what I'm talking about, it's because I just read that out loud from the website.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So MC : You read that on the description. See? There you go. Something that you never knew about that you now found because of this randomness machine. So that's my recommendation. Check it out. Make a bookmark for r/random.
LG : That's pretty good.
MC : Thanks.
ED : I love that. It reminds me of the Wikipedia option to go to any random Wikipedia page.
MC : Absolutely. So, Lauren, your turn. You're the host. What's your recommendation? LG : I admit,when I came up with this recommendation and I jotted it down in our weekly podcast script, Mike, I wondered if I was perhaps stealing it from you, because I recommend White Lotus on HBO Max.
MC : Yes.
LG : Yeah. Mike and I are both fans of the show. Emily, have you had the chance to check this one out yet? ED : No. I saw people talking about it on Twitter and was like, "OK. Good. Apparently there's a new show I can watch," but I know nothing about it.
LG : Yeah. When you take some time off after you're all done with this, the book project, you should definitely check out this show. As I say often, if anyone needs an HBO login, let me know. I give it out freely. I think that's why HBO didn't send me the press kit this year that they normally send people, because I saw people tweeting about that, and I was like, "Where is my kit?" But anyway, yeah, it's a fantastic show about a group of extremely privileged people who descend upon a Hawaiian luxury resort. These people don't all know each other necessarily, but they traveled in the same boat together, and then they are at the same resort together. So they keep running into each other at the pool, and on the beach, and whatnot. They're interacting with the staff at the resort, who are more diverse and presumably don't have … Their incomes are not as high as the people who are vacationing at the resort.
It's satire. It's really dark. I think The New Yorker called it a tragicomedy, and I think that's a good way to look at it. A really dark look at the interactions between these groups of people, and it's just quite good. At the time of this taping, I've watched three episodes. I think by the time this podcast comes out, there will be another episode. Check it out.
White Lotus , HBO Max. Mike, do you have anything to add to that? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So MC : It's a Mike White show. So if you're familiar with Mike White, he did Enlightened on HBO. He also wrote School of Rock and Nacho Libre.
He was a writer on Freaks and Geeks.
This is another hit in his long output of hits.
LG : I would say less like School of Rock and more like Freaks and Geeks for rich grownups.
MC : Yes, absolutely.
ED : Oh, wow. That sounds amazing. When you were describing it at first, I was hoping it was going to be like a Jordan Peele–style thing, and it would evolve into a massive revenge violence where all of these rich, privileged people get their comeuppance, but it doesn't sound quite like it's going to be like that.
LG : Not quite yet, but we don't know where it's going. I mean, I guess some of the press who write about this kind of thing regularly have seen all the screeners for it and know where it's going, but … MC : Yeah. It's a miniseries. I think it's only six episodes.
LG : Yeah.
ED : Oh, cool.
MC : Well, speaking of press, Lauren, I did get the press kit for this.
LG : You did? MC : Yes. It's an Aloha shirt, a box of ashes, and a bag of ketamine.
LG : Yes. That's amazing. Also, a kit to how to make your way through a midlife crisis.
MC : Yes.
LG : Yeah.
MC : Yes. Exactly.
LG : All right. All right. That's our show for this week. Thank you, Emily Dreyfuss, former WIRED one, for joining us on this week's Gadget Lab podcast. We look forward to reading your book next year when it comes out, Drafted Into the Meme Wars.
We'll keep an eye out for that, and we miss you.
ED : Thank you so much for having me on, you guys. I miss you.
MC : Yay. I mean, not yay that you miss us, but yay, good to see you.
ED : Yes.
LG : Thanks to all of you for listening. As always, if you have feedback, you can find all of us on Twitter. Just check the show notes. The show is produced by the excellent Boone Ashworth. Goodbye for now. We'll be back next week.
[Gadget Lab outro theme music plays ] 📩 The latest on tech, science, and more: Get our newsletters ! Prisoners, doctors, and the battle over trans medical care The Olympics could be a Covid "super-evolutionary event" How to stay under your 15GB of free storage from Google Space Jam: A New Legacy and the fury of an AI scorned These bendy plastic chips fit in unusual places 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🎧 Things not sounding right? Check out our favorite wireless headphones , soundbars , and Bluetooth speakers Topics Gadget Lab Podcast podcasts memes conspiracy theories Michael Calore Lauren Goode Michael Calore Lauren Goode Julian Chokkattu Lauren Goode Simon Hill Reece Rogers WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,050 | 2,021 |
"Inside Amazon’s Empire With Author Brad Stone | WIRED"
|
"https://www.wired.com/story/gadget-lab-podcast-504"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter WIRED Staff Gear Muchos Bezos: Inside Amazon’s Empire With Author Brad Stone Amazon's Jeff Bezos stepped down as CEO earlier this year. The implications of this move—among many other topics—are discussed in Brad Stone's new book, Amazon Unbound.
Photograph: Emma McIntyre/Getty Images Save this story Save Save this story Save Few tech companies have charted a more fascinating course than Amazon. It's expanded from its humble beginnings as a bookseller to an absolute juggernaut that spans scores of product categories and service offerings. The company has set out to change the way the internet is structured, the way we interact with computers, and the way we shop—online and off.
On this episode of Gadget Lab, journalist and author Brad Stone joins us to dish about stories from his new book Amazon Unbound: Jeff Bezos and the Invention of a Global Empire , including Amazon's more aggressive business maneuvers and Bezos' personal shenanigans.
Find Brad’s book Amazon Unbound here.
Read an excerpt from the book about the secret origins of Amazon’s Alexa here.
Read about how Bezos battled the tabloids here.
Brad recommends the book Press Reset by Jason Schreier. Lauren recommends Anne Helen Peterson’s CultureStudy newsletter on Substack. Mike also recommends a Substack: Tom Moon’s music newsletter, EchoLocator.
Brad Stone can be found on Twitter @ BradStone.
Lauren Goode is @ LaurenGoode.
Michael Calore is @ snackfight.
Bling the main hotline at @ GadgetLab.
The show is produced by Boone Ashworth (@ booneashworth ). Our theme music is by Solar Keys.
If you have feedback about the show, or just want to enter to win a $50 gift card, take our brief listener survey here.
You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link.
You can also download an app like Overcast or Pocket Casts, and search for Gadget Lab. If you use Android, you can find us in the Google Podcasts app just by tapping here.
We’re on Spotify too. And in case you really need it, here's the RSS feed.
Michael Calore : Lauren.
Lauren Goode : Mike.
MC : Lauren, when you order stuff on Amazon, how much are you thinking about Amazon as a corporation and not just an e-commerce site? Does that factor into your buying? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : That's a good question, and I would say yeah, like increasingly so. I think I pause a little bit now when I'm about to impulse buy something, and I think, "I wonder what the toll of this is to the people working there or to the environments, and do I really need this thing?" Do you think about it? MC : No. To be totally honest, I am a trained monkey. I just click the button, and then I start waiting for the thing to arrive at my door but- LG : That's what Amazon wants.
MC : That's mostly what we're going to be talking about today on today's show. We're going to talk about Amazon.
LG : What better way to get to the heart of Amazon than to bring on Brad Stone.
MC : Indeed.
[Gadget Lab intro theme music plays] MC : Hi, everyone. Welcome to Gadget Lab. I am Michael Calore, a senior editor here at WIRED.
LG : I'm Lauren Goode. I'm a senior writer at WIRED.
MC : We are also joined by journalist and author, Brad Stone. Welcome, Brad.
Brad Stone : Hi, guys.
MC : Great to have you here. Brad is a long time Bloomberg reporter, and he's the author of not one but two books about Amazon. Brad's first book about Amazon is called The Everything Store , and it came out in 2013. The new book came out this very week, and it's called Amazon Unbound: Jeff Bezos and the Invention of A Global Empire.
You can actually read an excerpt from the book that we published this week on WIRED. In the second half of the show, we're going to talk about Amazon's founder, CEO, and soon to not be CEO Jeff Bezos, but for this first half, there will, of course, be some Bezos talk, but we're mostly going to concentrate on Amazon as a company.
Now, Brad, I assume you felt the need to write a whole second book about Amazon just because so much has happened since the publication of your first book in 2013. The company has gone off in all these interesting directions in recent years. Groceries, movies, TV shows, Alexa. You had some catching up to do.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : Yeah, that or I'm a glutton for punishment because I got to say reporting, trying to dig up the secrets of this intensely secretive, dominating company is exhausting, but like a lot of journalists, I'm drawn to a good story. I'm a business journalist. I'm drawn to a good business story, and in 2017 when I started on this project, yeah, the Kindle company had become the Alexa company. The $100 billion company had become, at that point, the 800 or $900 billion company, and Bezos had transformed almost within front of our eyes from this geeky tech guy to a, I don't know, Vin Diesel or The Rock or I don't know. The the nerd version of that.
So, I started on it, and while I was researching the book, we had HQ2, we had Bezos's has National Enquirer scandal, we had the antitrust investigation in the big tech at Amazon, and then the pandemic. It really was, in some ways, fortuitous timing for me because here was a company becoming so big and dominating that a lot of people were starting, as Lauren said earlier, to ask questions about the impact. Then, of course, Bezos resigns as CEO right as I'm about to finish the manuscript, and it's really the end of an era. So, this is a book about the last 10 years and Amazon's growth from a tech juggernaut into a global empire.
LG : You were thinking, I'm never going to be finished reading this book as all of these things kept happening.
BS : Well, I was thinking, boy, this is juicier than I thought.
LG : Did you end up dumpster diving for this book? BS : No. Lauren, those days are well in the past for me, but the tabloid story was super interesting and kind of hall of mirrors full of questionable people with questionable motives and a lot of, at least, legal research to figure out what the heck happened.
LG : So, we're going to get to some of that personal drama in the second half of the program today, but let's talk about Amazon products because as we've noted now, it's not just the online bookstore or even just an e-commerce platform anymore. It's a multilayered complex company. There's Amazon Web Services, of course. From a product perspective, we've seen the emergence of things like Alexa, the voice assistant that most people know at this point. I'm sure it's going to trigger a bunch of Alexas for whoever's listening right now. Amazon's private label business, Amazon Basics, which also they've been scrutinized for because sometimes, it seems Amazon is making products that they've already measured to be successful that are made by third parties. Then, we've seen Amazon enter a bunch of new markets through strategic acquisitions. What would you say, aside from just the standard e-commerce business, is the most interesting business you've seen emerge from Amazon in recent years? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : Well, I mean, I think you listed a couple of them, but I'll select one that you didn't just describe, which is the Go store, which is still a big question mark. This is, people might know, the cashier-less. They look 7-Elevens now. Amazon's beginning to bring the technology into big supermarkets. This is the idea that when you take something off a shelf, computers will be watching you. Computer vision algorithms will tabulate what you've taken and automatically charge you.
The reason that's so interesting is that physical retail is 90 percent of all retail. People prefer to go into supermarkets to pick up a piece of fruit and to figure out what they want to eat that week. Amazon, if it can succeed in its very Amazon-like way of trying to use technology to wedge into a new industry, this, the $1.6 trillion company can be who knows how big. Now, it's interesting because I get into that in one of the chapters, and Amazon and Bezos kind of led this effort as he does a lot of these new things at Amazon. They determined that the pain point that they could solve for was waiting in line at the checkout. Now, I don't know about you, but I really don't mind that. You check your email, but the type A disruptors at Amazon figured they're going to put a couple million dollars worth of tech into the market to try to figure it out. It'll be interesting to see if that's successful.
LG : Yeah. It's interesting. I think one of the first go experiences I had was in Seattle when I was there for another Amazon event. Brad, I'm sure you were there too, and I remember thinking, "Oh, there's the Go store. Let me go check it out." So, in the early days, you might recall people trying to take things off the shelf and then put them on a different shelf to see if you could sort of trip up the system, or what would happen if you took something and just tucked it in your bag and then walked out with it? Would the computer vision technology work? Consistently, it seems like no matter how hard you try to trip up this cashier-less little grocery mart, the tech was picking up what you were buying. It was incredible.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So So, on the one hand, it's like, "Oh, wow. This is really cool futuristic stuff." Then, on the other hand, sometimes, they're just isn't really the greatest practical application for that. To some extent, that's voice control still too, right? It's actually remarkable what it can do, but at the same time, it's like I use voice control to set my alarm.
BS : Right.
LG : That's how far into the future we are.
BS : Well, a couple of little things that you just said got me thinking. One, they do employ an army, an invisible army of contractors to sometimes review when the system inside the Go store makes mistakes. There is a wizard behind the curtain, but the second thing is that, and this is going to sound like a trivial observation, but the sandwiches in the Go store are horrible. They're like nothing that you can't get from a 7-Eleven or a gas station, but why I think that's interesting is because the whole Go store experiment has been a very expensive technology trial. Amazon is setting this up for bigger and better applications. I do think now, moving those into Whole Foods size grocery stores, they're calling them Amazon Fresh, or licensing the technology to airport kiosks or other stores, this could be, if it works, a big opportunity for Amazon.
People described it to me as I was researching the book as the most expensive project in Amazon's history right up there probably with the black eye they got in China over many years and probably bigger than Alexa just in terms of pure R and D cost. It just embodies Bezos's willingness to try to do hard things. He has a vision. He pursues it and the patience to do it over many years. That project started in 2012. Now, it's almost 10 years later, and they really probably don't have much to show for it now that pandemic has slowed down a little bit, but it is really this unique appetite to do things over the long term and to lose money for a long time.
LG : Right.
MC : Speaking of experiments and losing money, the Seattle trip that Lauren just referred to, which I'm sure you made as well was for a launch event, right? Now, Amazon has these big media events where they launch a bunch of products like a gazillion gadgets all at once. I think on that particular trip, Lauren counted around 40 products launched in one day. We've seen Amazon do this year after year. What's the strategy here with basically carpet-bombing our homes with Amazon gadgets? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : Lauren, was that the microwave event? LG : Yeah. I'm trying to remember because there was one year where they actually tallied up more than that like probably closer to 60 or 70 products, but in that tally, they were counting every single little iterative software update too. I think there have just been events where, from a pure hardware perspective, there have been dozens of gadgets launched. That might've been the microwave year.
BS : Yeah. I mean, Michael, to answer your question, it's this idea, this vision or ambition that Alexa will be pervasive, that it'll be a platform layer inside all of the products in our home, kind of invisible artificial intelligence that we can summon the Star Trek computer anytime we want. I think we need to say that it really hasn't been successful. The microwave flopped, the Alexa glasses. I've never seen anybody wearing them. The wristwatch feels a poor imitator of a Fitbit or certainly an Apple Watch. The app ecosystem that Apple developed with the iPhone in iOS, Amazon has these skills on Alexa, and they're very hard to summon and certainly, there haven't been many businesses built on the Alexa platform. So, it represents an ambition and yet, I think even though by any measure, Alexa has been successful probably financially because they sell a lot of devices and certainly culturally because it's ushered us all into an age of voice computing, it hasn't really realized the vision of this ubiquitous AI Star Trek computer that Bezos had when he first drew the sketch on the whiteboard in 2011.
LG : Yeah. That's the story that we ran on WIRED.com this week, the inside story of how Alexa was built. We encourage everyone to go to WIRED to check that out and then, of course, to buy Brad's book. One of the questions I had about that was you mentioned in this excerpt how Amazon was doing this because they wanted their own software to be in people's homes and in people's lives. I think about that a lot, I mean, in the sense that they really don't have a mobile operating system. They did make a phone at one point. It was called the Fire Phone. It was a failure. It didn't really work out. So, I wonder if that strategy of getting Alexa into everyone's homes was driven by this longterm vision of this is actually where the voice assistant is going to be most valuable or if it was driven by the fact that they didn't have control over devices. They didn't have control ultimately what the native voice assistant would be on iOS or Android, and so they had to strategically think elsewhere.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : I mean, this is back in 2011. The Fire Phone was also a kind of incipient project back then, so they didn't see themselves as blocked off from the potential mobile ecosystem. They were developing tablets at the time with the same Fire OS that is now limping along, but I think it was more extending the advantage they had in cloud computing. Bezos was asking everyone inside the company, "What are you doing for AWS?" He was sort of thinking about, "Well, could you create a consumer device with its brains in the cloud that extended the advantage Amazon had into the consumer world?" At the same time, his assistant, Greg Hart, at the time showing him Google Voice, and they're probably demoing some things at the time for the Fire Phone, which also needed a voice assistant. They knew Apple had acquired Siri, or at least, Siri was a popular app at the time. Bezos comes back to his executives with an email, "We should build a $20 computer whose brains are in the cloud that is completely controlled by your voice." So, it was this combination of exploit AWS, bring something else into people's lives, maybe instead of clicking on Amazon once a week or once a month, it can be part of people's lives, invent something new in consumer technology, but it was developed alongside the Fire Phone, so it was not seen as sort of a replacement or a strategic alternative. If anything, they invested more and had higher hopes for the Fire Phone. Because it failed, maybe they were able to take a little bit more risks and invest more and advertise on the Superbowl and do all this other stuff with Alexa that maybe they wouldn't otherwise have done.
MC : I'm particularly interested in Amazon's private label business, both Amazon Basics and those so-called in-store brands, brands that are sold exclusively on Amazon that Amazon actually owns though that fact is not made obvious. How did this part of the business grow? How much did you uncover about how much Amazon is using third party seller data to inform its own business moves? BS : Right. That's the big question. Well, this was not a unique page from the retail playbook, right? You go into Costco, and it's all Kirkland. Walmart and Target and Walgreens, they have their own private labels. So, as Amazon build its consumables business and its food business, they started to think about, well, should they get into this arena as well? The early initiatives are hilariously ham-handed. They've got diapers that leak and that get terrible reviews. They've got ... I don't even ... The names are crazy. Solimo and ... They come up with all these names. I actually described in the book, they have a private label that is called Bloom Street That Bezos reviews and rejects after they've done a ton of work on it because he doesn't want a Kirkland style brand. He wants unique individual brands that maybe aren't explicitly tied to Amazon to your point, Michael.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Then, here's the key to Amazon. It's decentralized, OK? So, managers are like little CEOs over their own fiefdoms, and they're given crazy goals. If they don't meet their goals, well, maybe they're not on an upward trajectory. The managers of these private label brands have to achieve every year. One of the ways they do that at the time, early days, 2015, '16, '17, is they go look to see what is selling well on the marketplace. If you have a nutritional supplement seller and there's a million SKUs of enzyme, well, how does Amazon know what the private label and those sellers? I got documents, and I talked to former executives. The cookie jar was open even though Amazon had a policy against doing that, and they looked at the data. Fast forward to today and Bezos has asked about that in front of the House antitrust subcommittee. They say they're going to evaluate it and examine it and investigate it. They assure everyone that it doesn't happen and can't happen, but look. It did.
The caveat is that the private label business at Amazon is still kind of small, still kind of sad. The 365 brand that they got from Whole Foods, of course, is a big asset but it's funny. They're still finding their way there. I think that it's because they are geeky technologists that when it comes to creating something, a brand that has meaning for consumers like 365 or Kirkland, it's foreign to them. They're still trying to figure it out. So, we can point to the advantages they have. If a law was passed and private labels became illegal for at least a company like Amazon to do, it probably wouldn't slow them down that much, so you got to put it in context.
MC : All right. We're going to take a break, and then when we come back, we'll have more with Brad Stone.
[Break] MC : Welcome back. Our guest this week is journalist and author, Brad Stone. Brad's new book is called Amazon Unbound: Jeff Bezos and the Invention of a Global Empire.
It's out now from Simon & Schuster. You can also read an exclusive excerpt from Brad's book on WIRED, which we published earlier this week. So, how has Jeff Bezos changed or evolved as an executive in the time between your two books, the early 2010s and today? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : So, I'll tell you a story from Amazon Unbound , which is a little Godfather II -ish in terms of it's mostly a continuation of the story, the last 10 years of Amazon, but there are some flashbacks. There's a story that I tell, I think it's in chapter six, of it's a flashback, the early years like 2007. It's an FBA meeting, Fulfillment by Amazon. A finance executive presents Bezos with a paper. These are six-page papers full of data in the appendix, and he's scanning it. He somehow points out or identifies a mathematical error in the appendix. He says to this female finance exec named Cynthia Williams, "If I can't trust this number, how can I trust anything in this paper?" He tears it up, and he throws it down the table, and he walks out.
I mean, can you imagine? She describes going home, basically thinking her career's done. She can't believe she made the mistake, opening a bottle of wine, emailing Bezos to apologize. He writes back. He's cooled down. He says, "I don't know anyone who has made the same kind of error." So, that's the old Bezos. The books are filled with these kinds of anecdotes. It's very Jobsy in his lack of empathy, right, and that weird gene that he doesn't have and his ability to cut an employee down at the knees.
You fast forward to today, and I don't know if he got a leadership counselor, or he realized that you can't get away with it anymore. He does still have the high standards. He does still send the ants scurrying in panic around him when he makes a proclamation or passes an edict or asks a question that somebody can't answer, but there is a little bit, at least in Amazon, of a softer touch. Maybe at Blue Origin, he's let the demons out a couple of times, but I think he understands now maybe because of some of these depictions that he needs to inspire more than intimidate.
LG : So, one of the big stories in the book that also ran on bloomberg.com as an excerpt is the story about Jeff Bezos's personal drama that has unfolded in recent years and how he essentially wielded his power to squash what could have been an even more damaging story or how he beat the tabloids as you put it in the story. So, walk us through what happened and also how his ownership of the Washington Post became something of a complexifier in this extremely personal saga.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : Right. Well, let's assume, since we can't spend the hour it would take to recount the whole sorted ordeal, that people will have some recollection of the basics, right? Bezos is a married man. At least, the world believes that in 2018. He starts carrying on with a married woman, Lauren Sanchez, who was married to the very powerful head of the Endeavor Talent Agency. Early 2019, he announces his divorce on Twitter. The next day, the National Enquirer publishes details of the affair. All of our jaws collectively hit the floor, and we just can't believe that the most disciplined person in the world has been caught in this dalliance and embarrassed by a tabloid.
LG : He's been sexting.
BS : He's been sexting. Right. There are talks of explicit photographs. I think this is a family podcast, so we'll be careful in how we describe the tawdry details, but then fast forward maybe about a month or a couple of weeks, and he posts this blog to Medium where he accuses the Enquirer of extorting him. Well, he says that they are trying to force Bezos and his camp to drop the insinuation, that the story was politically motivated because the Enquirer is owned by AMI, which was all involved in the catch and kill allegations against Donald Trump. They have a non-prosecution agreement with the Southern District of New York, and they're not supposed to get up to any mischief anymore. So, they're trying to get the Bezos camp to stop these insinuations. They described what they have in their possession, which they were given by Lauren Sanchez's brother, Michael Sanchez, and Bezos wraps himself up in the Washington Post and says, "These are my political enemies, and their motives are still to be better understood." What I conclude in the book and in the chapter on this in the book is that it really wasn't about the post. The Saudis might have hacked his phone. We really don't know for sure, but essentially, it was a much simpler story of the wealthiest person in the world making himself into an object of tabloid fascination, but he won that episode. The cover of Business Week where the excerpt ran said, "Bezos wins." It was because it was a masterful turn of events, and he exploited the weaknesses of the National Enquirer with its arrangement with the prosecutors in New York and turned the tables on them and published their emails. It's remarkable. It's remarkable that a billionaire was ... A major tabloid newspaper tried to embarrass him, and he got the editor fired and turned the tables. It was a jiu-jitsu move that even today can hardly be believed.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So MC : Sticking with the controversies for a bit, Amazon, just all of the other large powerful tech companies, has not been immune to criticism because of cultural and social issues, right? There's the company's impact on the environment with all of its shipping, its treatment of its warehouse workers, its union-busting efforts. From your reporting, did you get the sense that any of these things sort of sit heavily with Jeff Bezos, and do they affect the culture of the company at all? BS : No doubt. He is incredibly attuned to criticism of the company and of himself. I mean, some of it is tactical, like he doesn't want people to hesitate when they click the Buy Now button. I think that they, I mean, arguably have been late to making adjustments in their fulfillment centers. A couple years ago, they moved their hourly wage to $15 an hour. We're talking in a week where they announced they were hiring 75,000 more employees and who are going to have a $17 an hour wage, but in that last shareholder letter, he wrote, which might be the last investor letter he ever writes considering he's retiring as CEO, he talked about wanting to be the world's best employer and how he was going to start devoting more of his time to improving that employee relationship.
Now, look. It's 25 years into the company. It shows that maybe instead of leading as they like to believe that they are, they're reading, right? They're seeing all the criticisms, and they're realizing that it poses a kind of existential threat to the company if people believe they're a negative force in the world. So, they're, they're looking at it. They take it seriously. You compare his reputation to Elon's, and it's remarkable the halo that is over Elon's head and almost opposite when people consider Jeff and his public image, but I think that's why he's starting to take philanthropy seriously and try to improve that legacy as well.
LG : It's so interesting that you say that because I thought you were going to go in the opposite direction and say, "If you compared him to Elon, Jeff has a glowing image compared to Elon," but I guess it's how I- Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So BS : Do you disagree? I mean, I feel like Elon, despite some of the Twitter missteps, he goes on SNL, and it's a cultural moment. You can't even imagine Bezos doing that. I feel increasingly, he is seen as a little bit of a economic ... Well, predator is a strong word but certainly in some corners, for sure and Elon as this as the swashbuckling space guy.
LG : Right. Speaking of space, Bezos also runs Blue Origin, a suborbital space flight company. We should probably talk about that as well as the fact that he has stepped down as CEO of Amazon. So, I guess two-pronged question. What does the future of Amazon look with Andy Jassy at the helm, and why is Bezos so interested in space? It seems like he's going to be spending more of his time with Blue Origin.
BS : Right. Well, space was always a personal passion of his. He gave his valedictorian speech in high school about it. He started Blue Origin in 2000 before SpaceX. He just thought he could go slowly, and Elon came around to SpaceX and started getting all this government money to scale the company. Then, Bezos thought, "Why am I spending a billion dollars of my own money?" Now, they compete for space contracts, and SpaceX has been winning everything, and Blue Origin has been protesting everything. I think it's created some dysfunction at Blue Origin, and so he's going to have to, in his newly available free time, go back there and maybe devote the kind of attention to it that Elon devotes to SpaceX. So, there's a really entertaining rivalry that we'll be following for a couple of years there.
Then, Lauren, to answer the other question, Andy Jassy ran the cloud business at Amazon. He is one of those Jeff disciples who is a shadow, his technical assistant but who has now really evolved into a formidable leader in his own right. AWS is a $50 billion run rate a year business. It's like he's a logical choice to succeed Bezos. The difference is that he's not an innovator or at least an inventor in the way that Bezos is. He's not going to be drawing the next Alexa on a white board, right, or coming up with something out of the blue. At least, I don't think so. I mean, he's an MBA and an operator. So, Bezos says he'll stick around to keep working on new things, but if he ever does really step aside, who will replace that function at Amazon is a really good question for people who watch the company.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : To follow up on Mike's earlier question, Amazon with Jassy at the helm, does the culture change at all? What is his style as a leader? I do wonder if the company will become something of a friendlier place for people to work at, which we could only hope.
BS : Right. I think he has a little bit more of the empathy gene than Bezos does, so perhaps it does. I think he's a lot more attuned to the sort of diversity challenges that Amazon has, the workplace pressure that it's under to improve its relationship with employees. He presents a humbler target also for regulators and lawmakers. Bezos is the richest guy in the world, and he's just not going to get a lot of sympathy sitting in Congress now, so I think we probably will expect the Jassy to be there. They'll probably still ask for Bezos. So, will the culture change? That'll have to be a slow process because Bezos has finely tuned the mechanics and the clockwork right down to the review process, the leadership principles. We'll also see how much leeway Bezos gives Jassy to make those kinds of changes because he's still going to be the loudest voice in the conference room, right? He'll still be around. I suspect if there is changes, it'll be gradual.
MC : All right. Well, let's take another quick break, and when we come back, we'll move into our recommendations.
[Break] MC : All right. Welcome back. We're here with Brad Stone. Now, Brad, you may have heard that this is the part of the show where we recommend to our listeners a thing that you have been enjoying that you would urge them to check out. It can be a physical object. It can be a piece of media. It can be a book about Amazon. Please don't recommend your own book, but what would you like to recommend? BS : OK, well, I have a colleague at Bloomberg named Jason Schreier, who is an enormously talented journalist. He covers the video game beat for us. We had the sort of coincidental, maybe misfortune of releasing books on the same day. His is called Press Reset: Ruin and Recovery in the Video Game Industry.
I have been gobbling this thing up at night after I'm done self-promoting. It's like this look inside the video game industry, everything from the demise of small video game studios like Irrational Games or how Curt Schilling, the famous former baseball player turned conservative gadfly, tried to develop World of Warcraft and buy the company that made it. It's like the seedy underbelly of the video game industry. It's such an entertaining read.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So I've got a PS4. I need to upgrade, I guess. We also have a Nintendo that we play with the kids. Learning the stories of this and what goes on and how difficult and challenging the culture of the video game industry is, is like a wild revelation. It's a book that I recommend to anybody who's interested in video games or the tech industry or how corporate cultures develop and can go wrong.
MC : Nice. The title one more time.
BS : Press Reset: Ruin and Recovery in the Video Game Industry.
MC : Awesome.
LG : Did he consider naming it Blow on the Cartridge ? BS : I will have to ask him that.
LG : Yeah.
MC : Lauren, what's your recommendation? LG : My recommendation is a Substack from the writer, Anne Helen Petersen. Now, some of you might remember that we've had Anne Helen on this podcast before. She joined us last year to talk about her book, Can't Even , which is about millennial burnout. We brought her on to give us advice for how, well, not to feel so burnt out. She was a wonderful guest, and she's also just an excellent writer. So, I now pay $5 a month for access to her newsletter, Culture Study, which is all about culture particularly internet culture but also other really interesting, fascinating topics as well. Bonus, if you subscribe to Culture Study, you also get access to this new Discord server that a bunch of fellow writers have started. Writers include Casey Newton, Eric Newcomer, Nick Quah, Delia Cai, Charlie Warzel, and of course, Anne Helen. This is a very writer on writer podcasts that we're sharing with you today. Some of these names might not be familiar to you, but some of you might know who these folks are. Anyway, it's a cool thing that they're doing to, to try to just run their own business as independent writers. I recommend supporting it, so subscribe to Culture Study, and then you can access the Discord.
MC : What's their Discord platform called? LG : Sidechannel. Because we at WIRED already had Backchannel.
MC : That's right. You know they wanted to call it Backchannel.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So LG : I mean, who wouldn't want to call it Backchannel? Mike, what's your recommendation.
MC : Would you believe it? I am also going to recommend a Substack newsletter.
LG : Oh, my gosh. Substack taking over the world for now.
MC : For now anyway.
LG : Brad's going to write his next book on Substack.
MC : Subscribe to get the chapters. So, the newsletter that I want to recommend, it's a music nerd newsletter. It's called EchoLocator. It's written by a lifelong music journalist named Tom Moon. Tom has reviewed albums, and he's written about musical genres. He's also the author of a book that you've probably heard cited everywhere. It's called 1,000 Recordings to Hear Before You Die.
So, the echo locator newsletter is dedicated to finding this sort of obscure and forgotten parts of the music world that are hiding in plain sight in the streaming era.
So, in recent weeks, there has been a whole essay about the "unknown remixes" of Fresh by Sly and the Family Stone. There has been one about the Detroit instrumentals that came out of the Motown era. There was one about ... There's a really great rant about Spotify. He's anti-Spotify. The funny thing is every newsletter that comes out has a Spotify playlist attached, so if you're interested in going a little bit further into the world of music recommendations and you prefer to get your music recommended to you by a person in the know rather than an algorithm that is guessing what you might like, then this is a great way to take that path because Tom is a good writer. His newsletters are very short, and there is a link to get right into what he's talking about at the top of every of every one. So, that's my recommendation. EchoLocator, and it's free.
LG : Excellent.
MC : All right. That is our show for this week. Brad Stone, thank you for joining us.
BS : Thank you, Michael. Thank you, Lauren.
LG : Thanks, Brad.
MC : Come back any time when you write that third book. Brad's new book is called Amazon Unbound: Jeff Bezos and the Invention of a Global Empire.
Read it on your Kindle and thank you all for listening. If you have feedback, you can find all of us on Twitter. Just check the show notes. This show is produced by Boone Ashworth. We will be back next week. Goodbye.
[Gadget Lab outro theme music plays] 📩 The latest on tech, science, and more: Get our newsletters ! They told their therapists everything.
Hackers leaked it all The statistical secrets of Covid-19 vaccines To make chips more powerful, IBM is growing them taller Don't underestimate the challenge of building a PC NFTs and AI are unsettling the very concept of history 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 💻 Upgrade your work game with our Gear team’s favorite laptops , keyboards , typing alternatives , and noise-canceling headphones Topics Gadget Lab Podcast podcasts Jaina Grey Brenda Stolyar Adrienne So Simon Hill Simon Hill Adrienne So Julian Chokkattu Julian Chokkattu WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,051 | 2,019 |
"15 Moments That Defined Facebook's First 15 Years | WIRED"
|
"https://www.wired.com/story/facebook-15-defining-moments"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Issie Lapowsky Business 15 Moments That Defined Facebook's First 15 Years Play/Pause Button Pause Elena Lacey Save this story Save Save this story Save On February 4, 2004, back when "Hey Ya!" was still topping the charts and global dominion was but a glimmer in a young Mark Zuckerberg’s eye, the 19-year-old Harvard sophomore and his roommates unleashed their creation, TheFacebook.com, on humanity. Or at least, they unleashed it on the elite sliver of humanity that occupies Harvard's halls.
But over the past 15 years, that sliver has expanded far beyond anyone's expectations---including Zuckerberg's. In June 2004, when WIRED published its first story on TheFacebook, comparing it to Friendster and whatever the heck Orkut was, Zuckerberg said, "I expected that a few people would do it at Harvard and they'd tell their friends, but I didn't expect it would take hold as this all-inclusive directory." At that point, success meant having 250,000 users on the platform. In the decade and a half since, Facebook has added four zeroes to that figure, transforming from a website for poking your college crush to, arguably, the most powerful engine of communication in the world. Zuckerberg's creation has, for better and for worse, forever changed how people connect, how businesses make money, how politicians seize power, and how information flows across communities and cultures. It's where grannies share pictures of their grandkids and where state-sponsored trolls wage cyberwar against other countries. It's how volunteers raise money for hurricane victims and how hate-mongers rally their followers to kill people.
How did that happen? We took a look back at Facebook's 15 years for the 15 moments that made the company what it is today and that signaled, sooner than most realized, what it would become.
1. The Winklevii sue Facebook.
TheFacebook.com was just seven months old when ConnectU, a startup founded by Harvard students Cameron and Tyler Winklevoss and Divya Narendra, sued Facebook for breach of contract in 2004. In what would become a years-long legal battle, memorialized in the Oscar-winning film The Social Network , the ConnectU founders alleged that Zuckerberg stole their idea and breached an oral contract he made to develop a social network for Harvard students that was then called HarvardConnection.
Zuckerberg had already launched a short-lived Hot or Not clone called FaceMash the year before. That site got him in trouble with Harvard, because the app used students' photos without their permission, but it also caught the attention of the HarvardConnection founders, who turned to Zuckerberg for help building their site. What they didn't know then---and what would later be revealed through court filings and leaked instant messages---was that, while Zuckerberg appeared to be toiling away on HarvardConnection, he was simultaneously building TheFacebook.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Justine Hunt/The Boston Globe/Getty Images The HarvardConnection team sent Zuckerberg a cease and desist letter days after TheFacebook launched and filed a formal lawsuit that September.
The bitter suit ended in a settlement. But the battle with the Winklevii provided an early look at how Facebook would come to use a combination of skill, speed, and eventually, size to copy or crush competitors.
2. News Feed launches.
In the beginning, Facebook was more or less a directory of people's profiles. Spending time there meant bouncing from one friend's Wall to the next, checking out the latest posts. The launch of News Feed in September 2006 changed that forever, creating a centralized stream on users' homepages, where they could see all of their friends' updates.
When Facebook flipped the switch on News Feed, however, users were outraged.
Suddenly, every action they'd taken on Facebook was visible to all of their friends. (In my case, that meant exposing a late-night, not entirely sober decision to friend every member of the New York University men's cross-country team.) In a blog post for a proposed Facebook boycott, one user wrote , presciently, "It is almost impossible now to keep your information to yourself." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The News Feed debacle presented Facebook's first opportunity to defend itself against accusations that it had invaded users' privacy. It didn't go so well. "Calm down. Breathe. We hear you," Zuckerberg wrote in a less-than-compassionate Facebook post responding to the backlash. "Nothing you do is being broadcast; rather, it is being shared with people who care about what you do—your friends." Days later, Zuckerberg backtracked in an open letter, saying, "We really messed this one up," and announcing new controls users would have over what stories populated their News Feeds. "When we launched News Feed and Mini-Feed we were trying to provide you with a stream of information about your social world," he wrote.
"Instead, we did a bad job of explaining what the new features were and an even worse job of giving you control of them." It's the sort of apology that would become all too familiar in the years to come.
But News Feed did more than alert users to the privacy risks inherent in all this sharing. It also began the process of consolidating a world of information into one, ceaseless scroll, personalized to every individual user's interests and beliefs. The News Feed wrested control away from publishers, putting it in the hands of Facebook's almighty algorithms.
3. Facebook begins outreach to brands, launching Ads, Pages, and Beacon.
Zuckerberg debuted Facebook Ads and Pages for brands in November 2007, at an event attended by hundreds of marketers. “For the last hundred years media has been pushed out to people," he said, "but now marketers are going to be a part of the conversation." By inviting brands to have their own Pages on Facebook and to amplify their Pages with ads, Facebook was not only creating a hugely successful business model, it was pushing forward a new paradigm in advertising, one that Google had already begun. Instead of offering advertisers a general audience the way television and print advertising had always done, Facebook was giving them a way to find exactly the people they wanted to reach , using all the data Facebook had collected on its users over time.
That same day in 2007, Facebook announced another new product called Beacon , through which businesses shared information with Facebook about what their customers were buying. Facebook would then immediately broadcast that information to users' friends. Just a year after the News Feed fiasco, the outcry was similarly swift. Once again, Zuckerberg apologized and promised to let users turn off Beacon. "I'm not proud of the way we've handled this situation and I know we can do better," he wrote in a post.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Facebook would eventually settle a class-action lawsuit over Beacon, and it shut the product down entirely in 2009.
4. Facebook hires Sheryl Sandberg.
Facebook chief operating officer Sheryl Sandberg.
Andrew Harrer/Bloomberg/Getty Images When Zuckerberg met Sheryl Sandberg, then a Google executive, at a party in Silicon Valley in 2007, he was looking for help transforming his massively popular but unprofitable website into a legitimate business. Sandberg, a former high-ranking Treasury Department staffer, joined Facebook in 2008 as chief operating officer, turning the company's fledgling ad business into what it is today and overseeing its often-rocky relationship with Washington.
5. Facebook debuts the Facebook Platform.
Facebook has always insisted that it doesn't sell users' data. But it does share that data with third parties, a decision that dates back to the rollout of the Facebook Platform , which allowed developers to build games and other apps that integrated with Facebook, in 2007. A year later, it launched Facebook Connect , which allowed people to log on to other websites with their Facebook username and password. It wasn't just an easy way to sign in---it also let you see which of your Facebook friends were on these other websites. Over time, Platform and Connect evolved into what's now known as the Graph API. Launched in 2010, Graph API enabled developers to suck up vast amounts of data on Facebook users, including users' friends, a feature that would become controversial years later.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When WIRED covered the announcement of Graph API, Ryan Singel wrote , "There's a nagging suspicion that when Facebook says it's simply reacting to changing norms about how public we want our lives to be, that it's actually forging that condition, not reacting to it." 6. Facebook launches the Like button.
When Facebook introduced the Like button in 2009, the company created a new currency for the internet. Simply sharing aspects of our lives wasn't enough. The Like button fed human beings' constant craving for validation by turning every post into a popularity contest. Likes came to drive corporate decisionmaking. They became informal poll tests for politicians. They helped posts spread virally. They arguably gave birth to a new profession, because what are influencers if not people who are so well Liked, they get paid to push products for a living? Facebook wasn’t the first company to use something like this, but because of its scale, the blue thumbs-up became ubiquitous. It changed human beings on a deep, psychological level, giving us a sweet, sweet hit of dopamine each time we get another notification. That only encourages us to share some more. Ten years later, it's hard to remember a world without it. You mean we used to tell each other everything about our lives just because? 7. A Federal Trade Commission investigation into Facebook's privacy settings ends with a consent decree.
After the FTC concluded an investigation into what it said were deceptive privacy practices at Facebook, the company signed a consent decree in 2011. Among other things, Facebook promised not to misrepresent users' privacy and security settings and to receive consent before making changes to those settings. It remains one of the few regulatory actions within the US to target the company.
Eight years later, the FTC is investigating whether Facebook held up its side of the bargain. The scandal involving a political consulting firm called Cambridge Analytica last year showed that until mid-2015, Facebook was still giving developers access to users' friends' data without their explicit consent. Now, the FTC is reportedly considering levying a "record-setting fine" on Facebook for violating the agreement. It would be the first time Facebook has suffered any significant financial penalty over the privacy concerns that have followed the company since its earliest days. Even a record-setting fine may still be a small price to pay for a company worth more than $476 billion.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg 8. Facebook and its business model evolve for a world moving to mobile.
The growth of Facebook as a platform for other apps coincided with the rise of smartphones, which posed a challenge for the company. As Zuckerberg put it in a recent post , "Running a development platform is expensive and we need to support it. Back when the main way people used Facebook was on computers, we supported the platform by showing ads next to developers' apps on our website." But Facebook couldn't do that on mobile. So, around 2012, Zuckerberg contemplated whether it might be time to change the business model. The pressure to grow was particularly high, with the company's IPO in May 2012.
One proposal on the table, according to a previously sealed batch of internal emails released late last year: requiring developers to buy ads in order to access user data. In effect, this would mean Facebook would begin selling user data, something it has always sworn not to do.
In one October 2012 email, Zuckerberg summed up how such a process could work: "The basic idea is that any other revenue you generate for us earns you a credit towards whatever fees you own us for using plaform[sic]. For most developers this would probably cover cost completely." Facebook ultimately opted against that approach, and instead, doubled down on mobile advertising to carry it through the transition. Starting in 2012, the company placed sponsored ads in the News Feed itself. Also that year, Facebook launched Custom Audiences , which allowed advertisers to even more precisely target users. Last quarter, mobile advertising accounted for 93 percent of Facebook’s ad revenue. This decision point in Facebook's history represents a pivotal moment, both for the business and for the people who share their information with it.
9. Facebook buys Instagram.
Getty Images Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It was the smartest $1 billion Facebook---maybe anyone---ever spent. The photo-sharing app was less than two years old when Zuckerberg snapped it up in 2012. Acquiring Instagram not only brought a would-be competitor under Facebook's control, it also helped secure the company's foothold with a younger generation of users who were fleeing the big blue app.
Today Instagram has more than 1 billion users. In its most recent earnings call, Facebook announced that the app's Stories feature now has 500 million daily active users. The company has also been incorporating some of Instagram's most popular features, including stories and photo filters, into the main Facebook app. In 2018, Instagram cofounders Kevin Systrom and Mike Krieger left, reportedly over objections to their decreasing autonomy.
Instagram may still make up a small percentage of the company's overall ad revenue, but it accounts for an increasingly large percentage of new ad revenue , leading analysts to believe that Instagram will be critical to Facebook's long-term growth.
10. Facebook launches Internet.org.
Depending on who you ask, Zuckerberg's Internet.org program, which he launched in 2013 to make access to the internet---and Facebook---more affordable in the developing world, was either about altruism or world domination. The plan was to beam the internet to unconnected populations using drones and to partner with mobile phone carriers to give people free access to a small subset of apps. Zuckerberg described the endeavor optimistically: “There are huge barriers in developing countries to connecting and joining the knowledge economy," he wrote.
"Internet.org brings together a global partnership that will work to overcome these challenges, including making internet access available to those who cannot currently afford it." But in dozens of countries, advocacy organizations protested the project, saying it violated the tenets of network neutrality by making Facebook a gatekeeper of what people could and couldn't see on the internet. They worried about creating a "single centralized checkpoint for the free flow of information." Those concerns turned out to be well founded. In countries like the Philippines and Myanmar where Facebook's so-called Free Basics program launched, Facebook became synonymous with the internet. That came with some unintended consequences. In Myanmar , Facebook has accepted blame for enabling conspiracy theories to spread, fueling a brutally violent campaign against the Rohingya people there.
Facebook has wound down the Free Basics program in countries including Myanmar. But Facebook continues to have an impact on these places. In its most recent earnings call, Facebook said that the Philippines and Indonesia, two countries where Free Basics launched , are among its fastest growing markets.
11. Facebook announces changes to privacy settings.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In 2014, Facebook announced its Graph API would no longer allow developers to access users' friends data, and officially shut down this feature in April of 2015. The move spurred a backlash from app makers who said they relied on that data---one company called Six4Three is still fighting a legal battle with Facebook over this change today.
The change was a pivotal one for Facebook. For years, the company had been giving developers unknown quantities of data about people who never knew those apps were snooping on them. If your friend had consented to having their data collected, you became fair game, too. Groups like the American Civil Liberties Union tried to sound the alarm about this loophole, but it would take years for the public to really take notice. When they finally did, Facebook's best defense was that it realized its mistakes and strengthened its privacy protections.
And yet, years after Facebook made the change, questions remain about what companies received extended access to the data and why. In December, The New York Times reported that Facebook gave companies like Microsoft, Netflix, and Spotify such access as recently as 2017.
12. Facebook's Trending Topics tool sparks debate over partisan bias in 2016.
Facebook launched Trending Topics in 2014 as a way to show users the top news of the day, across the Facebook platform. The company hired human curators to edit the final list of stories suggested by Facebook's algorithms. In 2016, during the height of the US presidential campaign, Gizmodo published a story claiming that those curators "routinely suppressed conservative news." The story spread across right-wing media, and lawmakers took notice. Zuckerberg called a meeting of conservative thought leaders in Facebook's offices, but that hardly quelled the outrage. Eventually Facebook bowed to complaints from the right and removed human curators from Trending Topics that same year. As WIRED later reported , this moment “set the stage for the most tumultuous two years of Facebook’s existence.” Without human moderators, the algorithm began surfacing fake news for all to see.
Facebook has been pummeled by accusations that it's biased against conservatives, with Republicans in Congress asking the company to answer, under oath, for the declining reach of far-right websites like the Gateway Pundit. That's despite evidence that algorithmic changes at Facebook have led to declines in traffic to a variety of news publications, regardless of partisan affiliation. It's a reputation the company can't seem to shake, and as it works to crack down on problems like the spread of fake news, accusations of bias only continue to grow.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Last year, Facebook shut down Trending Topics altogether.
13. Facebook acknowledges foreign manipulation of elections.
In the fall of 2017, Facebook made a limited announcement: It had found 5,000 ads, worth $150,000, that had been purchased by a Russian troll group called the Internet Research Agency in the run-up to the 2016 election. In reality, the scope of the problem extended far beyond those 5,000 ads. Facebook eventually acknowledged that the IRA reached 150 million Americans across Facebook and Instagram with its divisive, sometimes racially charged, posts that pitted Americans against one another.
Of course, now we know that the IRA wasn't the only group spreading disinformation and propaganda on Facebook, and Facebook wasn't the only platform these global trolls targeted. Google, Twitter, Reddit, Tumblr, Pinterest, and just about every other open platform on the internet have been hit with some sort of foreign manipulation campaign. Those campaigns continue to this day. Just last week, both Facebook and Twitter announced they were taking down hundreds more accounts and pages that had been masquerading as people and groups they were not.
The initial revelation by Facebook in 2017 forced the company---and its Silicon Valley peers---to be on constant watch for similar campaigns in every country where they operate. They've also created some new transparency efforts that require advertisers to report who they are, how much they're spending, and who their ads are reaching. Facebook's head of cybersecurity, Nathaniel Gleicher, said last week that the company is getting better at spotting these campaigns and taking them down quickly. But no one has figured out how to prevent them altogether.
14. The Cambridge Analytica scandal breaks.
In March 2018, the world got a wake-up call about the global data trade and the role that Facebook has played as chief supplier. That's when reports first broke that Cambridge Analytica , a consultant to Donald Trump's presidential campaign, had harvested the data of tens of millions of American Facebook users without their knowledge, thanks to Facebook's lax policies about sharing data on users' friends with developers. This is the policy that Facebook changed in 2015. But for most Americans that detail didn't matter, because there was no clawing that data back from companies like Cambridge Analytica that already had it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Facebook's stock price (temporarily) tanked, and the company was forced to answer for its past actions (see below). Zuckerberg committed to rethinking all aspects of Facebook's business to protect user privacy. But questions remain about whether those changes are purely cosmetic. Last week, news surfaced that the company has been paying people as young as 13 to download an app called Research that allows Facebook to see everything Research users do on their phones, down to their encrypted messages. In a striking bit of similarity to Cambridge Analytica, the Research app could also see information from users' friends.
15. Zuckerberg testifies before Congress.
Facebook CEO Mark Zuckerberg has said that Facebook does not sell user data, but a lawsuit alleges that the company seriously considered it.
Xinhua News Agency/Ting Shen/Getty Images Fifteen years after Harvard slapped him on the wrist over FaceMash, Zuckerberg was called before a more powerful committee---the US Congress---to explain Facebook's last two years of scandals, and the decade and a half of decisions that led to them. It was Zuckerberg's Big Tobacco moment: a chance for him explain the trade-offs Facebook has made between growth and privacy, a chance to question him on how Facebook treats competitors, a chance to wonder whether Facebook actually has any real competition at all.
They're questions that we still don't have all the answers to. If Facebook's next 15 years are anything like the first, they're questions we'll be asking for years to come.
How WIRED covered Facebook these past 15 years Here's everything Facebook has ever done Facebook was late to mobile. Now, mobile is its future Teens don't use Facebook, but they can't escape it, either The Social Network was more right than anyone realized How Facebook has changed computing 15 years of Facebook in four charts 📩 Want more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Writer X Topics Facebook Mark Zuckerberg Social Media Kari McMahon David Gilbert David Gilbert Will Knight Andy Greenberg Joel Khalili Amit Katwala Andy Greenberg Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,052 | 2,022 |
"Elon Musk Embraces Twitter's Radical Fact-Checking Experiment | WIRED"
|
"https://www.wired.com/story/elon-musk-embraces-twitters-radical-crowdsourcing-experiment"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Carl Miller Business Elon Musk Embraces Twitter's Radical Fact-Checking Experiment Photograph: MirageC/Getty Images Save this story Save Save this story Save Tweets from Elon Musk often inspire disagreement, but some recent pushback has come from a surprising source— Twitter ’s own experimental defenses against misleading claims, cherry-picked facts, and outright falsehoods.
Several posts by the entrepreneur since he took over Twitter have triggered a warning label offering “added context” via a brief corrective note. Earlier this month, Musk’s claim that “Twitter drives a massive number of clicks to other websites” got a rejoinder stating “The reverse is true” and citing statistics showing the platform to be a small player in directing online attention.
The warnings came from a unique experiment in crowdsourced fact-checking called Birdwatch that began last year but was deployed on Twitter in October, weeks before Musk took over. What appeared to be a modest pilot quickly caught the new owner’s attention.
In the same week that he made deep cuts to Twitter’s workforce, Musk found time to rename the project Community Notes and extend his enthusiastic support, tweeting that it had “incredible potential for improving information accuracy on Twitter!” So far, members of the team seem to have survived the transition. If Musk sticks with the project, it has the potential to reach beyond fact-checking to change how social platforms can operate.
WIRED Staff via Twitter Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Attempts to protect the messy, contested truth online are never straightforward, but Community Notes has a deceptively simple design. Once a user joins the project, they can propose that a short note of context be added to any tweet, perhaps correcting an error or plugging an important omission.
Other users can then rate the helpfulness of the note and any others suggested by users. When a famous account like that of Elon Musk posts a grandstanding tweet, the best note is automatically selected to appear on the post as it circulates around Twitter, like a contextualizing alter ego or digital conscience.
That might sound more likely to create problems than solve them. Isn’t the crowd what has made social media so partisan? But Twitter made the crucial decision to surface notes not by simply selecting the most popular, but those that win the broadest consensus. That approach was inspired in part by a platform called Polis—used in Taiwan to crowdsource the creation of new laws—that is among the few examples of technologies shown to coax agreement out of online debate.
Polis is rolled out in Taiwan to seek citizen input on specific questions, such as “how would you regulate Uber?” People draft their own responses and also click to agree or disagree with those of others. The software behind Polis uses this feedback to build a machine’s eye view of the “opinion space” for a question, mapping out clusters of people who agree with each other. Polis then surfaces only the statements that got support from across the ideological gaps it had mapped out.
The upshot is that rather than encouraging grandstanding or insults, Polis gamified the finding of consensus. “People compete to bring up the most nuanced statements that can win most people across,” explained Audrey Tang, the digital minister of Taiwan, when I visited in 2019 to see how Polis is used to turn digital debate into law.
“We always find a shape where most people agree on most of the statements, most of the time.” The software exposed something likely far more common than we suppose: Even on topics of violent dispute, agreement can be lurking beneath the surface. And the right platform engineering can bring it to the fore.
Taiwan has used Polis dozens of times, including to set the rules for how Uber operates in its streets. That helps explain why Twitter this year called one of Polis’ inventors, an engineer based in Seattle named Colin Megill. Jay Baxter, one of the Twitter engineers who created Community Notes, traveled to meet him over a long lunch in Seattle, Megill told me. “They knew about our work, and it looked like they were keen to see what they could build on,” Megill says. Baxter wasn’t able to discuss the project with WIRED but has described Polis as a “major inspiration,” amongst other research that influenced Twitter’s project.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg WIRED Staff via Twitter Unlike Polis, Twitter’s project has to find consensus not for one question at a time but for any conceivable controversy on the platform. Community Notes does that by estimating the diversity of viewpoints among participants, based on how different users rate the helpfulness of notes from others. Twitter’s version of bridging the divide is to find notes considered useful by raters who don’t usually agree on much, suggesting they have different viewpoints. This technique at the heart of Polis and Community Notes is called bridging-based ranking.
Megill believes Twitter’s team has taken it to new technical heights. “Birdwatch has made a profound breakthrough in scaling this kind of system across a bigger population and number of issues,” he says.
Twitter’s vice president of product said early this month that usage of Community Watch has recently spiked, but the project is still in its early days. The data is open source, and as of November 8 it had seen only 38,494 notes from 5,433 people—a small group to oversee a platform with more than 200 million users. Nor can bridging-based ranking change human nature. One independent study found that people are more likely to write notes on tweets expressing viewpoints different from their own. David Rand, one of its authors, concluded in the Financial Times that “partisanship is a major driver of users’ engagement on Birdwatch.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Twitter’s own recently released research also reports a partisan divide, with many more Democrats than Republicans finding the notes helpful. But a majority of both groups thought the notes selected by the system were helpful rather than not helpful. And Community Notes were also seen to reduce how much users share Tweets shadowed by heavily caveating notes. The project can also claim some notable, if anecdotal, victories: This month both the White House and Elon Musk deleted widely circulated tweets after a Community Watch note called out missing context.
Perhaps Community Notes’ biggest weakness is also one shared by Polis. “Those digital democracy platforms don’t have any kind of real authority,” Taiwanese parliamentarian Karen Yu told me.
Polis still relies on politicians to turn the consensus it draws out from citizens into law. Because the users of a social platform have so little power over the service they use, Community Notes is even weaker. With a flick of his wrist, Elon Musk could make it—and all the community’s notes—vanish.
But I don’t think he will. An old joke about Twitter attributed to Mark Zuckerberg says the company’s management was so clueless that “they drove a clown car into a gold mine and fell in.” Elon Musk may have driven his own clown car into his own gold mine. He seems unlikely to have known that Birdwatch existed before buying the platform, but he has stumbled upon one of the most exciting content moderation innovations ever to come out of not just Twitter, but any major platform.
For Musk, who has loaded Twitter with debt, there is much to love in Community Notes. It is scalable, powered by algorithms, and doesn’t require employing legions of content moderators. Most of all, it transfers responsibility for defining the truth away from Twitter itself and onto its users.
If Musk sticks with the project and it keeps scaling up, there might be a breakthrough of another kind altogether. For almost all of the social media era, the content you see has been chosen by algorithms designed to maximize your time spent on the platform. The consequences have been vast and ruinous: a wildfire conflagration of conspiracy theories, disinformation, radicalization, and even genocide.
Polis showed that platforms can be engineered in a different way to elevate consensus instead of division. It showed it could be done for small crowds and specific questions. Now Twitter is poised to test that philosophy on a vastly larger stage.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg WIRED Staff via Twitter You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Topics Elon Musk twitter Social Media Crowdsourcing Matt Burgess Vittoria Elliott Will Knight David Gilbert Kari McMahon Morgan Meaker Khari Johnson Vittoria Elliott Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,053 | 2,023 |
"Unhinged Conspiracies, AI Doppelgangers, and the Fractured Reality of Naomi Klein | WIRED"
|
"https://www.wired.com/story/covid-conspiracies-ai-doppelgangers-naomi-klein"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons By Kate Knibbs Backchannel Unhinged Conspiracies, AI Doppelgangers, and the Fractured Reality of Naomi Klein Facebook X Email Save Story Photograph: Kamil Bialous Save this story Save Save this story Save I was grabbing a drink with an old friend when it happened. I told her I was excited about an upcoming reporting trip to Vancouver, to interview Naomi Klein. My friend wrinkled her nose, as if the bartender had just farted. Then she asked why I’d give my time to someone who thought the Covid-19 pandemic was a conspiracy.
I sighed. Turns out, she’d been thinking of Naomi Wolf.
You know Naomi Klein, right? Rabble-rousing leftist journalist and climate activist? Author of Gen X touchstone No Logo and the mega-influential The Shock Doctrine: The Rise of Disaster Capitalism ? Decidedly not the former liberal feminist writer turned far-out Covid truther Naomi Wolf? But just because they share a first name—and, I suppose, are both telegenic Jewish public intellectuals who found fame through polemical writing—people confuse the two Naomis constantly. Klein gets mixed up with Wolf so much, in fact, a Twitter mnemonic was born: “If the Naomi be Klein you’re doing just fine / If the Naomi be Wolf, oh, buddy. Ooooof.” Thus the basis of Klein’s new book, Doppelganger.
Writing hundreds of pages based on the Twitter discourse surrounding your evil twin is, of course, a deeply questionable choice. Klein openly admits that her family and friends questioned her sanity. As she is quick to point out, though, Doppelganger is not really about Wolf. Instead, the book uses the experience as an entry point to dissect the “intellectual and ideological mayhem” of the Covid era. How wellness entrepreneurs demonize medicine. How the far right appropriates and warps leftist talking points. How parents insist on seeing their children as reflections of themselves. In all this, Klein writes, there’s a new doubling going on—weird fun house distortions of what used to be more straightforward realities. It’s a lively, slightly unwieldy, wholly vital work. It could only be hers.
Klein moved to the Sunshine Coast of British Columbia during the pandemic, a riotously beautiful nook of that vast province, where towns are nestled into fjords. It’s a place far more likely to be visited by orcas than members of the US media, and in the interest of saving me a journey on a ferry—you can only get to her home by boat or floatplane—Klein met me at her office at the University of British Columbia, where she codirects the Centre for Climate Justice. We’d intended to stroll around the sprawling, sunny campus, but the conversation kept such an intense clip, we ended up simply sitting for hours.
Kate Knibbs: Doppelganger is much more personal than your previous work. Why? Naomi Klein: I thought it was really important not to be on the outside of this story, but to be inside, to fess up to my own disorientation. Having a doppelganger who a lot of people confuse me with is a type of losing oneself, and it provided a toehold into this larger and more interesting set of feelings, of being lost in a world we might not recognize.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You listened to conspiratorial podcasts for research, including Steve Bannon’s. Were you ever worried you’d get lost in those worlds? I felt that way the first time I went to a climate change denial conference. I was a tiny bit worried I would start to doubt my own understanding of the science by listening to them. But the exact opposite happened, because it was so completely incoherent. One guy says it’s getting cooler. Another says it’s getting hotter—but the sunspots! Another guy says everyone should just get air-conditioning. That’s what it’s like listening to Bannon or any of those “intellectual dark web” types. You can see it right now with RFK Jr. He’s saying Covid was a bioweapon. This is also the guy who told people not to wear masks, not to lock down, not to get vaccinated. So which is it? Occasionally Bannon would have someone on who would claim that people were just dropping dead from the vaccine.
Like the whole #DiedSuddenly thing? Exactly. What you start to realize is that these people are acting as if we were immortal before Covid. As if no one died from anything. What worries me more isn’t that I’m going to start thinking that the vaccines are killing us or anything like that. It’s that I understand why the things he’s doing are so resonant.
Why are they so resonant? This is Bannon’s gift, sorry to say, and it’s how Trump won in 2016: by identifying a bloc of Democratic voters who had been screwed over by the party because they lost jobs to corporate free trade deals. So the offer was a counterfeit version of the left, which is what right-wing populism does. They were not rewriting trade deals in any significant way that would help workers. They were offering huge gifts to the already wealthy through tax cuts. But when people are desperate enough, they’ll go for a counterfeit.
I have someone close to me who has definitely bought into that counterfeit populism. It’s been hard to watch the change take place.
I’ve had so many conversations with people describing that feeling. It’s like watching Invasion of the Body Snatchers.
But I suppose we all have many competing, constantly mutating versions of ourselves. How do you think about your public persona now? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When we think about performing ourselves, we think about social media. For me, that’s Twitter [since renamed X]. And right now I don’t think any of us feel in control of whatever the fuck is happening on Twitter. But we’re still there, hoping to recapture something. I hope my relationship to my public persona is like my relationship with Twitter. I’m not really trying anymore.
Photograph: Kamil Bialous Do you think there’s a way for you to have a conversation like this that’s truly authentic, or are you in some sense creating a doppelganger version of yourself to promote the book? There’s always going to be some contradictions involved in hawking a book when you’re an anti-capitalist author. I’ve been living with that contradiction for a long time. I find talking to people exciting. I have ideas that I wouldn’t have had otherwise. I had the idea to write No Logo while I was doing an interview with a student journalist.
Are your students influential in other ways? One of the really nice things about being on campuses right now is that, if I was just getting my sense of youth culture through media, I’d think that all young people are constantly posing and performing themselves on Instagram. But it’s definitely a minority. A lot of young people feel alienated from it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I get a lot of youth culture tidbits from my babysitter, which is how I know that super polished and posed Instagram photos are seen as a geriatric millennial thing.
They want it to look really authentic, to be messy.
I reread No Logo recently. It holds up.
Maybe not the Blockbuster references! Honestly, we need to bring back your concept of selling out. I got in a lot of trouble on Twitter a few months ago for saying the Barbie movie looked bad. I love Greta Gerwig, but I don’t want to like Barbie ! I hate the idea of a Mattel Cinematic Universe.
The thing that’s so clever is that it’s shiny and pretty enough to get the normie Barbie fans, but it also has so-called subversive content for the people who don’t want to like Barbie. It’s genius marketing. But the world is fraying. It’s an odd time for us to get excited about pink plastic.
Probably an odd time for me to be really annoyed about it, too.
No, I think it’s time to have some standards again.
Do you ever think about returning to that mode of criticism? Just to keep you company? To keep me company, and because efforts to turn cinema and television into capital-B Brands—the Marvel Cinematic Universe, most infamously—are so much more flagrant than before.
And also to keep us in our childhoods in a strange way. This is not kid content, it’s adult content, but it’s feeding on nostalgia for being 8 years old.
What’s a recent movie you liked? Despite the critics hating it, I thought Don’t Look Up was brilliant. It was taking aim at the culture of narcissism and distraction at this most critical moment. It was broad, like all of Adam McKay’s comedies. But that was not the problem. The problem was that it was right.
Doesn’t everyone die at the end? That’s the best part. He fucked with the Judeo-Christian trope that the righteous will be saved.
I do think it was broad.
Well, Anchorman is broad! True. But I don’t necessarily want my comedy to be didactic. I just really don’t want it to be branded content from Mattel. There’s this amazing Canadian filmmaker, Sarah Polley, and she’s doing a live-action Bambi.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg My grandpa worked on the original Bambi.
He was an animator.
I read about this. Didn’t he get fired for trying to unionize? He did. And they had the first strike at Disney during the production of Dumbo.
Have you been paying attention to the strike wave happening? It’s exciting. I’m really glad that there’s the focus on AI.
What else interests you politically, right now? I think it’s important to think about where the Covid denialism energy is going now that there aren’t vaccine mandates. It’s morphing, going in new directions, and it’s important to try and follow that.
Which new directions? There are two main wellsprings the Covid denialism movement drew from. One was the anti-vax people. The other group was climate deniers. Now, when you post anything about climate change, you’ll get hit with “Davos elites, Great Reset.” When we were talking earlier about how people take leftist ideas and make counterfeit versions of them, I was thinking about how that happened to the shock doctrine—your idea that global elites use disasters to push brutal policies to benefit themselves at the expense of the masses. People co-opted the concept to talk about the Great Reset, saying there was a global conspiracy to use Covid to strip away personal freedoms. Has this changed your relationship to your own ideas? Do you feel less ownership over them? I’ve never felt I had that much control over my ideas in the culture. I remember Arundhati Roy saying to me many years ago, we can’t control what our words do once we release them.
I have tried to correct the record and do my own writing about what I think the shock doctrine is and isn’t, but I think I’ve always felt a bit of detachment around it.
Jane Fonda started her Fire Drill Fridays because of you.
That was just getting somebody at the right moment of receptivity. That’s what Jane did. I take no credit.
Do you believe in the horseshoe theory? Are the people on the far left swinging far right because they’re attracted to conspiratorial thinking about Covid? There are some people who have decided that Tucker Carlson is a great guy and Trump’s better than Biden. But most of those people I wouldn’t consider very left-wing. Someone like Glenn Greenwald. For a while, he seemed to be a left-wing person because he was against the Patriot Act and the Iraq War. But he was a libertarian upset about Bush-era government overreach. So it makes sense, when a government has to robustly respond to a pandemic, that a lot of those people got upset. I know some of these people—Matt Taibbi and Glenn Greenwald—I know that they are not deep left thinkers. We have to make the distinction.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Do you think there’s an incentive to shift rightward now to bolster one’s personal brand online? Yes.
Could there be a positive incentive the other way? Is it possible to build up an ecosystem of independent leftist outlets? Remember that idea? We need to invest in media, and not be reliant on quixotic billionaires to find one another. I think we need to get serious about independent alternative media and local media.
Meaning, like, a new Twitter? The problem with something like Mastodon or the smaller Twitter competitors is that they’re not able to offer what Twitter did at its best, which was this feeling of we’re all having one conversation together.
I don’t know if there will ever be one main conversation again.
I wish Twitter could’ve been turned into a co-op. This is labor we’ve put into this thing. We all wrote for free! A lot.
There was always something self-exploiting about that. Sure, we were able to share our articles and do self-promotion, but I always knew they were going to try to charge us. It’s too valuable.
There’s a co-op movement for media startups, where the writers own their outlets, but I haven’t seen the same thing happen for social media.
And the thing happening now with AI—it was one thing for all of us to be writing for free for Zuckerberg and Musk, but now it turns out that all of that content is being used to create doppelgangers of us by AI companies. Now that’s going to be used to put people out of work, or cheapen their labor.
Photograph: Kamil Bialous Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It’s accelerating so rapidly. Big outlets are already putting out AI-generated articles.
This relates back to conspiracies and why they’re spreading as quickly as they are. It’s a dangerous time to give people more reasons not to believe what’s in front of them. Anything you’re shown now can be dismissed as fake news. “It’s not even Biden, it’s AI.” We’re barely glimpsing the ramifications.
In Doppelganger , you wrote about a South Korean politician who used AI to look younger.
The thing about the Korean example is, it was not hidden. Everyone knew. And it worked for him. So who knows? As our candidates get older, they may rely on AI doppelgangers. It’s being packaged as a way to reach younger voters, because they prefer synthetic reality.
Have you had discussions with your students about AI? Do they actually prefer synthetic reality? Last semester, ChatGPT was really everywhere, and we were discussing how they were not using it to write their essays. I think we’ve overfocused on the plagiarism piece of things. It’s just one element within a completely unstable and frightening future. Maybe it’s helpful writing essays, but they also know it’s replacing entire sectors they may have been preparing for—between not being able to afford living in the city to the acceleration of the climate crisis to AI changing the job market.
I’m aware of at least one podcasting company hoping to use AI to translate podcasts into a bunch of different languages. It sounds cool, but then you think: What about translators? The thing I find disingenuous is when you hear, oh, we’re going to have so much leisure time, the AI will do the grunt work.
What world are you living in? That’s not what happens. Fewer people will get hired. And I don’t think this is a fight between humans and machines; that’s bad framing. It’s a fight between conglomerates that have been poisoning our information ecology and mining our data. We thought it was just about tracking us to sell us things, to better train their algorithms to recommend music. It turns out we’re creating a whole doppelganger world.
We’ve provided just enough raw material.
When Shoshana Zuboff wrote The Age of Surveillance Capitalism , it was more about convincing people who’d never had a sense that they had a right to privacy—because they’d grown up with the all-seeing eye of social media—that they did have a right to privacy. Now it’s not just that, even though privacy is important. It’s about whether anything we create is going to be weaponized against us and used to replace us—a phrase that unfortunately has different connotations right now.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Take it back! The right stole “shock doctrine,” you can nab “replace us” for the AI age.
These companies knew that our data was valuable, but I don’t even think they knew exactly what they were going to do with it beyond sell it to advertisers or other third parties. We’re through the first phase now, though. Our data is being used to train the machines.
Fodder for a Doppelganger sequel.
And about what it means for our ability to think new thoughts. The idea that everything is a remix, a mimicry—it relates to what you were talking about, the various Marvel and Mattel universes. The extent to which our culture is already formulaic and mechanistic is the extent to which it’s replaceable by AI. The more predictable we are, the easier it is to mimic. I find something unbearably sad about the idea that culture is becoming a hall of mirrors, where all we see is our own reflections back.
You reached out to Naomi Wolf and she didn’t respond. If she had responded, would you want to debate her? I think it’s important to engage with what’s being said and marshal counterfacts. But the idea of just sneering at people is dangerous. I think we do need to debate, but whether that means creating some kind of theatrical Naomi vs. Naomi spectacle—I don’t know about that.
You could be second billing to Musk vs. Zuckerberg.
Anyway, as you know from reading the book, it’s not really about her. She’s just a case study. I follow her down the rabbit hole. But I’m more interested in the rabbit hole.
Let us know what you think about this article. Submit a letter to the editor at [email protected].
You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics longreads Big Interview Books conspiracy theories Andy Greenberg Brandi Collins-Dexter Angela Watercutter Steven Levy Lauren Smiley Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,054 | 2,023 |
"Why Aren't Disabled Astronauts Exploring Space? | WIRED"
|
"https://www.wired.com/story/ashley-shew-disability-space-exploration"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ashley Shew Ideas Why Aren’t Disabled Astronauts Exploring Space? Photo-illustration: WIRED Staff; Getty Images Save this story Save Save this story Save Today, young people are becoming disabled in record numbers with all the various impacts of long Covid , which is estimated to affect between 8 and 25 percent of people who have been infected. The disabled future is coming to pass now, and we need to create inclusive and accessible environments for all kinds and ages of disabled people to deal with it.
Beyond Covid, pollution is increasing rates of environmentally produced disability—higher levels and lower onset ages of different types of cancers , as well as rising rates of asthma, chemical sensitivities, and autoimmune disabilities, some of which can come from smog and conditions of poor air quality. The future is also disabled for the planet itself. Sunaura Taylor, a fellow disabled scholar and an animal and environmental activist, writes powerfully of the “ disabled ecologies ” that constitute the landscapes we have impaired. Her case study is the Superfund site in Tucson, Arizona, which contaminated local groundwater and, 40 years later, is still affecting the land and surrounding communities. She thinks disabled people have important insight into how to live, age, and exist with disabled ecologies. She reminds us that we can’t just get rid of our land, our environment. We have to learn how to live in a world we have disabled.
Even with hopeful futures like that of space travel , we can expect the production of disability. Space is already disabling for humans. Just as the built environment on Earth is not suited for disabled bodies, space as an environment is not suited to any human bodies. Every astronaut comes back from the low gravity of space with damage to their bones and eyes—and the longer they are off Earth’s surface, the worse the damage. Some things can be restored over time, but some changes are long-lasting. These realities are absent from futurist writing about technology, which is framed as simply magicking away the disabling effects of space travel.
This is why technofuturists’ discussions of “ The End of Disability ” are so silly. Disability isn’t ending; we’re going to see more and newer forms of disability in the future. This doesn’t mean that all medical projects aimed at treating disease and disability are unpromising. But we need to prepare for the disabled future: becoming more comfortable with other people’s disabilities, accepting the fact that we ourselves will eventually be disabled (if we aren’t already), learning to recognize and root out ableism—these are all moves toward building a better future for everyone. Planning for the future in a realistic way requires embracing the existence, and indeed the powerful role, of disabled people in it. We must rid ourselves of technoableism—the harmful belief that technology is a “solution” for disability—and instead pay overdue attention to the ways that disabled communities make and shape the world, live with loss and navigate hostility, and creatively adapt.
The promise of disabled space travel is a particularly potent case study. Deaf-and-disabled-led literary journal The Deaf Poets Society asked us to dream in 2017 with their #CripsInSpace special issue. Guest edited by Alice Wong and Sam de Leve, this issue was announced with a video of de Leve showing us how they are specially suited for space—since, as wheelchair users, they were already trained to push off of kitchen counters and walls to get where they wanted to go. They also pointed out that while most kids can dream of being astronauts, disabled people are usually given fewer options, even early in life. So they asked us to dream, write, and create art: The issue features short stories, prose, and poetry in which people think about how they are better suited for going to the stars.
Others have also considered disabled space travel and disabled futures. In 2018, blind linguist Sheri Wells-Jensen (now the 2023 Baruch S. Blumberg NASA/Library of Congress Chair in Astrobiology, Exploration, and Scientific Innovation) made “ The Case for Disabled Astronauts ” in Scientific American.
She wrote about how useful it would be to have a totally blind crew member aboard. Spacesuits would need to be better designed to transmit tactile information, but a blind astronaut would be unaffected by dim or failed lighting or vision loss from smoke, and would be able to respond unimpeded, unclouded, to such an emergency—Wells-Jensen refers to a problem on the Mir where they couldn’t find the fire extinguisher when the lights went out.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Two discussions at the Library of Congress about uncertain space futures took place in 2018, first an “un-conference” called Decolonizing Mars and, a few months later, a series of panel discussions and performances on Becoming Interplanetary.
These events, organized by astronomer Lucianne Walkowicz (who has since founded the Just Space Alliance), fostered conversations from a wide variety of perspectives on how our narratives about space center “the right stuff” (to borrow the title of Tom Wolfe’s novel) in ways that are sometimes problematic when it comes to recruiting, dreaming, and planning for space. The “stuff” that is taken to be “right” is usually privileged, masculine, from dominant cultures, and extremely abled (there are stringent physical “fitness” requirements for astronauts). Recruiting for space has always held up certain bodies as better than others, in ways that don’t at all map onto what might actually work best. During the Decolonizing Mars event, as we sat in a smaller group discussion circle, I learned that short women with larger thighs do better at not passing out when they pull high numbers of g’s as fighter pilots; their brains are closer to their hearts, so the additional blood flow helps them remain conscious, and their larger butts/thighs seem to absorb some impact. Yet typically, the “best” fighter pilot looks like Val Kilmer as Iceman in Top Gun.
Courtesy of W. W. Norton & Company Buy This Book At: Amazon Bookshop.org Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Later I offered the example of the Gallaudet Eleven—eleven Deaf men recruited from Gallaudet University in the 1950s and ’60s for a NASA study of motion sickness. They went through astronaut training and many different tests. Congenitally deaf people don’t get motion sickness, and NASA simply wanted to know how nondisabled astronauts could avoid motion sickness too. The Deaf men were never considered for astronaut candidacy, however, despite their ability to avoid motion sickness. Other participants, like Brenda J. Child, Chanda Prescod-Weinstein, and Brian Nord, highlighted the ways in which our space rhetoric perpetuates narrative structures that have done a lot of harm—ideas about frontiers, claiming planets and territory, mining and extraction from other planets, and colonization. As they pointed out, the continued use of these terms restricts how we imagine space, framing it simply as a continuation of colonization and capitalism—the very ways of thinking about space, ownership, and land that are so deeply disabling the Earth.
Sheri Wells-Jensen has now been on two zero-g parabolic flights and knows what it would feel like to be in space. She and others put her case for disabled astronauts out into the world, and onto the right desks—and she became part of the first flight of Mission: AstroAccess.
The goal of AstroAccess is to include disabled people in space exploration. Their first mission flew with 12 disabled “ambassadors” aboard in 2021, and they flew again in late 2022. To me, this disabled zero-g flight was huge news, just as Stephen Hawking’s similar zero-g flight had been in 2007. However, the AstroAccess flight made less of a public splash; I only saw it reported because I follow disability-specific news.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The thing about space flight, space stations, and the type of exploratory travel we are talking about in space is that it’s all uncertain; we don’t know what skills might be needed. (This is true on Earth, too, just easier to imagine off-surface.) And all the necessary space infrastructure—any aircraft, spacecraft, or station—is something we build. (We could certainly be building regular airplanes to be more accessible to disabled people already. Wheelchair users are particularly degraded, restricted, forgotten, and excluded with our current airplane setups.) We already know retrofitting sucks. Why not build things to be as inclusive as possible now instead of trying to fix them later? Finally, since we are going into an environment that we were not brought up in, it doesn’t matter whether astronauts are nondisabled: Again, we are all disabled in space. Our environmental niches are all on Earth, and our capabilities are all Earth-related. Disabled people don’t have the same disadvantages in space that they may have here on Earth—especially if we work to avoid creating or re-creating disadvantages in how we build and plan for space.
My disabled friends can imagine ways that we would be well suited for space or space for us; we can all give different reasons why either our bodies would feel better in space (less gravity weighing our pain on us) or why our bodies would be superior for space flight or travel. My friend Mallory Kay Nelson is the cleverest here, because she’s well adapted for pooping in space. In case you don’t know, it’s very difficult to poop in space—both in terms of physical properties and engineering-wise. Astronauts have to train to use specialized toilets (there is a whole toilet-engineering team with each space agency), and the toilets are finicky and have a history of breaking. Because pooping is so complicated, Mallory has suggested that NASA should only be recruiting people with ostomies—people who have openings in their abdomens (called stomas) to excrete waste using ostomy bags. All the engineering and work that currently goes into space toilets is only necessary because no one has an ostomy! I’m puzzled why we aren’t actively recruiting for some types of disability here. Sheri Wells-Jensen has already given us the case for the edge that blind people would have on crews, and Sam de Leve, as part of #CripsInSpace, discussed the edge that manual wheelchair users would have moving in space. The Gallaudet Eleven were considered superior, and were studied for that reason! I got to lead a colleague’s class at one point where we ended up talking about how people who have experienced some types of mental illness might be better suited in some ways to monitor themselves and others around them for certain emotional and physiological responses to space. They might also help come up with ways to manage conditions like seasonal depression, which could be a huge concern if we traveled farther away from the sun. We already know what our slight tilt of the Earth means for mental health in the far north and far south of our globe when it comes to higher rates of suicide and depression, and we should be attuned to this in how we plan for space too.
We need to be wary of technoableism—technology development and marketing that makes it seem like disability is a big, bad thing that needs to be downplayed or eliminated. Most of our supposed experts about disability are nondisabled people, who don’t know what it’s like to be the object of ableism, of design made at you rather than for you, of future imaginings that snuff you out of existence, of scrutiny around every one of your choices, your behavior, and your being. This is why we need to look to intersectional, cross-disability communities for expertise, and for creative visions of a future that cuts no one out. We need to make the world more hospitable to more ways of being and existence, not just by heeding disabled expertise but by loosening our ideas about what “the right stuff” is, and by insisting there is no wrong stuff. We should be actively anticipating all the stuff—and planning that way.
Excerpted from Against Technoableism: Rethinking Who Needs Improvement.
Copyright (c) 2023 by Ashley Shew. Used with permission of the publisher, W. W. Norton & Company, Inc. All rights reserved.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Topics Book Excerpt space astronauts disability Meghan O'Gieblyn Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,055 | 2,022 |
"The Hunt for the Kingpin Behind AlphaBay, Part 1: The Shadow | WIRED"
|
"https://www.wired.com/story/alphabay-series-part-1-the-shadow"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Part 1: The Shadow Part 2: Pimp_alex_91 Part 3: Alpha Male Part 4: Face to Face Part 5: Takedown Part 6: Endgame By Andy Greenberg Backchannel The Hunt for the Dark Web’s Biggest Kingpin, Part 1: The Shadow Illustration: Hokyoung Kim The Rise and Fall of AlphaBay Part 1: The Shadow Now Reading Part 2: Pimp_alex_91 Part 3: Alpha Male Part 4: Face to Face Part 5: Takedown Part 6: Endgame Save this story Save Save this story Save PROLOGUE on the morning of July 5, 2017, a gray Toyota Camry slowly turned into the cul-de-sac of a quiet neighborhood in Bangkok—a moderately upscale subdivision on the western edge of the city, where the pulsating capital's downtown high-rises began to flatten out into highways and canals snaking through tropical forest and farmlands.
Behind the wheel sat a woman who went by the nickname Nueng. A slight, 46-year-old agent of the Royal Thai Police with a short, boyish haircut, she wore a white polo shirt and black pants rather than her usual military-style uniform. Both she and the female officer beside her in the passenger seat were working undercover.
This story is excerpted from the forthcoming book Tracers in the Dark: The Global Hunt for the Crime Lords of Cryptocurrency , available November 15, 2022, from Doubleday.
Courtesy of Penguin Random House Nueng's heart pounded. For more than two years, law enforcement agents from around the world had been hunting the dark-web mastermind known as Alpha02, a shadowy figure who oversaw millions of dollars a day in narcotics sales and had built the largest digital drug and crime bazaar in history, known as AlphaBay. Now, a coordinated takedown and sting involving no fewer than six countries' agencies had tracked Alpha02 to Thailand. The operation had finally led to this quiet block in Bangkok, to the home of a 26-year-old Canadian named Alexandre Cazes. Nueng knew that the success of the plot to arrest Cazes and knock out this linchpin of the global underworld economy hinged on what she did in the next few moments.
Trying to give the impression of an inexperienced driver, Nueng slowly rolled the car toward a model home and real estate office at the end of the cul-de-sac. She signaled to a security guard outside the house that she had taken a wrong turn and needed to pull a 180. She heard him shout at her to back directly out instead, that the street was too narrow for a three-point turn.
Nueng quickly muttered a nearly silent prayer—an adapted, high-speed plea to the holy trinity of the Buddha, his teachings, and all the monks and nuns in his service. “Dear Buddha, please bless me with success,” she whispered in Thai. “Dear Dhamma, please bless me with success. Dear Sangha, please bless me with success.” Then she put the car in reverse, turned the wheel to the left, and ever so gently—almost in slow motion—slammed the Toyota's fender into Alexandre Cazes' front gate.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg ALPHA02 Around 18 months earlier, Robert Miller sat in the US Drug Enforcement Administration's wiretap room in Fresno, California, spending another painfully boring day listening in on the life of one of the DEA's endless supply of narcotics targets in California's Central Valley.
All Miller ever wanted was to be on a SWAT team. At the academy, instructors had praised him for his instinctive judgment and thoroughness—how, in training raids on the academy's mock-ups of drug dens, he always meticulously cleared his corners and covered his blind spots. And when the young DEA agent was assigned to the agency's field office in Fresno right after graduation, he had high hopes it would put him where he wanted to be: making arrests, carrying out search warrants, “hitting doors,” as he put it. (Miller's name and some personal details have been changed, per his request.) The sunbaked agricultural city in the middle of California had long served as a corridor for cocaine, heroin, weed, and methamphetamine smugglers, as traffickers from the southern border made their way to buyers in the Northwest and on the East Coast. Agents spent their days carrying out undercover buy-and-busts, following trucks packed with dope along Highway 99 and tracking, raiding, and arresting cartel operators.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But not long after he moved to Fresno, Miller injured his foot and his shoulder while rock climbing. Both injuries required surgery. There would be no SWAT team, no “hitting doors”—not, at least, for the two years it would take to recover.
So Miller was assigned to surveillance. He'd stake out targets from his car or sit in the office's wiretap room, listening to suspects' phone calls and reading their texts for weeks or sometimes months on end. The work was often mind-numbingly mundane. “Ninety-nine percent boredom and 1 percent excitement,” as he remembers it.
At one point in 2013, Miller's partner on a surveillance assignment suggested they try to work on a new sort of case. She had heard about a booming drug market on the dark web called Silk Road—a site where anyone could connect through the anonymity software Tor and spend bitcoins to buy any drug imaginable—and its pseudonymous creator, the Dread Pirate Roberts. But when Miller asked his superiors about the site, he was told that teams in New York and Baltimore were already on it. Not long after, while Miller was on a surveillance stakeout in his car in a mall parking lot, his phone buzzed with an alert that the notorious market had been busted. The Dread Pirate Roberts turned out to be a 29-year-old Texan with no criminal record named Ross Ulbricht. He had been arrested in the science fiction section of San Francisco's Glen Park Public Library with his laptop open and logged in to Silk Road.
Two long years later, in early 2016, Miller's boss came into the wiretap room and asked whether Miller wanted to join a different team. Someone in the office had remembered Miller's inquiry into Silk Road. A local assistant US attorney had assembled a group to focus on dark-web crime, and he was looking for volunteers from all the federal agencies clustered around Courthouse Park in Fresno's downtown square: the Internal Revenue Service, Homeland Security Investigations, and the Drug Enforcement Administration. The assignment, Miller knew, was pretty much the opposite of the SWAT team. But at least it would be something new. “OK,” he said. “I'll do it.” Grant Rabenn, the young prosecutor at the helm of Fresno's dark-web strike force, laid out a set of modest initial goals for the group: They would be going after individual money launderers and drug dealers, not kingpins and masterminds. “We are not the Southern District of New York. We are in a dusty town in the Central Valley of California,” as Rabenn put it. “Let's hit singles before we try to go for a home run.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg That humble starting point was fine with Miller, who had little idea of how the dark-web drug trade even worked. When Rabenn asked Miller to start making undercover heroin buys, he couldn't figure out how to buy bitcoins, let alone the drugs themselves. He drove two and a half hours to San Jose to find a physical bitcoin ATM rather than simply use an online exchange. Even then, he discovered that after transaction fees he could purchase only half a gram of heroin instead of the 2 grams he'd planned on.
But slowly, as Miller poked around the dark web and perused the various markets, he got a feel for the post-Silk Road online drug economy. He soon came to see that it was dominated by a single entity: AlphaBay.
Get exclusive commentary and behind-the-scenes notes from writer Andy Greenberg.
Sign up for The Rise and Fall of AlphaBay companion newsletter.
AlphaBay had first appeared in late 2014, just one in the broad scrum of markets vying for a share of the growing dark-web criminal trade. But the site's pseudonymous administrator, Alpha02, seemed cannier than those behind many of the competing markets. Alpha02 was a well known if not exceptionally talented “carder,” a cybercriminal hacker focused on credit card theft and fraud. He'd become a significant player on Tor Carding Forum, a dark-web site where hackers traded in stolen data. He'd even sold his own 16-page “University of Carding Guide,” designed to teach beginners the tricks of the trade, like how to “social-engineer” customer service representatives at banks, calling from spoofed telephone numbers to deceive them into approving fraudulent transactions.
In its first months online, AlphaBay seemed destined to serve much the same hacker clientele. It was devoted almost exclusively to cybercriminal wares, such as stolen account logins and credit card data. But as Alpha02 bootstrapped the site from its carder origins, its portfolio of vendors quickly expanded to offer the dark web's more lucrative contraband: ecstasy, marijuana, meth, cocaine, and heroin, all shipped through the mail. Soon it became clear that Alpha02's grand vision was to unite two spheres of the dark web that had, until then, been somewhat distinct—one devoted to cybercrime and the other to drugs—to create a single mega-market. AlphaBay's goal, he declared, was “to become the largest eBay-style underworld marketplace.” Silk Road's Dread Pirate Roberts had espoused a kind of anarcho-capitalist ideal, describing his site as a “movement” or a “revolution” bent on liberating mankind from oppressive government control of commerce and limiting sellers, at least in theory, to offering only “victimless” products. Alpha02, by contrast, seemed to adopt a much less high-minded focus on the bottom line. Aside from a ban on child abuse materials and murder for hire, the only rule Alpha02 imposed on AlphaBay's vendors was that they not sell data or accounts stolen from Russia or other former Soviet states, or infect those countries' computers with malware. This prohibition, common among cybercriminals from that part of the world, was typically designed to avoid trouble from Russian law enforcement—a kind of “don't shit where you sleep” principle. For Miller and other federal agents and prosecutors sniffing around the site, it also suggested that AlphaBay and its mysterious founder were likely based in Russia—an impression cemented by Alpha02's signature in messages on the site's forums: “Будьте в безопасности, братья,” Russian for “Be safe, brothers.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In an interview in April 2015 with the news site and dark-web directory DeepDotWeb, Alpha02 reassured his users that he and his site were beyond the reach of any Silk Road-style seizure. “I am absolutely certain my opsec is secure,” he wrote, using the shorthand for “operational security,” and added, “I live in an offshore country where I am safe.” Throughout that interview, Alpha02 wrote in the style of a corporate press release: “We have made sure to have created a stable & fast marketplace web application which has been built with security in mind right from the start,” he wrote, adding, “We would like to assure all of our users (both vendors & buyers) that their security, privacy and anonymity rank first place in our priorities list.” What Alpha02 lacked in political inspiration he seemed to make up for in technological aspiration and coding competency. He boasted about features that included auction-style bidding, search tools that helped fraudsters comb through stolen data to carefully choose their victims, and a multi-signature transaction scheme designed to reassure users that it would be far harder for law enforcement or rogue staff to steal funds held in escrow.
Among digital crime investigators, Alpha02's notoriety was like that of Osama bin Laden. He and AlphaBay were invoked at every law enforcement conference on cybercrime, every interagency meeting, every training event.
“We want to have every imaginable possible feature to be the #1 market,” he wrote to DeepDotWeb. On each page of AlphaBay, he'd signed his work: “proudly designed by Alpha02.” When a judge imposed a double life sentence on the Silk Road's Ross Ulbricht in May 2015, she told the court that the draconian sentence was partly meant to scare off future dark-web drug buyers, dealers, and administrators. By the time of AlphaBay's rise, that unprecedented punishment seemed to have had the opposite effect. A study in The British Journal of Criminology found that sales on what was then the top dark-web site, Agora, more than doubled in the days following the news of Ulbricht's sentencing, to more than $350,000 a day. The study's author, trying to interpret that unexpected increase, reasoned that by imposing such a shocking prison term, the judge had only generated new awareness of the dark-web drug trade. Rather than deterring users, the judge seemed to have created a massive advertisement for the world's burgeoning cryptocurrency black markets.
Alpha02 was hardly fazed by the news. Following Ulbricht's sentencing, in an interview with Vice's tech news site, Motherboard , he momentarily affected a revolutionary posture, picking up the Dread Pirate Roberts' torch. “Courts can stop a man, but they can't stop an ideology,” he wrote. “Darknet markets will always be around, until the war on drugs stops.” But in response to other questions, AlphaBay's boss seemed to ditch the torch and speak more plainly. “We have to carry on with business,” he wrote. “We all need money to eat.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg By the fall of 2015, AlphaBay was the biggest market on the dark web. Agora's administrators had taken their site offline that August, citing concerns that a vulnerability in Tor, the online anonymity system that powered the dark web, might be used to locate Agora's servers. AlphaBay appeared to have no such security flaw. As it absorbed Agora's tens of thousands of buyers and vendors, the growing crowd of law enforcement agents around the world surveilling the site could find no coding or opsec slipups to give them the slightest clue as to where they might find its servers, not to mention its founder.
Shortly before AlphaBay took over the dark web's top spot, Alpha02 had changed his username on the site to merely “admin” and announced that he would no longer accept any private messages sent to him by anyone other than AlphaBay's staff. Instead, he left much of the site's communications work to his second-in-command and head of security, a figure who went by the pseudonym DeSnake.
The Alpha02 moniker had served its purpose, lending the site its initial credibility. Now the person behind it intended, like discreet criminal bosses the world over, to slip into the shadows, raking in his fortune as quietly and anonymously as possible.
That fortune was, by the time of Alpha02's name change, growing at an unprecedented rate: By October 2015, AlphaBay had more than 200,000 users and more than 21,000 product listings for drugs, compared to just 12,000 listings on Silk Road at its peak. Sometime around the middle of 2016, AlphaBay surpassed Agora's peak sales rate of $350,000 a day, according to researchers at Carnegie Mellon. It had become not only the biggest black market on the dark web, but the biggest cryptocurrency black market of all time. And it was still growing wildly.
For Grant Rabenn, the Fresno-based prosecutor, it was clear that Alpha02 was now the most wanted man on the dark web; Rabenn compared his notoriety among digital crime investigators to that of Osama bin Laden. AlphaBay and Alpha02 were invoked at every law enforcement conference on cybercrime, every interagency meeting, every training event, Rabenn says. And as the target on Alpha02's back loomed larger, so too did the unspoken fear that this mastermind might stay a step ahead of them indefinitely.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “Is this person just a pure genius who's figured out all of the possible mistakes?” Rabenn remembers asking himself. “Has this individual found the perfect country with the right IT infrastructure to run a marketplace, and he's able to bribe the officials there so we'll never touch him? “As every day passed there was, more and more, a sense that this might be the special one,” Rabenn says. “You begin to wonder: Is this the Michael Jordan of the dark web?” But Rabenn followed these discussions of Alpha02 from a distance. The idea that his Fresno team might actually take on the Michael Jordan of the dark web had never occurred to him. “It's not expected for people like us,” he says simply, “to go after a site like that.” THE TIP Before Grant Rabenn became a federal prosecutor, his second job out of law school was at a boutique firm in Washington, DC, devoted to defending white-collar criminals. The young, olive-skinned lawyer with dark hair and a Hollywood smile ended up representing Russian oligarchs and corporate executives accused of bribing foreign governments. “Very interesting, wealthy people trying to hide their assets and avoid scrutiny,” as he described them, or alternatively, “James Bond characters who are jet-setting around the world with suitcases full of cash.” Rabenn was captivated by these glimpses into a world of billions of dollars moving in invisible transactions. But he also found that he admired and envied the prosecutors on the other side of the table—the way they worked in the public interest and possessed a certain autonomy, choosing which cases they would pursue. So he began applying for Justice Department jobs, finally finding one in Fresno.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Despite having grown up in Southern California, Rabenn couldn't place Fresno on a map. But when he arrived at its DOJ office in 2011, he found what he'd always wanted: a place with almost no hierarchy or bureaucracy, where he was simply told to focus on money laundering and was otherwise given free rein. For the next few years, he and the local agents tackled fraud and extortion, child exploitation, corrupt cops, and, of course, drug trafficking—following illicit trails of money wherever they led. “We were just running and gunning,” Rabenn says of those prolific years with a boyish enthusiasm.
Rabenn's money-laundering cases often began with the stream of suspicious activity reports that banks were required to file under the Bank Secrecy Act. By mid-2013, Rabenn found that more and more of those reports were being triggered by financial transfers out of crypto exchanges, platforms where users could trade digital currency for traditional money like dollars, euros, or yen. The banks often suspected that these currency swaps were cash-outs of dirty digital profits. So Rabenn immersed himself in dozens of hours of YouTube videos to understand this still new currency called Bitcoin, its mechanics, and how it seemed to be powering an anonymous underworld of online commerce.
Criminals flocked to these dark markets because the cryptocurrency was widely believed to be anonymous and untraceable. Sure, every transaction was immortalized on Bitcoin's blockchain , an unforgeable, unchangeable, and altogether public ledger. But that ledger recorded only which bitcoins resided at which Bitcoin addresses—long, unique strings of letters and numbers—at any given moment. In theory, at least, that meant buyers and sellers of illicit goods on opposite sides of the globe could send one another cash payments from behind the mask of those cryptic addresses without revealing any hint of their real-world identities.
But just as cryptocurrency-based platforms like AlphaBay opened up vast new global markets to criminals, they also opened up huge new opportunities for law enforcement, as Rabenn quickly realized. The dark web presented him with the chance to work cases on a scale that would otherwise be impossible in Fresno: As long as a dark-web drug dealer could be coaxed into sending a package to the Eastern District of California, the crime officially occurred in his jurisdiction.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Rabenn had no real idea how to pierce the veil of the blockchain's anonymity. But he figured that even dark-web dealers must sometimes make mistakes that could be caught through traditional buy-and-bust police work. For an ambitious young prosecutor, the possibility was thrilling. “I wasn't necessarily happy with just prosecuting drug mules driving meth up the 99 freeway,” he says. If he could arrange an undercover buy online and somehow identify the seller, he could arrest dealers all over the country. “All I have to do is order dope from them, and then we can go get them. And that's what we did.” In 2014, Rabenn began forming his dark-web strike force, inviting local investigators from Fresno's Homeland Security Investigations and IRS Criminal Investigations offices to join. It was a small team of “odd ducks,” as he describes them—agents on the more cerebral side, content to work cases largely on a computer screen instead of kicking down doors like their Central Valley colleagues.
By the time he recruited Robert Miller out of the DEA's wiretap room, Rabenn's team had already achieved some success with their undercover approach. They'd started by cracking down on a few so-called peer-to-peer exchangers—individuals who bought and sold bitcoins in the real world and were often used by dark-web dealers to cash out their dirty cryptocurrency. In several cases, they'd mined those exchangers' Rolodexes for leads on the legal names of dealers who'd done business with them, tracked them down, and arrested them.
But Rabenn had also begun to suspect that his original hunch was correct: Many of the dealers they targeted were indeed sloppy enough that agents could simply purchase drugs and look for clues either in their packaging or the vendors' online profiles.
Miller, starting his new assignment, assembled the usernames of AlphaBay's top dealers of heroin and the powerful synthetic opioid fentanyl, and he began to buy from them one by one. As the packages arrived, triple-sealed in silver Mylar and plastic, Miller and the team scrutinized both the shipments and their sellers' online presence. They found that one vendor had made an elementary mistake: He'd linked his PGP key—the unique file that allowed him to exchange encrypted messages with customers—with his email address on the PGP key server that stores a catalog of users' identities.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Miller and Rabenn quickly tied that email to the dealer's social media accounts and real name. They learned that he was based in New York. Miller then found fingerprints on a package of heroin sent from one of his accounts, which matched those of another New York man. Finally, Miller worked with postal inspectors to get photos taken by a post office self-service kiosk. The photos showed the second New Yorker putting a dope shipment in the mail. Miller and a team of agents flew across the country, searched the two men's homes, and arrested them both.
The same simple PGP trick allowed Miller to find the real name of another dark-web opiates dealer—which turned out to be part of his dark-web handle, written backward—and caught him shipping dope, again using evidence from a post office kiosk camera. When agents raided the man's home in San Francisco, Miller says, they found piles of fentanyl and heroin powder sitting on tables and in open plastic containers.
Rabenn's team was now on a roll, building significant cases—and even a reputation. When Miller ordered a package of opiates addressed to Fresno, he was amused when his San Francisco suspect warned him that a particularly aggressive group of feds operating out of the Central Valley seemed to be targeting players on the dark web and that he'd better watch his back.
But Miller and Rabenn didn't kid themselves: Busting a few of AlphaBay's sloppier dealers wasn't any more likely to topple that black market than the DEA was to defeat Mexican cartels by chasing yet another meth mule up Highway 99.
By November 2016, Miller was ready to try something new again. He'd achieved a couple of decent dark-web busts, but he didn't love the paperwork or the weeks spent in front of a screen. His shoulder and foot had finally recovered. Perhaps it wasn't too late to get onto the SWAT team after all.
Then, one afternoon, Miller returned to the office after picking up lunch, his In-N-Out Burger bag still in hand, to find an email from an intriguing stranger.
The email explained that the sender had been googling dark-web arrests, looking for a law enforcement contact. They'd tried the FBI tip line, but no one had responded. They'd tried Homeland Security—no luck there either. Finally, they'd found Miller's contact information in one of the Fresno team's criminal indictments of an AlphaBay drug dealer.
So the stranger had decided to try getting in touch with Miller. And now they were ready to share a tip about who Alpha02 might really be.
Continued in part 2: On the trail of a mastermind, a tip leads detectives to a suspect in Bangkok—and to the daunting task of tracing his millions in cryptocurrency.
This story is excerpted from the book Tracers in the Dark: The Global Hunt for the Crime Lords of Cryptocurrency , available November 15, 2022, from Doubleday.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Chapter illustrations: Reymundo Perez III Photo source: Getty Images This article appears in the November 2022 issue.
Subscribe now.
Let us know what you think about this article. Submit a letter to the editor at [email protected].
Read next Read next The Hunt for the Dark Web’s Biggest Kingpin, Part 2: Pimp_alex_91 You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics longreads magazine-30.11 The Rise and Fall of AlphaBay dark web Crime cybersecurity FBI Andy Greenberg Lauren Smiley Angela Watercutter Brandi Collins-Dexter Steven Levy Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,056 | 2,000 |
"O, Engineers! | WIRED"
|
"https://www.wired.com/2000/12/soul"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Evan Ratliff O, Engineers! Save this story Save Save this story Save Twenty years ago, Tracy Kidder published the original nerd epic.
The Soul of a New Machine made circuit boards seem cool and established a revolutionary notion: that there's art in the quest for the next big thing.
Nestled into a wicker rocking chair, among his framed maritime charts and teetering piles of sailing books, Tom West could easily pass for a salty old sea captain. In fact, rocking back and forth on his porch in the foggy coastal town of Westport, Massachusetts, wearing a worn-out T-shirt and sandals, he'd prefer it that way.
"Nobody in this town knows who I am," he says. "I don't talk about what I did. They don't ask." He leans back slowly, lightly gripping the chair's armrests with weathered hands. "It offends me when people think they know me because of the book." The book, to West and others who lived its story, is Tracy Kidder's The Soul of a New Machine.
The 1981 best-seller and Pulitzer Prize winner chronicles the dramatic efforts of West and his team of engineers at Massachusetts-based Data General to build a minicomputer known to its creators as "the Eagle." In the 20 years since Soul made West a minor high tech celebrity for his gruff, competitive management style and brooding technical vision, PCs and workstations have supplanted minicomputers. After a long struggle in one hardware market or another, Data General too disappeared, swallowed up last year by storage giant EMC. Almost all of the Eagle project's engineers and managers abandoned the sinking company in the early '80s, scattering to the four corners of the high tech world and beyond. West stayed at Data General, finally retiring two years ago to the anonymity of his Westport home, his four boats, and the wireless server he designed and built in his basement.
To someone who knows West only from the book, he does at first glance defy its characterizations. For one thing, he's no longer the thin, bushy-haired figure Kidder describes. At 60, he sports a hearty gray beard and a healthy captain's belly. He's also lost his aversion to engineers who work on computers at home - he spends much of his time these days on the Internet. More striking is his demeanor, which, in stark contrast to the book's portrayal, borders on jovial. Today, West talks easily about what it's been like to have such a public record of one part of his life. "It was an odd experience, that's for sure," he muses. "I think I remember the story more than the event. Most events happen and I file them away. This one happened over and over again." More than a simple catalog of events or stale corporate history, Soul lays bare the life of the modern engineer - the egghead toiling and tinkering in the basement, forsaking a social life for a technical one. It's a glimpse into the mysterious motivations, the quiet revelations, and the spectacular devotions of engineers - and, in particular, of West. Here is the project's enigmatic, icy leader, the man whom one engineer calls the "prince of darkness," but who quietly and deliberately protects his team and his machine. Here is the raw conflict of a corporate environment, factions clawing for resources as West shields his crew from the political wars of attrition fought over every circuit board and mode bit. Here are the power plays, the passion, and the burnout - the inside tale of how it all unfolded.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Over two decades, Soul has endured as the high tech story by which all others are judged. "It was the first book to describe the inner workings of the technology groups,"says Novell CEO Eric Schmidt, "and it did a good job of getting into the psychology of leadership. The corporate maneuvering was both fascinating and abhorrent to me." Soul demanded that followers of technology thereafter see their subject with a new, astute eye. "I had never read such a book covering the work of engineers," says Apple cofounder Steve Wozniak. "The readers got to 'live' with these engineers for a while. It's easy to consider engineers inhuman and hackers dangerous threats when you don't know them. I was very sad at the end, that the engineers were not better-respected and marketing folks here were credited with the computer." The engineer as artist, scientist, visionary; the computer builder as protagonist, even celebrity - these cultural figures came into being in Kidder's Soul and provided a new framework for understanding the progress of the industry.
Of course, the book was only a snapshot of the lives of its characters, most of whom are now, at mid-career, in their forties and fifties. The Eagle eventually shipped, and when it did, the people who toiled in the basement of Data General looked up and realized they needed something to fill the void. An engineer's essential desire, after all, is to design and build a machine and see it through to completion, but completion itself is therefore not the ultimate reward. In the Eagle days, West called this paradox "pinball." In pinball, he reasoned, the prize for winning is getting to play again. The story of the Eagle engineers since Soul is one of a career-length version of pinball.
West, too, kept playing. But for him, pinball meant more than building circuit boards. It was a grand contest requiring an intricate, and at times fierce, corporate strategy. There was more to a machine than designing it; there was confronting the business culture that often resisted innovation, and there was the pleasure of beating the other guy. West played this kind of game for 20 years after Eagle. He battled on until he was too burned out to fight for the next project, then he took his quarters and went home.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg "Engineers are aesthetes," observes Tracy Kidder, looking back on the hero of Soul today. "They want technological symmetry. The smartest engineers at Data General wanted to build beautiful machines. West was different. He had another motive. He was pissed." "The smartest engineers at Data General wanted to build beautiful machines. West had another motive. He was pissed." Signing Up West usually drove out of Westborough fast after work. "I can't talk about the machine," he said one evening, bent forward over the steering wheel. "I've gotta keep life and computers separate, or else I'm gonna go mad." - Tracy Kidder, The Soul of a New Machine Tom West never prepared himself for what became the Eagle project. Even today, when hindsight could make the chaotic effort seem like a well-planned scheme, he allows that the whole thing "just kind of happened." Then again, that's how the best engineering efforts often take shape. West had come to Data General in 1974 from RCA, where he'd essentially taught himself computer engineering after seven years of traveling the world building digital clocks for the Smithsonian Institution. Arriving as a line engineer, he quickly jockeyed his way to the head of DG's Eclipse group, which built one of the company's wildly successful 16-bit minicomputers. West was more than just technically adept; he had a knack for getting a computer out the door.
The drama recounted in Soul began in 1978, hatched out of a bitter power struggle. At the time, DG was a player in the multibillion-dollar minicomputer market, part of the late-'70s "Massachusetts miracle" of high tech development. But due in part to a feud over taxes between Data General founder Edson de Castro and Massachusetts' governor at the time, Michael Dukakis, de Castro transplanted DG's lead development team to Research Triangle Park, North Carolina. Many of the company's top engineers, including West, refused to uproot their families and move.
Meanwhile, DG was desperate for a new machine. A year earlier, the company's arch rival, Digital Equipment Corporation, had released the powerful and quick-selling 32-bit VAX. DG's brass looked on in dismay as sales of VAX swamped those of their slower, 16-bit machines. DG needed a 32-bit computer, and fast. With the engineering department now split, the North Carolina team was chosen to develop an advanced 32-bit design that would be far more complex than VAX's. Dubbed the Fountainhead Project (FHP), after its former home in a Westborough, Massachusetts, apartment complex, the machine would be the company's chance to leapfrog Digital.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg With de Castro ordaining the North Carolina group as the company's savior, West and other engineers who'd stayed behind felt slighted. "The implication was, those guys had the right stuff and we didn't," says Carl Alsing, West's soft-spoken deputy in the Eagle days. "We were being asked to just maintain the old tried-and-true designs and upgrade them every year or two. We felt a little affronted by that, and that's how it all got started." So West made a brilliant Machiavellian move. Instead of designing a next-generation processor, his group would simply port the 16-bit minicomputer to 32-bit, keeping it reverse-compatible with the old software. He pitched it to de Castro as insurance; it would be there if something went wrong in North Carolina. In fact, he realized, a streamlined approach and its promise of reverse compatibility could be executed more quickly and prove more successful than a brand-new design. The soft sell worked - the project received tacit approval from de Castro. Code-named Eagle, the machine would be designed and built by West's group in the basement of Westborough building 14A/B. He promised, audaciously, that it could be completed in a year. "We're building," West told Kidder, "what I thought we could get away with." West and Alsing corralled a group of managers and hired two dozen young engineers, most straight out of college - "smarter, non-mindfucked people," West says today. The new hires split into two groups: the "Hardy Boys," responsible for the Eagle's hardware, and the "Microkids," charged with writing the machine's microcode. From its tortured beginnings, the project was layered with the tangible intensity of twentysomething engineers racing against the clock to save the company. While West was "low-key" about the machine outside the Eagle group, he was the opposite within, telling the kids that the company was on the line, spurring them on with the belief that the Eagle - and they - were DG's last hope for survival.
"We sublimated everything to the project," recalls Jonathan Blau, a Microkid on Eagle. "You worked long hours, seven days a week. Your head was always in it, and it was fun. It had that boot camp quality that can't really be repeated." West had invented a term for this DG brand of sublimation, in which the machine became the engineers' lives. He called it "signing up." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To Kidder, the combination of the team's fervor, West's cunning and taste for vengeance, and the corporate mystery shrouding a computer came as a shock. At the time a freelance writer struggling to pay the bills, Kidder had been inspired to write about technology after the protests surrounding the opening of the Seabrook nuclear reactor in 1976. Over a beer, his editor at The Atlantic, Richard Todd, suggested he look into computers. Todd knew someone in the business: his old college roommate, Tom West.
Kidder took a sailing trip with West, and after hearing about Eagle, came to the basement of 14A/B to see the project firsthand. The day he showed up, he says, Alsing immediately shunted him off to the cafeteria. "There was this feeling of paranoia," remembers Kidder. "Then he started telling me these stories. I thought he was just talking about making molded plastic boxes - the most boring thing in the world. But they were so passionate about it." The Eagle engineers' passion was nurtured inside - and perhaps in spite of - a company with a reputation for brash attitudes and a culture rife with dictatorial management and cutthroat competition. This spirit enveloped the competing Eagle and FHP, and in West, the battle revealed a true talent for a brand of fierce corporate gamesmanship. Kidder describes West's tirade about a department he believed was holding up the Eagle: "'I'm gonna detonate those guys,' said West in a flat, calm voice, as if he were planning a business trip. Then he promised to 'waste 'em.' He added, 'We'll string them up by their toes.'" Such viciousness toward outside threats may have been understandable. More mysterious was his aloof management style within his own team. To the younger engineers, he came off as cold, uncaring; Soul relates how he would ignore greetings from Hardy Boys and Microkids when he passed them in the hall. "I would never try to defend that I knew what I was doing," West says now, looking back. He was "shy," he suggests, or maybe "just embarrassed." "It really was a thinking game," he finally says, "and somebody had to keep a clear head about what the overall goal was. To do that requires a fair amount of insulation and isolation. Otherwise, you just get caught up in the chatter." But perhaps the most convincing explanation for West's brutal aloofness is postulated in Kidder's book: West was attempting to provide the team with a scapegoat, someone to blame for their cramped conditions and unrealistic schedules.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It was West's corporate agnosticism, Alsing says now, that drove the project and ultimately Alsing himself. "People expect their company to do the right thing, and usually they're disappointed," he says. "Tom expected the company to do the wrong thing, and he wasn't disappointed at all." West was protecting the team from his lack of faith, Alsing says, describing West's philosophy. "When your company doesn't do the right thing, you manipulate it until it does." "Somebody's got to dig ditches. But it's a lot more fun to dig ditches where nobody else has dug one before." "We used to complain to Tom about working conditions," laughs Ken Holberger, a manager of the Hardy Boys. "One time it just got really hot, the ventilation was terrible, and the offices were too crowded. He'd look at us and say, 'Well, look how good you're doing! Tell me what I'm doing wrong!' Which was certainly a cynical thing to say, but it was funny at the time." West's strategy, if cynical, was effective, and the team somehow brought the machine to life. The FHP had fallen hopelessly behind schedule, and the Eagle - although it took longer to complete than the year West had promised - became more than "insurance." It was Data General's only hope to rescue itself from permanent 16-bit obsolescence. "Tom West took it upon himself and Steve Wallach [Eagle's designer], as a personal thing, to prove that they could outdo those guys in North Carolina," says Ed Zander, director of marketing for Eagle and FHP at the time and now president of Sun Microsystems. "It got very nasty. At the end of the day, when it came out, the Eagle saved Data General - but Data General was never really saved. With three years of lost market share to DEC, it never really recovered." The machine, officially named the Eclipse MV/8000, was announced to the public in April 1980, in an afternoon ceremony in New York City. A few members of the team got to go and bask in their roles as company saviors, but the feeling was short-lived. Because West had shielded them from the politics of DG - something many wouldn't discover until reading Soul - the Eagle team was unprepared for the backlash the project created. They believed they had rescued DG, says Microkid Blau, but "unfortunately the rest of the company didn't feel that way, so there was a lot of animosity." The FHP team, for one, felt betrayed when its machine was canceled. And a team that worked in secret - with a crafty leader who bucked the system - could be highly effective, but it also could be dangerous to the powers that be. A new vice president of engineering had taken over at DG, replacing the pro-Eagle Carl Carman. The new VP was openly hostile to a group he believed had purposefully defied the interests of the company - "neglecting to point out," Wallach says now, "that without Eagle there would not have been a Data General." The Eagle group was broken up and scattered to various projects, and West was shipped off to Data General's Japan office before a single MV/8000 was sold.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg By the time Soul was published a little more than a year later, greeted with a glowing review in The New York Times, many in the Eagle group had already left Data General or were about to leave. Some wanted to start their own ventures. Some were burned out. Others were young and simply ready to move on to the next thing. Dissatisfied with the lack of recognition and opportunities at a company that their herculean effort helped save, and frustrated by the politics of conflict that pervaded DG, they saw little reason to stay.
Holberger still describes the Eagle drama in terms of an old Western, as he did to Kidder 20 years ago. "I felt like the team members were gunfighters who were brought into town to solve some problem," he says. "They shot the place up, and they solved the problem. And then the town had to figure out what to do with them afterward. Which was mostly to get rid of them." Perpetual Motion Holberger has noticed that there is almost no one in the basement involved in CPU design who is over 35. What happens to old CPU engineers? Holberger is 26 now, and though not exactly on his deathbed, he is curious about what a computer engineer does "afterward." When Data General ran the Eagle gunslingers out of town, most of them took different routes to a similar destination: the next project. Having successfully created a machine - seen it through from bare wires and circuits to working computer - they were ready to sign up and do it again. Even after the burnout and the lack of recognition at DG, they left seeking projects as intense, if not more intense, than Eagle. They often found them. And for all the gruffness of West's management style, none of the Eagle vets look back on the project with anything but fond memories.
Ken Holberger and Chuck Holland, a Microkids manager, left DG in the early '80s and traveled similar career paths. After bouncing around at other hardware companies for a few years, the two founded Epoch Systems, where they designed combination optical and magnetic disc storage. "Ken and I struck out into the deep West," says Holland, describing the pioneer spirit of their early startup efforts. When they sold the company for a pile of cash in 1992 - ironically to EMC, which later acquired DG - neither needed to work again. Both do.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg On his third startup after Epoch, Holberger, at 46, has the luxury of picking and choosing his projects, the most recent being to serve as director of marketing at Vox2, which is working on a product that ties cell phones into a home telephone network. Holland, now 48, is back working full time for LiveVault, a network backup company he and Holberger founded seven years ago. "I've always been driven to create," he says. "And engineers want to create something and see it come to the end - the end is everything. Then, if you ever get there, you wonder what's next." "Engineers want to create something and see it come to the end - the end is everything. Then, if you ever get there, you wonder what's next." Few Eagle alumni have attained what is generally viewed as an engineer's corporate grail: a high-level management role at a large tech company. They have stayed close to the spark of technology, the thrill of projects, the intensity of creation.
"I had high hopes for a management career," says Carl Alsing, now 57. "The hope was that I could leverage my experience and judgment. That was disappointing, because at the lower levels of management where I ended up, whatever companies said they wanted me to do, they really wanted me to put out fires in the current product and delay any kind of innovation." Alsing figures more prominently in Soul than any Eagle architect besides West. Although in many ways West's inverse - tall and lanky, with a quiet, hands-on manner around the younger engineers - Alsing may have known the Eagle leader better than anyone else. When West first took over the Eclipse group, Alsing, as he says in Soul, went to work for him "largely because he felt that it would be safer to stand on West's side than not." "You see somebody like that and you say, 'I think I'll stay around and watch this and see what happens,'" he says now. "'Could this be right? Is this how the world is?'" Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg So when West left for Japan, Alsing didn't stick around. In late 1980, he moved to Silicon Valley to work at Tandem, an early entrant in the fault-tolerant computer business. Four years later, he jumped to a small startup and began developing optical character recognition technology. Since the mid-'80s, he has bounced around small companies in the OCR industry, mostly by choice and occasionally by downsizing. Despite an aversion to large companies, especially in an age in which he says corporate loyalty to employees is nil, he did a one-year stint at Xerox PARC beginning in 1995. Since then, he's worked as an independent contractor. "I admit what I'm doing now is more for the satisfaction of designing things myself," he says. "So maybe I can only do one man's work in a year, and I can't get 20 people to do some cool thing. But it's fun." For Alsing, recently signed on with MagnaWare, an OCR startup in Santa Cruz, California, the core desire is still to innovate, regardless of whether he's running things. "Somebody's got to dig ditches," he says. "But it's a lot more fun to dig ditches where nobody else has dug one before." His challenge has been to stay mobile enough to keep up with the pace of change. "You stay in a place too long, you miss out on new technology and new tools and new ways of doing things," he says. "I've seen friends who stayed too many years in something, and they always find a niche where they become a guru of something and manager of whatnot. And then when that activity ends and they leave the company or get laid off, they have no skills. In 10 years, you really are obsolete. The tools are gone, the vocabulary is different." This idea of perpetual movement in the face of looming obsolescence is a constant theme among the Eagle vets. Like Alsing, most of them had already glided into the next tech market by the time the minicomputer sector crashed in the mid-'80s. Some struck it rich with their own tech ventures, while others either never made the right play or elected to avoid the risks that startups pose. A few have stayed put at one company for 15 years or more. But all of them have been forced to adapt as Moore's law and the Internet redefined and rebuilt the industry time after time. "The technology keeps changing," says Ken Holberger, "and the people keep changing - to track it, to chase it, or to push it, depending on where you are on the curve." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Jonathan Blau is the only member of the team who left the high tech world, disillusioned by his post-DG jobs. He worked for a decade alongside a half-dozen other Eagle vets at a company called Alliant, based in Massachusetts and started by FHP alumni, and eventually found that he "did not perform well under the pressure. It was not as much fun; a terrible contrast to my years at Data General. DG did have that kind of rough edge to it, but we were told we were the heroes, we were going to save the company." Blau, a Microkid and Hardy Boy whose voice still crackles with excitement when he talks about solving the Eagle "puzzle," is now a junk bond analyst at Donaldson, Lufkin & Jenrette in New York City. After burning out at Alliant, he came back to his hometown and did some software development for an investment bank, gradually transitioning into an analyst role. Now 44 and content to study rather than build technology, he still sees parallels between the past and present.
"We'll hire kids out of school," he says, "and I'll see what they're going through, and think back to those times. It was such an intense experience, where we went through so many cycles of ups and downs throughout the creation of the thing." "We used to say for every year of experience at Data General, it's worth two years at any other place," adds Steve Wallach. "And you'll age four." Brooklyn-born, and in his mid-thirties at the time he became a manager on Eagle, Wallach was the technical mastermind behind the computer's processor. Kidder describes his eureka moment - how he constructed the processor's addressing scheme - in a chapter entitled "Wallach's Golden Moment." Portrayed as cheerful but volatile, the Wallach of Soul is a man with a photographic memory who wears cowboy boots and has a tendency to kick the hell out of his office wall when frustrated.
Wallach seems no more mellow at 55. But his cowboy boots, if not his Brooklyn accent, are more at home in the offices of Texas-based Chiaro Networks, where he is vice president of engineering. Outspoken and blunt, he has a roster of funny anecdotes about Soul, each of which he punctuates with a verbal wink like "if you follow what I'm saying" or "Do you get my meaning?" His epitaph, he says, should simply read, "Here lies a computer engineer." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg "Data General did have that kind of rough edge to it, but we were told we were the heroes, we were going to save the company." Wallach left DG in 1980, spending time in California before cofounding a next-generation "mini supercomputer" company called Convex in Dallas. He tried to get West to join, but while West liked the idea, he couldn't muster the enthusiasm. "He was just burnt," says Wallach. The company, successful for a few years, hit the wall quickly when the market was soaked up by workstations in the early '90s, and Convex was eventually bought up by HP in 1995. But by then, Wallach's reputation as a gifted hardware mind was already sealed. He went into what he calls semi-retirement (working only 40-hour weeks), dabbling in venture capital, consulting for the government's ASCI supercomputer projects, and serving on the Clinton administration's IT Advisory Committee.
Last year, when a friend from the venture world told him about Chiaro, a startup developing next-generation optical switches, he jumped at the chance to play a little pinball. But just as with Eagle, Wallach - who still rolls up his sleeves and does coding at Chiaro - isn't looking for accolades. "My motivation on Eagle had nothing to do with recognition," he says. "I wanted to prove that I could get something out the door. And I was right and the other guys were wrong. I'm not interested in notoriety or bullshit." He remembers getting a call a few years ago from a headhunter who was seeking a CTO for a "fast-growing Massachusetts company." "I asked him which one," recalls Wallach. "He says, 'We can't tell you.' I said, 'If you don't tell me the name of the company I'm hanging up.' He says, 'OK, the company is Data General. The job is to replace Tom West.' So I'm laughing for about a minute or two. He says, 'What's so funny?' He knew I worked at Data General and nothing else. And I said, 'Go read The Soul of a New Machine and you'll understand.' That's how I knew Tom West was retiring." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Playing Pinball "[DG vice president Carl] Carman says the company's in a lot of trouble if it's not there by April. Suppose I quit? I could just say, 'Fuck it,' and go ... I'm not gonna do the next machine. I'm gonna give somebody else a chance to fail. I'm gonna get totally out of computers." West stopped once in this long, unusually bitter monologue to say: "No, we wouldn't have a disaster. We'd back and fill." He seemed to be saying that he had to make himself believe that dire consequences would ensue if his team missed its deadline.
Of all the Eagle team, Tom West seemed the most unlikely candidate to be a Data General lifer.
Soul characterizes him as a wanderer, a former guitar player and folksinger who might rather drift from town to town than see another computer through the DG gauntlet. Although a master of corporate strategy, West seemed in some ways larger than Data General, too worldly for its confines. "He's not a company guy," says Alsing today. "Well, he wasn't a company guy." Kidder even writes in Soul, reflecting on West's time at DG: "Ever since he had gone to work for Data General, West had been talking about quitting. Someday he'd wander off." He never did.
In 1980, with the Eagle project barely completed, DG's upper management offered him a series of what he calls "unpalatable options"; Japan seemed the most promising. While Kidder hints in the book that the transfer was just what West needed, West today says he was "effectively fired." "He got the shaft," concludes Wallach matter-of-factly. But, says West, "I thought, 'Well, this will keep me alive for the moment.'" Even two decades later, he laments that because of his departure he wasn't able to protect the Eagle kids, to prepare them for the bitter end of the project they'd thrown their lives into. "Their legacy was the book," says West.
The MV/8000 itself managed to keep DG afloat in the minicomputer business, selling briskly for several years. West returned from Japan after a year to find the machine a success. Yet without the book, he doubts the Eagle achievements would ever have been recognized. "The people who shot the revolutionaries realized that there was an imprint," he says, "and that they couldn't rewrite history." History intact, he returned to the job of technical manager and was quickly promoted to vice president and eventually senior vice president of engineering - "senior VP in charge of not much," he calls it. "They decided they didn't want me around people, so I would just come up with ideas," laughs the man who blustered in Soul about "detonating" fellow employees and stringing them up by their toes.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg By 1983, Data General was floundering again and the computer landscape was changing radically. Just as minicomputers had captured the market from mainframes by being smaller and easier to use, PCs and workstations were crashing the minicomputer party. In Japan, West had designed the DGOne, the first full-screen laptop, in an attempt to push the company into the growing PC market. But saddled with proprietary software and a slow processor, the project was ultimately canceled. No longer the brash upstart of its heyday, DG failed to adjust its course to the prevailing market winds.
Every DG veteran, from Tom West to Ed Zander to Joel Schwartz, current head of the Data General division at EMC, recites a litany of disruptive technologies that DG developed but failed to exploit as a way of explaining why the company never became a powerhouse. There was FHP's ahead-of-its-time network-computing architecture. There was a laser printer developed in the late '70s. There was the DGOne. There was a thin Web server developed by Tom West in the mid-'90s. The list goes on.
West blames DG's management, and its inability to recognize or reward the company's engineering talent, for the failures. "They like to talk in terms of missing the different waves of technology," says West, "but a well-managed company doesn't do that. It was a very top-down, autocratic, turn-of-the-century mill-owner kind of management mentality. It could only grow to a certain size, because nobody trusted anybody." By the late '90s, Data General seemed a company that had been granted immortality but had neglected to ask for perpetual youth. Revenue stagnated at $1 billion for over a decade, while profits sank and the stock plummeted from a high of 81 in 1983 to single digits by 1990, before edging back up to 10, where it hovered until 1999, when the company was bought by EMC. DG had held on, though, while the high-flying minicomputer outfits of the 1970s, with names like Wang Laboratories and Prime Computer, shuttered or sold out to outfits closer to the leading edge. Compaq, underscoring the PC's decimation of minicomputers, snapped up Digital in 1998.
All the while, West endured at DG, although he often felt more like a showpiece than an innovator. "There was still the notion that I was sort of a necessary evil," he says. "They needed me to sign books and go on sales calls. They were much happier with me as a figurehead than as an action figure." The Soul of a New Machine and the Eagle had made him something of a tech icon. "Whenever we announced something, Tom was always involved," says Joel Schwartz. "He added credibility. We were always able to get a greater attendance from analysts when we rolled out Tom." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg West continued to fight for new ideas, and DG even mustered a mid- '90s turnaround of sorts by trimming costs, laying off thousands, and shifting focus to the successful Clariion data storage products that West conceived. He then set to work on saving DG again, turning to the Internet in a last-ditch effort to develop a technology that would vault the company into the next high tech era. The answer, according to West, was a thin client server, the kind of thing small businesses could use to get connected. It was an idea ahead of its time, and again DG failed to capitalize. After an initial market run garnered less than spectacular sales, the project was scaled back. Today, servers like West's are a huge and growing business.
West struggles to explain why he stuck around to watch the sunset of DG, rather than hitch his fortunes to one of the countless startups or industry leaders that tried to lure him away. "I'd much rather be a big fish in a little pond," he offers at one point, "than someone like Gordon Bell, who went to Microsoft and disappeared." Another time, he says, "You could do new products and companies within the company, rather than shag some venture capitalist and kill yourself for five years." To be an entrepreneur, he says, "you have to be interested in networking, even with fools." Still, most of the Eagle team wonders what kept him at Data General. Steve Wallach is sure that it was in West's genes - his father and grandfather both spent their whole careers at AT&T. Others suspect the Eagle project and its aftermath, in which West ended up divorced, may have drained his energy. At the end of Soul, Kidder describes West as losing weight and sleep over the Eagle. "He put a lot into it," says one Eagle engineer today, "and it took a toll on his personal life." Others who worked on the Eagle insist that for West, staying put at DG wasn't what it might have been for a more ordinary guy; it wasn't the same as being stuck. "Just because Tom stayed at one company, that doesn't put him on the spectrum of the average engineer," argues Chuck Holland. "He did different projects and worked in different sections of the company. It wasn't a static career at all." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg West, Alsing believes, somehow turned the tables on obsolescence. "I think he felt that he knew how to work with the company, he knew how to get them to do what he wanted. So I don't think he ever felt frustrated, ever just said, 'I can't get anything accomplished here. I have to go somewhere else.'" Alsing's rosy assessment, however, didn't hold for the duration of West's tenure. West eventually discovered that he was, in practice, no longer an engineer. DG had become just another job. "I did usually prevail," he says. "But I began to think, 'It's too hard. This isn't a technology job at all. It's about moving around these roadblocks to try and do things that are pretty sensible. You're solving these same problems over and over again that are really people problems. They have nothing to do with electrons.'" By the time he retired, West found that Data General wasn't even listening to his advice on Internet strategies. "I thought that was kind of silly," he says, laughing. "Because I'd spent all my time and energy trying to figure out how this Internet thing could be used by an old minicomputer company, and they just didn't ..." He trails off, then says softly, "didn't care." The Zen of Soul Many looked for words to describe their true reward. They used such phrases as "self-fulfillment," "a feeling of accomplishment," "self-satisfaction." [Hardy Boy] Jim Guyer struggled with those terms awhile with growing impatience. Then he said, "Look, I don't have to get official recognition for anything I do. Ninety-eight percent of the thrill comes from knowing that the thing you designed works, and works almost the way you expected it would. If that happens, part of you is in that machine." West doesn't play much music these days - arthritis in his hands hampers his guitar playing. But happily remarried and living in Westport, he's plenty busy sailing, fishing for striper, and keeping tabs on the industry via the Web. He seems mostly content to be done with the high tech game, and proclaims no desire to return to it. Life is full. "I've seen a lot of burnout," he says, "but the sadder thing I've seen is a lot of people who reach 65 and find that there's nothing in the world they like to do. That's really sad, because they've worked their whole lives, and then the whole meaning of things goes away." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg He also sounds the Moore's law theme. "High tech careers today," he points out, "require a great deal of planning. You can be building optical switches today and be on top of the market. But at some point, optical switches are going to be like modems - a dime a dozen - and then you're going to have to do something else. So you should realize that it might be more healthy to be involved in different things." West cultivated his own eclectic interests over the years and has remained friends with Kidder. He grumbles that he's been trying for months to get him down to Westport for a sailing trip. Kidder, at 54, is at work on his fifth book since Soul, this one based on his July story in The New Yorker story about a Harvard-educated doctor working in Haiti. Other than keeping up with his friend West, he says he "almost made a fetish out of not following the computer industry." But he marvels at the pace of change since his days in the basement of building 14A/B. "If you had told me in 1981 that Digital and Data General wouldn't exist today," he says, "I would have said you were out of your mind." Kidder sold the movie rights for Soul to Columbia Pictures in 1982, and the studio sent Kurt Luedtke, winner of a best screenplay Oscar for Out of Africa, to DG to research the script. "One day he flew in to town and interviewed us all, while consuming vast quantities of scotch," recalls Chuck Holland. "He kept asking if anything exciting happened. 'Well, yeah,' we said, 'remember when a board burned up?' It's so silly that none of us thought to make up something juicy. Needless to say, there was no movie." Even without an accompanying Hollywood blockbuster, the book has seen remarkable success. Translated into a dozen languages, today it's required reading in top business schools and universities as a case study in everything from effective project management to the exploited capitalist worker. Over the years, as minicomputers landed on the scrap heap and Data General faded, Soul continued to fascinate readers who found some kernel of truth in what Kidder captures about the intensity of the working world, something that transcends high tech.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg "It's got a Zen characteristic," says West. "It's not a cookbook for building computers. It's not a cookbook for good management strategies. Why did this book strike a chord with such discordant people? I'm not sure I know. Tracy can't tell you. It has something to do with work, and dreams, and why people do it." Every Eagle veteran recalls encountering readers, from washing-machine repairmen to teachers, who could relate to the book - and countless engineers who were inspired by it. Data General, meanwhile, never hesitated to wring every drop of publicity from Soul 's success, despite the fact that most Eagle alumni felt thoroughly unrewarded by DG. The company handed out copies of the book to scores of potential clients and recruits over the years, and even mentioned it in one of its annual reports.
Something in the use of Soul as a publicity tool, however, defies everything that went into the Eagle project. The engineers, after all, never sought a record of events, nor did they promote their connection to the book over the years. Although happy to be recognized, all of them pin the book's success squarely on Kidder's storytelling ability, not their own efforts to create a long-outdated computer. For them, the goal was to finish the machine so they could sign up again, and get on with their real business - technical creation.
Back in Westborough, West was often asked to autograph copies for clients and VIPs. It irritated him. "It was Tracy 's book," he laments. Signing Soul triggered a self-denial not unfamiliar to colleagues like Alsing and Wallach who have watched him lead. "I kept trying to point out to people that this is a book.
Tracy won the Pulitzer Prize. I didn't win the Pulitzer Prize. And they didn't seem to always get it." Joel Schwartz recounts a time when West flatly refused to sign books promised to a group of 30 visiting Korean clients and dignitaries. "Tom had a raggedy side," remembers Schwartz. "He was having one of those days, and he didn't want to sign them. I called him, I pleaded with him. But he wouldn't do it." Perhaps it was this same obstinate focus and proclivity for privacy that not only drove West to create the Eagle but also to stay at DG for the next 20 years. Schwartz continues: "So I said there's only one thing to do. I brought them over and signed them all myself: 'Best wishes, Tom West.'" PLUS Souls, Lost and Found Contributor X Topics magazine-8.12 Gregory Barber Will Knight Kari McMahon Andy Greenberg Brendan I. Koerner Matt Kamen Amit Katwala Megan Farokhmanesh Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,057 | 2,021 |
"Sid Meier and the Meaning of “Civilization” | The New Yorker"
|
"https://www.newyorker.com/books/under-review/sid-meier-and-the-meaning-of-civilization"
|
"Newsletter To revisit this article, select My Account, then View saved stories Close Alert Search The Latest News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Puzzles & Games Video Podcasts Goings On Shop Open Navigation Menu Find anything you save across the site in your account Close Alert Under Review Sid Meier and the Meaning of “Civilization” By Neima Jahromi Illustration by Edward Steed Save this story Save this story Save this story Save this story Sid Meier is famous for creating the video game Civilization. He’s also known for having his name on the box. Meier released Civilization thirty years ago this month, after developing it with Bruce Shelley, a veteran board-game designer. The pair were inspired by the illustrated history books you might find on a middle-school library shelf, and by titles like Seven Cities of Gold (1984), a video game of Spanish conquest created by the designer Danielle Berry. In Civilization, you start with a covered wagon on a map that is largely obscured. You found a city. You learn metalwork, horse riding, feudalism, democracy, and diplomatic relations. Eventually, the rest of the world is revealed—a patchwork of nations. You can dominate your neighbors or strive to outshine them. History rolls on.
Civilization didn’t mark the first time Meier’s name appeared on a box. In 1987, we got Sid Meier’s Pirates!, in which you sail your way across the Caribbean, evolving from a winsome privateer to a peg-legged Blackbeard. In 1990, Meier’s earlier collaboration with Shelley resulted in Sid Meier’s Railroad Tycoon, a construction simulator that spawned a slew of copycats. And then, in 1991, with little marketing fanfare, Civilization appeared. Players realized that they had found a gem. The Sid Meier stamp exploded, popping up on Sid Meier’s Gettysburg!, Sid Meier’s Alpha Centauri, and Sid Meier’s SimGolf. There were sequels to Civilization, which Meier had little to do with. We’re now on Sid Meier’s Civilization VI. His name is still on the box.
The latest rectangle to bear his name is not a game but a book: “ Sid Meier’s Memoir!: A Life in Computer Games ” (W. W. Norton). It provides a whistle-stop tour of the video-game industry as it evolved across Meier’s four-decade career. Today, we swim through a digital soup made by machines that were developed, in large part, to play games. Graphics processors designed in the nineteen-nineties for first-person shooters became useful, a decade later, to the developers of the neural nets that power our social-media platforms. Many of the people who helped create our virtual environments cut their teeth by making and playing video games. “I’ve been playing Civilization since middle school,” the Facebook C.E.O., Mark Zuckerberg , wrote in a post on his Web site. “It’s my favorite strategy game and one of the reasons I got into engineering.” Like Meier, Zuckerberg signed his software: when thefacebook.com launched, in 2004, it was “a Mark Zuckerberg production.” Facebook is now a much larger enterprise, as is Civilization. The game is put together by hundreds of hands, from producers, designers, illustrators, and coders to marketers, play testers, and skin-modding fans. Even Meier’s memoir is the result of a collaboration with Jennifer Lee Noonan, a former sound designer for video games. A growing pile of video-game histories—such as Tristan Donovan’s “ Replay ” and the two-volume “ The Ultimate History of Video Games ,” by Steven Kent—suggest that the medium has always had collective effort at its heart, from its academic beginnings to its ascent into everyday life. In Meier’s memoir, we discover that he was a good game-maker when he fought this essential fact, but that he became great when he learned to embrace it.
Meier came to computers just as computers were coming to the world. In 1971, the year Meier entered the University of Michigan to study computer science, the first coin-operated video games appeared in American bars, stealing attention from pinball machines and pool tables. One of those games, a spaceship-fighting simulator created by a pair of electrical engineers, Nolan Bushnell and Ted Dabney, was dubbed Computer Space. Computer Space was a clone of Spacewar!, a 1961 game that a group of M.I.T. students devised for their university’s Buick-sized PDP-1 computer. One student suggested the concept, another prototyped the inputs, and the rest of the group critiqued, patched, and improved it. The code made its way from campus to campus, spreading the earliest seeds of video-game design. In 1975, Meier, a member of the game’s target audience, graduated. He found a job networking cash registers in Maryland, and started making a “Star Trek” game while he was bored at work. “I even added small beeping sound effects,” he writes. The game quickly caught on in the office. “Small beeps ricocheted through the halls as a sort of work-abandonment klaxon of shame.” Bushnell and Dabney, meanwhile, formed a company in Los Gatos, California, and called it Atari. At the time, an arcade cabinet played exactly one game, but, in 1977, Atari released a home console system that let you play different games on a single machine. Two years later, the company released the Atari 800, a console computer that came with a keyboard, four joystick inputs, and, most important, a programmable cartridge that allowed Meier to make his own games. In 1980, he created Hostage Crisis, a shoot-’em-up inspired by the diplomatic standoff in Iran. A giant face dubbed the Ayatollah sat in one part of the screen and shot missiles at the player. Meier proudly showed the game to his parents, resulting in a scene ripe for psychoanalysis: My father, especially, was a connoisseur of machinery and gadgets, so I had assumed he would find programming as interesting as I did. Instead, I received a terse reminder that his own career as a professional typesetter was being phased out of existence by this newfangled thing I’d brought into their living room. . . . He stayed in the room, at least, watching with languid wariness as I connected the Atari to the television and handed my mother the unfamiliar joystick.
She was excited in the way that all mothers are excited for their children’s accomplishments. . . . Soon, however, my four-color rendition of the Iran hostage crisis had her frowning in concentration, and letting out small cries of “Oh no!” at each new threat that headed her way. As the game progressed, she became more and more rapt, clenching her jaw and dodging missiles with her whole body. Suddenly, she dropped the controller and turned her face away.
She couldn’t play anymore, she told me. Her heart was racing and it was all too much.
At that moment, Meier realized his passion. “If great literature could wield its power through nothing but black squiggles on a page, how much more could be done with movement, sound, and color?” he writes. “The potential for emotional interaction through this medium struck me as both fascinating and enticing.” Meier’s offering wouldn’t have been welcome in the American big leagues. Atari, the leading name in video games, was extremely shy of controversy. The avatars onscreen were often just rectangles or blobs, and the concepts had to stay within the bounds of dinner-table politesse. In one game, a Cold War battlefield became a fictional alien planet; in another, the Holy Grail turned into an “enchanted chalice.” Atari also forbade its coders from signing their work, even though, as Donovan writes in “Replay,” its developers “were starting to see themselves as the artistic pioneers of a new form of entertainment.” In 1980, an Atari engineer named Warren Robinett decided to make a little mischief. In a secret room within his sword-and-sorcery game Adventure, he placed a script—“Created by Warren Robinett”—that appeared like a winking medieval acrostic.
Although Meier’s games were ill-suited for Atari, the cathedral was about to collapse, anyway. In 1979, several star Atari programmers, frustrated by their work not being publicly credited, created their own company, Activision, to make games for the Atari console. Atari sued Activision and lost, unleashing a torrent of independent, third-party video-game developers. (Donovan credits the flood of cheap Atari games, some of them poorly designed advertisements for things like dog food, with the industry’s decline in the United States.) Meanwhile, Meier was on the rise. Like a student sketching faces from the statuary at the Met, he learned his craft through imitation. He often made unauthorized clones of Space Invaders and Pac-Man, stuffing the games into plastic baggies and trying to sell them through his local electronics store.
Though Meier feigns remorse now (“ ‘Adaptation’ is such a flattering word. So much nicer than ‘copyright infringement’ ”), his early approach toward intellectual property echoed the attitudes of academically trained programmers. “Signing code was thought of as arrogant,” the digital librarian Brewster Kahle has said of his time at M.I.T. in the nineteen-eighties. And as the reporter Clive Thompson makes clear in “ Coders ,” his illuminating history of computer culture, anti-authoritarian hackers and coders of the era saw software as “an intellectual barn raising,” a collective effort. “ Owning an algorithm you’d written,” Thompson writes, “seemed as nuts as ‘owning’ the concept of multiplication itself, or constitutional democracy, or rhyme.” But Meier and his cohort were going a different way. In 1982, Meier created a driving game, Formula 1 Racing, and the publisher put his name on the box. This suited him. “It seemed to me that computer code was just as elegant as any literary prose,” Meier writes. That year, Meier founded a company with Bill Stealey, a former colleague and veteran Air Force pilot. They set up shop in Stealey’s basement and called their enterprise MicroProse. Stealey had a business acumen that Meier lacked. He schmoozed at video-game trade shows and ginned up demand by calling electronics stores, assuming a fake identity, and asking if they had MicroProse products in stock. He also pushed Meier to put out a steady clip of war games—Spitfire Ace (1982), NATO Commander (1983), F-15 Strike Eagle (1984)—which Stealey vetted for military accuracy.
Stealey’s big idea, though, was to turn Meier into a brand. In 1984, he staged a photo shoot, seating the mop-topped coder in front of a computer, putting a joystick in his lap, and surrounding him with cartoonishly labelled bags of money. “But Bill had decided that even this was too subtle,” Meier recalls. “Just before the photo was taken, he had climbed onto my desk to hang glittering golden dollar signs.” Stealey fashioned Meier as a folk hero for other programmers. “In order to lure the smartest and most creative talent in the industry,” Meier writes, “he wanted to promote the message that we treated our designers with the admiration and respect they deserved.” The video-game auteur had arrived.
Meier goes to pains to prove that he in no way encouraged this self-promotion. But he did have one prima donna-ish quirk: he wanted to do everything himself. Like many talented programmers at the time, he preferred to disappear into a fugue of coding and return with a gleaming piece of software. Until Pirates!, Meier, a music fanatic who owns dozens of guitars, had done the sound design on his games himself. He also rendered his own art until 1985, when Stealey hired an illustrator for Meier’s submarine-warfare game Silent Service. “I was, to be honest, a little offended,” Meier recalls. “Sure I was no Van Gogh, but I had been doing our game art for years and felt like I was pretty good.” Meier surrendered when he saw the illustrator’s results. “His 3D perspective was truer, his color contrast was livelier, and his captain looked human,” Meier writes. “It was better in basically every possible way a work of art could be better.” By the late eighties, game design had become much more collaborative. A century-old Japanese toymaker, Nintendo, had entered the market, led by its own auteur: the banjo-playing Shigeru Miyamoto , who created the Legend of Zelda and Super Mario Bros. series. Even Miyamoto had help; his worlds were enriched by the Tolkienist storytelling of his colleague Takashi Tezuka, and, as Melissa Wood and France Costrel’s Netflix series “High Score” shows, by the many illustrators and sound designers who touched the games. Meanwhile, Meier had started working with Shelley, the board-game designer, who gently nit-picked Meier’s sprawling world-building. In early versions of Railroad Tycoon, for instance, bridges would randomly wash out in floods, just like in real life. The hazard turned out to be more punishing than interesting. “Bruce reminded me of one of my own axioms of game design,” Meier recalls. “Make sure the player is the one having fun.” Game designers want to impress the players, Meier knew, but players want to impress themselves. “The game isn’t supposed to be about us,” Meier—of Sid Meier’s Civilization—writes, without irony. “The player must be the star, and the designer as close to invisible as possible.” But the player was about to ascend in ways that Meier did not anticipate. Soon after Meier and Shelley circulated their prototype of Civilization, other MicroProse developers began playing the game and hammering on Meier’s door. “What if aqueducts prevented fires, granaries prevented famine, city walls prevented floods?” he recalls them saying. “What if lighthouses increased your navy’s speed, but suddenly became obsolete after the development of magnetism?” Meier incorporated many of these ideas and shipped the game out, only to be buried again under fan letters with suggestions about Aztec bronze-working or the speed of trade caravans. “ Civilization brought out the inner game designer in everyone,” Meier writes.
These video-game enthusiasts were about to leap into the car and drive. By 1996, the public Internet was in full swing, and Meier had handed over Civilization, and his name, to other coders. Brian Reynolds, one of the lead designers on Civilization II, followed the example of the first-person shooter Doom, and built a back door that allowed fans to pack new sounds, art, and even mechanics into the game. Meier fretted. “They would probably be terrible at it, I thought, and blame us for their uninspired creations,” he writes. “And if by chance they did happen to be good at it, then all we were doing was putting ourselves out of a job.” The older game designer was now the uneasy parent, looking on as his children ran amok. But Meier ended up seeing that he was “wrong on all counts,” he writes. “The strength of the modding community is, instead, the very reason the series survived.” And, it’s why the label “Sid Meier” lives on, too.
These player communities transformed the rhythm of game design. The task of making today’s blockbuster games—the zombie-apocalypse saga The Last of Us, for example—doesn’t square with the one-man-band approach that Meier and his Atari peers used half a century ago. The journalist Jason Schreier recently catalogued this turn in his book “ Blood, Sweat, and Pixels.
” Again and again, Schreier watches platoons of illustrators, coders, sound designers, and producers struggle in the trenches for years before a game’s launch, and then scramble for years afterward to meet player demands with a fog of patches and updates.
This is the way of all software in the twenty-first century. It’s how social-media developers, in particular, approach their craft, with much of a product’s sculpture and polish arriving, for better and worse, after it has entered our view. In 2006, a team of developers at Facebook rolled out the News Feed, which made a mosaic of content out of your friends’ profile pages. As Thompson points out in “Coders,” many users, feeling overexposed, protested the change. Zuckerberg apologized, and the company made a privacy patch to address the concerns. Fifteen years later, the News Feed is still around, but it’s a bit like the ship of Theseus: they’ve been patching it ever since.
With painting or prose, it has been said that a work is completed, in some metaphorical sense, by its encounter with an audience. With code, this circuit is literal. Programs and platforms are put on display, then tweaked because of error reports and user data; in multiplayer games, the activity of other players animates the experience. It is easy to say that this diminishes the artist-developer. But what the history of video games reveals is the story of all art. Our accounts often thrive on the vision of singular minds, even though every great work relies on the sweat, luck, and talent of many people, each inflecting one another in a continuous loop. When Sid Meier began tinkering with a new game, thirty years ago, his hope was that players would see themselves in his version of our planet. It was when the audience could watch one another tinker, too, that the planet became a world.
New Yorker Favorites How we became infected by chain e-mail.
Twelve classic movies to watch with your kids.
The secret lives of fungi.
The photographer who claimed to capture the ghost of Abraham Lincoln.
Why are Americans still uncomfortable with atheism ? The enduring romance of the night train.
Sign up for our daily newsletter to receive the best stories from The New Yorker.
More: Video Games Book Reviews Technology Massachusetts Institute of Technology Computers Books & Fiction E-mail address Sign up By signing up, you agree to our User Agreement and Privacy Policy & Cookie Statement.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
The Sporting Scene By Simon Akam Our Columnists By Benjamin Wallace-Wells Our Columnists By John Cassidy Q. & A.
By Isaac Chotiner Sections News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Crossword Video Podcasts Archive Goings On More Customer Care Shop The New Yorker Buy Covers and Cartoons Condé Nast Store Digital Access Newsletters Jigsaw Puzzle RSS About Careers Contact F.A.Q.
Media Kit Press Accessibility Help © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
The New Yorker may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Facebook X Snapchat YouTube Instagram Do Not Sell My Personal Info
"
|
2,058 | 2,022 |
"Robot Vacuums Still Haven’t Floored Me | WIRED"
|
"https://www.wired.com/story/robot-vacuums-must-improve-rant"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Simon Hill Gear Robot Vacuums Still Haven’t Floored Me Photograph: Darya Danik/Getty Images Save this story Save Save this story Save As I ran around the house picking up discarded cat toys and odd socks, I began to feel a nagging sense of doubt. I knew that no matter how hard I worked, I would soon receive a distress call from our robot vacuum, Gizmo IV, who always gets stuck in the same spot under the couch. After Gizmo finishes, I then have to pick hair out of the carpet, which Gizmo expertly clumps but never sucks in. After that, I could look forward to a face full of dust as I emptied its tiny, barely-half-full bin (despite Gizmo’s protests that it can hold no more).
In fact, the week after pitching this very article, I came downstairs to find foul-smelling skid marks across the floors. Our youngest cat, Luna, often poops next to the litter tray instead of inside. At first, I feared an infection had prompted her to wipe all over the house. But following my nose revealed the terrible truth. A machine designed to spread poo could not have done a better job. I may never recover from the horror. While picking pieces of my cat’s fishy feculence from Gizmo’s tire tread with a toothpick, I began to wonder why I got a robot vacuum in the first place.
When they first trundled onto the scene, more than two decades ago, robot vacuums were prohibitively expensive and not very good at their job. But feature lists have swollen, and prices have fallen. Around 14 percent of Americans own a robot vacuum , and 13 percent intend to buy one, which would press around 30 million into service in American homes.
Raves from friends convinced us to purchase our first robot vacuum, a Eufy Robovac 11 that we dubbed Gizmo I. The promise of a machine toiling while we sat with our feet up was enticing. But I have come to believe that the ideal robot vacuum owner lives in a single-level home with hardwood floors and no pets or children. Our mostly carpeted, two-story household contains one balding cleaner (me), three messy, long-haired humans, and two messy, long-haired cats. Gizmo had as much chance as King Canute struggling against the tide.
No one told me how much maintenance they need. It’s not enough to empty the bin. You must regularly unscrew rollers, gently clean plastic covers, unspool hair, change filters and brushes, polish metal charging contacts—the list continues. Fail to keep up with regular maintenance, and your robot vacuum will cease to perform.
The average life expectancy of a robot vacuum in the Hill house is 10 months. Gizmo I lasted nine before it began to turn uselessly in circles; Gizmo II, a Eufy Robovac 11S, managed eight and then declined to turn on; and Gizmo III, a Trifo Max, made it just six before refusing to hold more than 15 minutes of charge. Gizmo IV is an iRobot Roomba 965, and the first to go beyond a full year.
With all my moaning, you may wonder why I persist with a robot vacuum at all. But as with most labor-saving devices, from the dishwasher to the blender, once you use one you never go back. Even a budget robot vacuum saves you some time. Gizmo nails the post-breakfast cleanup—I’ll never have to sweep up another stray Rice Krispie again. It also keeps our hardwood hall free of mud and dust and picks up stray cat litter.
As Adrienne So, our resident robot vacuum expert , pointed out, manufacturers have been working on the problems I encountered for a while now. She reviewed a botvac that could recognize pet poop years ago. Ecovacs, Roborock, and iRobot have done a lot with obstacle identification and navigation. We have been pushing self-emptying bins for a few years.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Would I give up on Gizmo? Never. I’ve also grown to love the self-satisfied tune it plays on the odd occasion it makes it home to the charging base after a successful clean. Before you give up on yours, a quick Google search might help you diagnose your ailing robot vacuum. It might just need a deep clean or a replacement part. You will not believe how much hair can get clogged inside one of these things until you indulge in a little exploratory surgery.
Most of our issues were likely caused by spotty maintenance and our modest budget. But if you’re considering one of your own, my advice for interested shoppers is to read our guide to the best robot vacuums , save up for a decent model, and be aware that no matter how expensive it is, there will always be spots it cannot reach and obstacles it cannot overcome. We live in a fallen world, and Gizmo is just one more imperfect part of it. Someday, perhaps, they will make a model that can tackle stairs.
Special offer for Gear readers: Get a 1-Year Subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
📩 The latest on tech, science, and more: Get our newsletters ! Sober influencers and the end of alcohol For mRNA , Covid vaccines are just the beginning The future of the web is AI-generated marketing copy Keep your home connected with the best wi-fi routers How to limit who can contact you on Instagram 👁️ Explore AI like never before with our new database 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Contributor X Topics robot vacuum cleaning smart home rants and raves Shopping Adrienne So Julian Chokkattu Adrienne So Simon Hill Eric Ravenscraft Julian Chokkattu Jaina Grey Jaina Grey WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,059 | 2,022 |
"Amazon's iRobot Deal Would Give It Maps Inside Millions of Homes | WIRED"
|
"https://www.wired.com/story/amazon-irobot-roomba-acquisition-data-privacy"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Khari Johnson Business The iRobot Deal Would Give Amazon Maps Inside Millions of Homes Photograph: Zuki/Getty Images Save this story Save Save this story Save Application Hardware Robotics Surveillance End User Big company Sector Consumer services Source Data Sensors Technology Machine vision Robotics After decades of creating war machines and home cleaning appliances , iRobot agreed to be acquired by Amazon for $1.7 billion, according to a joint statement by the two companies. If the deal goes through, it would give Amazon access to yet another wellspring of personal data: interior maps of Roomba owners’ homes.
iRobot got its start building robots for the US military , but 20 years ago added consumer vacuums to the mix. (It spun off the defense business altogether in 2016.) Those Roombas work in part by using sensors to map the homes they operate in. In a 2017 Reuters interview , iRobot CEO Colin Angle suggested the company might someday share that data with tech companies developing smart home devices and AI assistants.
Combined with other recent acquisition targets, Amazon could wind up with a comprehensive look at what’s happening inside people’s homes. The ecommerce giant acquired video doorbell company Ring in 2018 and Wi-Fi router-maker Eero a year later.
Speakers and other devices with AI assistant Alexa can now control thousands of smart home devices, including Roomba vacuums. And Amazon plans to acquire primary care chain One Medical in a $3.49 billion all-cash deal, which if approved would put the health data of millions in its keeping.
“People tend to think of Amazon as an online seller company, but really Amazon is a surveillance company. That is the core of its business model, and that’s what drives its monopoly power and profit,” says Evan Greer, director of the nonprofit digital rights organization Fight for the Future. “Amazon wants to have its hands everywhere, and acquiring a company that’s essentially built on mapping the inside of people’s homes seems like a natural extension of the surveillance reach that Amazon already has.” Amazon declined to respond to questions about how it would use iRobot data, but company spokesperson Alexandra Miller provided a statement that claimed the company had been a good steward of customer information. "Customer trust is something we have worked hard to earn—and work hard to keep—every day,” the statement said.
Amazon has a track record of making or acquiring technology that makes those concerned with data privacy uneasy. In 2020, Amazon introduced a home security drone , and last month Ring, a company that’s forged partnerships with thousands of police and fire departments , admitted to sharing home video footage with law enforcement without a warrant.
Should law enforcement or governments demand access, so much data about people in the hands of a single company poses the threat of being a single point of failure for democracy and human rights, Greer says.
The company already has its own home robot, Astro , which it introduced last fall. At the time, Amazon senior vice president of devices and services David Limp said the company launched the robot with no defined use case. In an interview with WIRED in June, Amazon vice president of consumer robotics Ken Washington said the initial focus is home monitoring and security.
Astro is currently only available by invitation only. Washington declined to share the number of Astro in people’s homes today or when Astro will be made generally available. Since launch, Amazon pushed an update to Astro that allows people to add rooms to a home map without the need to remap an entire home.
Amazon home robots are currently unable to coordinate activity between multiple units, but Washington said climbing stairs and coordination between Astros on multiple floors are part of the product development roadmap. Rather than hope that Astro catches on with a mass audience, the iRobot acquisition would give Amazon an instant home mapping presence at a huge scale.
It’s too early to tell, but the deal could face scrutiny from the Federal Trade Commission. Privacy advocates have already been vocal in their opposition, and FTC chair Lina Khan has been deeply critical of acquisitions by Big Tech companies. The five-member commission solidified a 3-2 Democratic majority in May. And Khan herself notably came to prominence after a Yale Law Journal article that reimagined antitrust law—with Amazon as the central focus.
Even without bringing iRobot into the fold, there are few aspects of people’s lives that Amazon does not have access to. It already tracks intimate details like what people eat, buy, watch, read, and the prescription drugs they consume. Soon, it may also know every inch of their homes.
Updated 08-05-22, 10.10 pm EST: This story was updated to add comment from an Amazon spokesperson.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Senior Writer X Topics artificial intelligence Amazon roomba data privacy David Gilbert Nelson C.J.
Peter Guest Andy Greenberg Steven Levy Will Knight Joel Khalili Kari McMahon Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,060 | 2,022 |
"Ecovacs Deebot X1 Omni Review: A Robot Vac That Mops Floors, Has a Cam | WIRED"
|
"https://www.wired.com/review/ecovacs-deebot-x1-omni"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear Review: Deebot X1 Omni Facebook X Email Save Story Photograph: Ecovacs Facebook X Email Save Story $1,000 at Best Buy $1,000 at Ecovacs If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 6/10 Open rating explainer I hate mopping, but I hate mopping robots more. And I especially hate robot vacuum-mop combos. During my years reviewing robot vacuums, I can’t count how many times I've had to unhook a minuscule water bin off the bottom of a robot, fill it with a thimbleful of water, and watch it laboriously drag a barely moist towel across my kitchen floor. It never seemed worth the effort when you just could grab a Swiffer.
That was until I installed the Deebot X1 Omni from Ecovacs. My 7-year-old had just shaken sugar off her toast all over the kitchen floor, so once she was off to school, I moved some chairs out of the way and plugged the mopping attachments onto the X1 Omni's bottom.
I summoned my bot with the command “OK Yiko,” and there was a massive rumble as it stirred. The mopping attachments rinsed themselves in a pool of clean water at the base of the machine before it trundled off. In 15 minutes, it covered my entire 200 square-foot kitchen floor, scrubbing furiously all the way. It never moved off the hardwood onto the carpet. (It did make a tentative pass into the open laundry room door, but only once.) Once it returned to base, the cleaning station used hot air to dry the little mops. After my floor dried, I took off my socks and walked hesitantly around. No sugar grains remained. The floor wasn’t even sticky. I finally found a mopping vacuum that can do its job.
Much to my surprise, I found the X1 Omni to be much more useful as a mop than as a robot vacuum.
Photograph: Ecovacs A few years ago, I predicted that every robot vacuum would have its own cleaning station. The stations have arrived, and they keep getting taller. The X1 Omni’s tower stands almost 2 feet high, 17 inches wide, and 17 inches deep. We have a 2,000-square-foot downstairs, and the only place I could find to put it was directly in the center of my house, in the kitchen next to the trash can.
The vacuum itself is a pretty standard 4 inches tall, able to fit under the sofa with ease. It comes with two side brushes and two mopping attachments that you can easily detach and reattach. Inside the tower are two water bins, one for clean water and one for dirty mopping water, and space for a 3-liter disposable dust bag for the vacuum’s auto-empty function.
You'll need the auto-empty function, because the dustbin in the body of the vacuum is a relatively small 0.4 liters. (Most robot vacuums I've tried have 0.6-liter capacity or more.) Instead, the X1 Omni’s body houses Ecovacs’ (possibly overbuilt, but more on that later) camera, microphone, and navigation system.
Ecovacs’ proprietary navigation system is called TrueMapping, which combines two navigation techniques. AIVI, Ecovacs’ AI-powered camera vision system, identifies common household objects. TrueDetect 2.0 uses laser scanning to create a 3D map of your house.
It also has an onboard speaker so you can talk to your family from your robot vacuum. Yes, you read that right. And rather than tackling the complicated matter (pun intended) of integrating with third-party smart speakers, the X1 Omni has its own voice assistant named Yiko. Ecovacs also offers the X1 Plus, which has an auto-empty station but no cleaning station.
Photograph: Ecovacs The Deebot surprised me a lot, but the first shock came when I initiated Quick Mapping. With nearly every robot vacuum, accurately mapping the cleaning area takes awhile. It’s usually three to five cleans, or a week where you have to stay home while it's cleaning to pick everything off the floor and be on hand to maneuver the robot around unforeseen obstacles.
Ecovacs Deebot X1 Omni Rating: 6/10 $1,000 at Best Buy $1,000 at Ecovacs If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Somehow, the X1 Omni developed a pretty accurate map of my home in its first pass. It took 120 minutes to clean about 570 square feet, and the battery was almost dead when it straggled back to base, all tuckered out, but it got the job done! I was also surprised that saying “OK Yiko” actually worked. I was skeptical, given that Apple, Google, and Amazon all amass tremendous amounts of language processing data and still fail. I suppose it helps that there are a limited number of commands you can give to Yiko and “OK Yiko” is a surprisingly distinctive wake phrase—though I wish you could alter it in the app.
In fact, “OK Yiko” is a much easier way to command the vacuum, much better than navigating Ecovacs’ surprisingly opaque app. (I should note that the app was in beta when I tested it.) The only aspect to the X1 Omni that gives me pause is the video feed. I really, really dislike the idea of giving any autonomous robot the ability to view and record your family in their most intimate moments. Ecovacs notes that the X1 Omni is the first robot vacuum to meet the TÜV Rheinland privacy and security certification; TÜV is an independent, third-party organization that certifies devices to meet the specifications of ETSI TS 303 645 , which is a prominent internet-of-things security standard.
For example, you can protect the video manager with an additional security number, and Ecovacs encrypts the data as it passes to the cloud. However, the company doesn't offer basic protections like two-factor authentication.
I also question the utility of taking up valuable onboard space with a speaker and microphone. It’s convenient that the mapping function can pinpoint trouble spots in your house and let you look at them through the robot’s camera—especially when it’s lost. It’s much less useful to be able to talk through a robot vacuum.
In an especially creepy move, I rolled the vacuum up to my daughter as she played with her iPad on the couch. “Hi, baby,” I said.
She looked at it dubiously, as I looked up at her from the vantage point of her feet. “Mommy?” she said, and got down on the floor. “Is the robot vacuum talking?” “Yes,” I said. Then I switched the camera off and returned the vacuum to the cleaning station. I really don’t see the potential of very many heartwarming moments here, unless The Lives of Others is your idea of a romantic film.
Photograph: Ecovacs Of course, many robot vacuums have onboard cameras, including my favorite iRobot Roomba J7+, which takes pictures of obstacles around your house that you can check in the app. However, its camera is aimed downward at obstacles, not upward at your feet—or worse—children. I don’t think paying extra so you can talk to your family through your vacuum is a particularly good use of money.
There are other dedicated robot mops—most notably iRobot’s Braava mops.
But the X1 Omni’s cleaning process is much more thorough than the Braava spray-and-wipe system, and it’s much less expensive and less complicated than buying two separate products and linking them together. I do wish Ecovacs recommended cleaning solutions you can buy in the US, but the company has cleaning solutions available in other markets, and hopefully those will be here soon.
If you live in a household where small people get your kitchen floor conspicuously dirty every day, the X1 Omni is pretty much a godsend. It's amazing that I can quickly and easily mop the kitchen floor in the time it takes to brew and sip a cup of coffee. However, if the idea of a camera creeping on your kids gives you the heebie-jeebies, I completely understand. You have many other options.
Check out our full list of the best robot vaccums.
Ecovacs Deebot X1 Omni Rating: 6/10 $1,000 at Best Buy $1,000 at Ecovacs If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $1,000 at Best Buy $1,000 at Ecovacs Senior Associate Reviews Editor X Topics Shopping review smart home robot vacuum Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,061 | 2,021 |
"Bikepacking Gear Guide (2021): Tent, Clothing, Frame Packs, Food, Water | WIRED"
|
"https://www.wired.com/story/bikepacking-gear-guide"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Stephanie Pearson Gear The Gear to Carry on Your Next Bikepacking Adventure Photograph: Pearl Izumi Save this story Save Save this story Save According to the editors at Bikepacking.com the summer of 2021 will be … a lot like the summer of 2020. We may be able to walk mask-free into a convenience store to fuel up on Snickers and Gatorade, but the unpredictability of international travel will keep most of us exploring in our own backyards. For those of us who love our backyards, that’s not such a bad prognostication. If you've already got a working bike, all you need is a goal, whether it’s exploring new roads solo or finally signing up for that multiday charity ride.
There are no hard and fast rules for bikepacking. Some cyclists thrive on riding 1,000 miles in cutoff denim shorts, drinking from streams, bivouacking under the stars, and tempting fate with every decision. Others prefer to carry the extra weight of tents, sleeping pads, and stoves to ensure their comfort, safety, and well-being. There may not be a “wrong” way to do it, but there are some kit items, bike accessories, camping gear, and food that will make your two-wheeled foray into the wild more enjoyable.
What you're reading now is a newly updated version of the guide we originally published last year. We’ve provided a few new suggestions for key pieces of the bikepacking puzzle and kept a few steadfast no-brainers provided last spring by Jeremy Kershaw , a registered nurse who for more than a decade has been organizing events like the Heck Epic, a three-day bikepacking race in northern Minnesota. Kershaw has pedaled thousands of miles to hone his systems. As he likes to say, “Bikepacking is a tinkerer’s dream. The pros and cons of each piece of equipment can be dramatic, but that’s part of the fun.” If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED.
There's plenty of bike-specific gear available to outfit you from head to toe, but here's our advice for what works best on those week-long backcountry rides.
If you want to maximize time off the bike on a multiday trip, try Specialized's Rime Flat Shoes ( $130 at Specialized , $130 at Backcountry ). It sounds like an oxymoron, but Specialized designed this relaxed biking shoe with hiking in mind. The design pairs an uber-grippy rubber outsole with a durable mesh and TPU upper that breathes well and drys quickly in inclement weather. It also has enough interior support to properly optimize hip, knee, and foot alignment on the bike, reducing your risk of injury. At 13.6 ounces, it feels like a light hiking shoe when you wear it off the bike. In the saddle, it’s stiff enough to power the pedals forward.
For those who want maximize their power, efficiency, and style quotient while minimizing weight, the answer is the Rapha Explore Powerweave shoe ( $355 at Rapha ). Yes, it’s pricey, but it's packed with tech. The stiff carbon sole of a road shoe is topped by a 3D-woven fabric with TPU-reinforced yarns that give it strength and weather resistance. The two-wheeled boa lacing system ratchets to just the right tension so the shoe ends up feeling custom designed for your own foot.
Photograph: POC Sports Some bikepackers believe that helmets only add to the fatigue they feel over long miles while providing little added benefit, especially when riding on roads lightly traveled by cars and trucks. Others wouldn’t even consider straddling a bike without wearing a brain bucket. Here’s one helmet that meets the debate in the middle: the POC Ventral Lite ( $275 at POC , $275 at The Pro's Closet ). Weighing 8.5 ounces, this highly ventilated helmet is one of the lightest ever produced, making it far less of a burden on your head. POC shaved weight by scaling back the outer shell to cover only the essential parts of the liner, which is made using a lower-density EPS foam.
Photograph: Velocio A cycling baselayer should wick sweat going uphill and keep you warm and dry going down. It should also stretch in the shoulders, be compressive enough to provide support, and be long enough to keep you covered. We like the Specialized Merino Seamless Short Sleeve Base Layer ( $80 at Specialized , $80 at Backcountry ). Made from soft merino wool, this lightweight base layer does all of the aforementioned tasks well. Thanks to its naturally antimicrobial threads, it will also keep you stink free for those nights you happen to roll out on the town.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So What you wear as your primary layer is a matter of personal choice. Some prefer a basic technical tee, while others will want a standard zip-up, three-pocket cycling jersey. So, let us consider the outer layer. The latest trend in cycling apparel is the technical hoodie. They’re great for cool riding in shoulder seasons, but they are also awesome off the bike while camping. Five bike companies sent me their hoodie for testing. I especially loved Velocio’s Recon Hoodie ( $249 for women , $249 for men , both at Velocio). I wear it every day. The Italian-designed piece has a streamlined fit, a merino fleece lining, two zip pockets on the front, and one smaller zip pocket on the side.
A jacket needs to be roomy and pliable enough to allow you the freedom of movement you require to safely maneuver your bike. A good jacket should also be breathable while staying fully wind and waterproof for long-haul rides. A hood is nice too. The POC Signal All-Weather Jacket ( $280 for men or women at Backcountry, $350 for men or women at POC) ticks all those boxes while still packing down wherever you want to stash it; just stuff it into its own back pocket and attach it, via snaps, to the front handlebars. Its built in RECCO receiver will ping search and rescue folks with your whereabouts if you wind up in a ravine, and an NFC chip inside can store critical health details that first responders can access using a companion app that’s available for Android or iOS.
Photograph: Pearl Izumi Diehards like to show their grit by riding in cutoff shorts with no protective chamois. And while those may dry faster, bib shorts are better. Bibs are aerodynamic, don’t bind in the waist, stay up, and have a chamois to keep your undercarriage from getting chafed. There are beefier bibs out there, but we like the Pearl Izumi Interval Cargo Bib Short ( $124 and up for men or women at Pearl Izumi ) because it has cooling mesh side panels for hot summer riding. It also has pockets on the thighs for quick access to snacks, a leg-gripping hem, and a comfortable friction-reducing chamois. Ladies take note: The distaff version has a drop panel designed for quick and easy pee breaks. Pearl Izumi tends to run slightly smaller than other brands, so consider sizing up.
Every season, I waver on whether expensive sunglasses are worth their lofty price tags. After testing multiple brands, I found that the more affordable Tifosi Sledge Light ( $70 and up at Tifosi Optics ) are as good as the more expensive options. They’re lightweight, flexible, and slip-free. And, importantly for long days, they come with interchangeable polycarbonate lenses—swap in clear, all-condition, or full-sun lenses—that keep your eyeballs covered no matter what kind of light the sun throws at them.
Bandanas are still more popular, but we can’t let go of our Buffs ( $14 and up at Buffs ) because they provide better coverage and a wider variety of protective features. The various models offered by Buffs guard against annoyances like the wind, the cold, biting insects, and the sun (with SPF 50 protection) to match whatever riding conditions you happen to find yourself in.
Photograph: Suunto On a long ride into the unknown, you'll need a piece of technology to count the miles, and of course tell you where exactly on the green hills of Earth you are. Stem-mounted bike computers are the standard-bearers of GPS systems among dedicated bikepackers, but some multi-sport athletes prefer the versatility of wearing their way-finding tech on their wrist. Plus, a smartwatch has the added benefit of tracking your heart rate and other physical data points. Whichever option you choose, Kershaw advises that you “make sure you understand your system before heading out.” Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Wristwatch : My top pick is the new Suunto 9 Baro Titanium ( $419 at REI , $599 at Suunto ). It's a premium, upgraded version of the Suunto 9 that debuted in March. Track the weather, your heart rate, and your route using the intuitive buttons, or by swiping across the touchscreen on this beautifully designed Finnish timepiece. The watch offers turn-by-turn directions (the navigation system is powered by adventure mapping specialists Komoot ) and provides up to 170 hours of GPS tracking in the battery-sipping tour mode—a key feature for those in the wild for multiple days with limited access to recharging. In standard mode, the watch ratchets down to 25 hours of battery life, which is plenty for city-to-city rides.
Cycling Computer : Go for the Wahoo Elemnt Bolt ( $280 at Wahoo ). Wahoo's updated bike computer is a highly intuitive companion. Slightly larger than a pack of dental floss, it unobtrusively mounts to your handlebars. The waterproof—and, thanks to its Gorilla Glass screen, nearly crash-proof—device packs a new, 64-color high-contrast screen and expanded navigation features. Wahoo also increased the battery to provide a 15-hour runtime and increased onboard memory to 16GB, which means you can preload as many miles of maps as you can handle. When paired with the Wahoo Elemnt mobile app, riders can customize their data screens, sync routes between computers, and analyze their ride data.
It’s nice to get out of the elements on occasion with a night in a hotel or couch surfing with friends, but it’s also good to be prepared for those days when you’d rather just sleep under the stars.
“The ultralight tent versus bivvy versus hammock debate is endless,” says Kershaw. Hammocks you can string up between two trees, and simple bivvies (ultra-minimal shelters) are easy options because you don’t have to deal with poles, but Kershaw says you should consider an ultralight tent if you want a dry place to read at night.
For minimalists, we like the Rab Ridge Raider Bivi ( $375 from Rab ), a one-person bivvy rigged for sleeping anywhere—even in a ditch if you have to. You have to squeeze yourself inside, and it’s a tight fit, but its Pertex shell gives you a dry, breathable, secure hideaway for sleeping. With only one overhead hoop and a micropole at the feet to keep the morning dew off your sleeping bag, it takes less than five minutes to set up. Weighing just under two pounds and packing down to the size of an overstuffed Chipotle burrito, it’s an essential rig for those who want to keep it as simple as possible.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Those craving something more luxurious should try the SeaToSummit Telos TR2 ( $499 at SeaToSummit ). This two-person, three-season, two-door backpacking tent has a unique pole system; the middle pole curves in the opposite direction outward, like butterfly wings, so at its apex, the tent becomes roomy enough for somebody to almost stand fully upright. The packed weight of 3 pounds, 7 ounces, is mere peanuts, but with an innovatively designed segmented stuff sack, the tent can be distributed between two bikes. With a floor area of 28 square feet and a vestibule area of 19.5 square feet, the weight to footprint ratio is exemplary, especially when you need to spread out and dry stuff after a long, wet day in the rain.
When it comes to sleeping bags, Kershaw’s advice is to find a sleeping bag and pad that packs down and keeps you warm. “Go as light as you want to,” says Kershaw. “There’s such a wide variety of temperature ranges out there.” Some seasoned riders just bring a tarp and wrap themselves up in it like a burrito. If this is your first bikepacking trip, however, we recommend sucking up the extra weight of a bag and pad.
Kelty's Cosmic Ultra Down 20 sleeping bag ( $200 and up at Kelty , $200 and up at Evo.com ) was already a pretty ideal selection, but this year Kelty upped the down fill from 600 to 800, changed the rectangular baffles to trapezoidal ones to retain more heat, and added a soft taffeta liner. The upgrades over last year's model shaved a few ounces off the weight (it now measures 2.4 pounds for the men’s version and 2.9 pounds for the women’s) and added $40 to the cost, but I find that added comfort is worth the extra money.
For a ground pad, try the Big Agnes Insulated Axel Air pad ( $152 and up at REI , $152 and up at Big Agnes ). For its light weight (around 17 ounces for my midsize pad) the Axel Air sleeps like a much beefier pad, and with an R-Value (the measure of a sleeping pad's ability to resist heat transfer; higher is better ) of 3, it kept me warm and dry even in the damp chill of early spring in Minnesota. There’s always a risk that a pad this lightweight will pop, so be gentle with it. The pad comes in multiple lengths and widths, and in a mummy shape or as a rectangular pad. All the sizes and shapes are different prices, and some are easier to find in stock than others.
You have to eat and drink out there. Here's some tested advice on what to pack, how to pack it, and some other strategies for staying fueled up.
There's no getting around it: you're going to have to carry water with you. Kershaw says to secure any water bottles or bladders to your bicycle frame instead of relying on a hydration pack. “It’s much better to carry as much weight as possible on your bike as opposed to on your back,” he says. He also offers this expert advice: If your route is remote, pack a filtration system.
For those looking for efficient water storage, I like the HydraPak Seeker 2L ( $22 at REI , $22 at HydraPak ). More versatile than your average hydration bladder, this ultra-tough TPU water carrier will scrunch into the size of a fist when not in use. It's also compatible with any filter (like the Katadyn BeFree) that screws on to a common 42mm thread, and it can be kitted out with a separate hydration hose for use as a hydration pack during the day. At the campsite, secure it with its leakproof screw cap and use it for water storage.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So If you want 99.9999999 percent piece of mind that a water-borne illness won’t force you to end your trip early, pack the MSR Guardian Gravity Purifier ( $250 at REI , $250 at MSR ). It’s a little bulky for ultra-streamlined rigs, but if space isn’t critical, this high-flow, gravity powered system is handy. It filters bacteria, particulate matter, viruses, and intestine-ravaging protozoa.
Photograph: Good to Go “A lot of the fun of bikepacking is coming into a town for a food stop,” says Kershaw. But, he adds, “We can’t assume we can find places to eat, so know in advance where reliable food stops are.” If you're going to be far from civilization, just BYO nutrition. I can recommend the delicious, nutritious, just-add-water meals from Good to Go.
For me, these have made backcountry food prep a thing of the past. The company's new pre-packaged food kits offer an assorted selection of meals to last five to 10 days. Breakfasts, lunches, and dinners are included. The five-day package offers 305 grams of protein, 8,430 calories, and tasty options like Cuban rice bowls , Thai curry , and Good to Go's award-winning chicken pho.
There are meal kits for vegans too. ( $135 and up for the five-day kits.) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Kate’s Real Food Dark Chocolate Mint bars make a great on-the-bike snack. The peppermint-tinged bar is packed with organic ingredients including peanut butter, gluten-free oats, dark chocolate, peppermint extract, and natural cacao powder. (12-pack, $30 at Kate's Real Food.
) When you’re sweating it out all day on a bike, you need more than just water to replenish lost electrolytes. The new Honey Stinger Rapid Hydration Mix ( $15 and up from Honey Stinger ) offers three types of specialized hydration: Prepare for swigging pre-ride, Perform for sipping on the bike, and Recover for your evening come-down. Each mix uses organic honey for sweetness and to provide a natural energy boost, and combines it with sodium to speed the absorption of key added nutrients. The best part: each flavor has a satisfyingly tart taste without the sickly aftertaste of many performance drinks.
Bring an ultralight camp stove for your morning oatmeal and coffee.
Photograph: MSR If your route takes you through towns with shops and restaurants, Kershaw advises that you follow this simple plan for fueling up your engine: “Bring a tiny stove and a little tiny cook kit for cooking breakfast, then credit card camp for the rest of the day,” he says.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So For making that first meal of the day, we like the MSR Pocket Rocket II ( $45 at REI , $45 at Amazon ). Screw this featherweight burner onto an isobutane-propane-fueled stove, and it boils water in less than three and a half minutes.
It's about more than just the bike. Supplement your ride with these items for storage, repairs, and safety.
You might be tempted to pack a big backpack, but that's the wrong move—see Kershaw’s advice above about carrying weight on your bike instead of on your back. “Frame bags are great, just make sure you load up and see how your bike feels before you go,” he says. And put some quality test miles on your loaded-up chariot so you can dial in your setup. “If a strap is rubbing, that annoyance will be compounded when it starts to rain.” I like the Ortlieb Frame-Pack RC Toptube pack ( $150 at Ortlieb , $150 at REI ). The German-made, four-liter, waterproof frame bag is ideal for bikepackers in wet climates who need dry storage for things like a tent, a stove, and food, yet still want to access the water bottles secured to their frame below. The combination of Velcro and roll closures keep your goodies on the inside. For more storage, Ortlieb’s fork packs ( $60 each ) and rear panniers ( $190 for a pair ) are a welcome addition; they attach to either side of the wheels in front and back.
Flats are a reality on a long ride. There are two good options for spare tubes: good old rubber; or TPU, a stretchy thermoplastic. The tradeoff between them is that the rubber may be more versatile in terms of the size tires it can accommodate, but the TPU is unmatched in weight and packability. I recommend Tubolito's S-CX Gravel Tube ( $40 at Tubolito ). The lightest, smallest tube on the market, this 35-gram TPU tube with a Presta valve is as strong as a standard rubber tube at a fraction of the weight. It's compatible with tubeless tires too, making the S-CX is the ideal spare for all 700c and 650B tires between 30-mm and 47-mm tire widths.
The best method for getting a tire up to pressure and ready to roll after a repair is also a matter of debate. Some prefer the trusty method of pumping air into a tube via a mechanical pump. But that's tedious and time-consuming, which is why others insist on the quicker, easier, and occasionally explosive option of inflating the tire with a pressurize CO2 canister.
The good news is that you can have it both ways with the Cannondale CO2 Road Mini Pump ( $38 at your local bike shop ). This super-compact pump is the size of an Epi-Pen, and it eliminates the debate by pairing a speedy CO2 cartridge mechanism with a mechanical backup of a real pump. The pump comes with a bike mount, but it's small enough to be stashed in a jersey pocket or pack. It's an especially good bet for winter riding, since the metal CO2 cartridge is already in position and ready to fire, and those things can become too cold to handle on frigid days.
A study conducted by Clemson University in 2016 showed that, on average, cyclists believe they are 700 percent more visible to cars than they actually are. That’s why, even the minimalists should still pack a strong lighting system. Consider Bontrager's powerful and easy-to-mount light combo, the Flare RT and Ion Pro RT ( $185 at Trek Bikes , $185 at REI ). It comes with a headlight to illumiante the full width of any road or trail, and a rear flare that can be seen from 2 kilometers away thanks to its unique flash pattern. If you have a Garmin computer or any ANT+ device, you can use the display to track the lights' battery levels.
There’s also a place for a headlamp in a bikepacking kit, as a backup headlight on the road, and for use in camp to more quickly and easily put up the tent or cook meals in the dark, or just to relax and read. I like the 168-lumen Third Eye Headlamp ( $50 at Third Eye , $48 at Amazon ) because it throws a beam that can extend up to 360 feet. It has two easy-to-use push buttons, one for white light and one for red light, which preserves night vision while still providing illumination. The headlamp portion is made from 100 percent recyclable, non-toxic plastic too. The various designs for the machine-washable headband are fun as well.
For a compact multitool, we like the Leatherman Squirt PS 4.
Photograph: Leatherman Kershaw’s recommended fix-it kit list includes a bunch of small items. Definitely pack the mini Leatherman Squirt ( $40 at Amazon , $40 at Huckberry , $40 at REI ) with pliers to fix cables. For tire maintenance, you'll want a tire boot for repairing sidewall cuts, a small pump (like the one above), a tire lever for getting tires on and off the wheels, and a patch kit for fixing flats ( try this $7 kit from Park Tool ). All of that, of course, is in addition to your spare tube. If your route is long or filled with gravel sections, then maybe bring two tubes. Also take along a set of extra brake pads and a quick link/extra chain link for fixing drivetrain issues. And don't forget the extra batteries or charging pack for your GPS unit or smartwatch.
To treat the small scrapes and aches, Kershaw packs an antibiotic ointment, several large Band-Aids or 2-inch bandages, cloth tape, and ibuprofen. He also never leaves home without a bug net, headlamp, sunscreen, and lots of Voile straps ( $4 at Voile Straps ) for securing gear to the bike. These brilliant orange, perforated polyurethane strips with clips were originally designed to haul skis, but they work perfectly for holding a tent tight to the handlebars.
One last thing: Never underestimate the importance of seemingly small details, like the cushion in your handlebar tape.
Lizard Skins just debuted a 4.6mm-version of its popular DSP V2 tape specifically designed for bikepacking ( $40 and up at Lizard Skins ). It provides extra vibration damping and cushioning where your hands meet metal. Plus it comes in four colors—Jet Black, Graphite, Crimson Red, and Electric Blue—so you can look stylish even when there's not another soul for miles.
📩 The latest on tech, science, and more: Get our newsletters ! The 60-year-old scientific screwup that helped Covid kill We hiked along with cicada biologists so you don’t have to The Ford F-150 Lightning is the electric vehicle of dystopia SNL helped create the age of memes.
Now it can't keep up STEM’s racial reckoning just entered its most crucial phase 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 📱 Torn between the latest phones? Never fear—check out our iPhone buying guide and favorite Android phones Topics Bicycles outdoors cycling apparel Bags buying guides Shopping Scott Gilbertson Scott Gilbertson Carlton Reid Boone Ashworth Reece Rogers Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,062 | 2,023 |
"Apple Watch Ultra 2 Review: You’ll Still Need to Keep Your iPhone Handy | WIRED"
|
"https://www.wired.com/review/apple-watch-ultra-2"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear Review: Apple Watch Ultra 2 Facebook X Email Save Story Photograph: Apple Facebook X Email Save Story $780 at Amazon $799 at Apple $800 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 8/10 Open rating explainer The best, and worst, part about reviewing products is when your experience takes a hard right turn. Last week, I went on a trail run with the Apple Watch Ultra 2.
At home, I had set the orange Action button to start Backtrack , Apple’s navigation feature that creates a virtual breadcrumb trail in the Compass app for you to follow back home. I connected my headphones and started my playlist. I tapped the watch face and started an Outdoor Run.
I like going on trails by myself, but I find it mentally taxing. I stop at every trail crossing. I study familiar landmarks and check the time as I pass them. I checked Backtrack a few times as I was running and saw that it was working. It even gave me a time estimate for my return on the topographic map! Secure in my ability to find my way home, I let my brain shut off. I started mentally composing this review with an intro on how the watch has made going outside so much more accessible. I was flying through the sun and air in the trees, as happy as I’ve ever been.
Then I got to my turnaround point. I flipped back through my watch screens. Somehow, in between checking my heart rate and mileage and checking my music, I had … turned Backtrack off. I turned off my music. The deep woods around me were totally still. Luckily, I had previously downloaded the topographic map of the area on my phone, and I was able to check the watch's Compass app even though I didn't have a data signal. So it wasn't like I was lost.
But it wasn’t hard to imagine how I could have been.
Even the best of tools occasionally succumb to user error, and being alone in the woods is still a bad time to make a mistake.
Photograph: Apple The Watch Ultra 2 looks pretty much like last year’s Watch Ultra ( 8/10, WIRED Recommends ), with a few key differences. This year it has a faster S9 chipset, which among other things powers some of the basic Siri interactions right there on the watch. You no longer have to wait for simple voice commands—start a workout, set an alarm, log your weight—to travel up and down from the cloud. Machine learning tasks are also completed twice as quickly than on the original Ultra, which theoretically extends the battery life of the watch. The extra power enables new interactions like Double Tap, which uses the watch's sensors to detect when you tap your thumb and index finger together twice. That gesture can be used in place of the primary watch button on any screen, or open your Smart Stack. There are other gestures too, like covering your watch to mute it.
The new Alpine Loop watch band is made from recycled materials, in this case polyester and spandex.
Photograph: Apple Apple Watch Ultra 2 Rating: 8/10 $780 at Amazon $799 at Apple $800 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The new Ultra's display maxes out at a brightness of 3,000 nits. That is shockingly bright; for reference, the iPhone 15 has a max-2,000-nit display. You can also configure the watch with its new Modular Ultra watch face, which lets you set an additional real-time metric along the bezel of the watch—pick between seconds, elevation, or depth if you’re diving. There’s a second-gen ultra wideband chip inside the latest model that makes the precision finding features more accurate, so it's easier to locate your lost iPhone using your watch. (It slipped behind the snacks in your backpack's front pocket.) And finally, when paired with the new trail loop , which I’m wearing, the Watch Ultra 2 is what Apple claims as one of its first carbon-neutral products. The case is made of 95 percent recycled aluminum, and the loop itself contains 32 percent recycled content, made in factories powered by 100 percent clean energy. Of course, we urge you to take these (and any) environmental claims with a grain of salt.
Photograph: Apple I’ve tried pretty much every loop the Ultra has to offer. The trail loop is my favorite so far; not a surprise, since trail running is one of my favorite sports. Other people have remarked that on my 150-mm wrist, the 49-mm case size looks enormous. But I don’t find Ultra 2 unwearably huge. I also now appreciate the enormous screen, especially when it comes to examining topographic maps.
I cycled to a nearby river on a sunny day to see if the 3,000-nit display did anything to increase the screen's visibility when viewed among the bright reflections of sunlight bouncing off the water. It was not noticeably more difficult to see the iPhone 15's screen in the sun next to the Apple Watch Ultra 2. However, I do like the Modular Ultra face very much. I have my bezel set to elevation. It can get pretty wonky—my poor watch showed me as being several hundred feet under sea level when I got off the plane. However, it recalibrates pretty quickly and comes in handy when I find myself getting inexplicably tired on the back half of a run and discover that I’m actually running uphill. I also use the real-time compass a lot.
With what some might consider normal use—one GPS-tracked run per day, along with some walking and swimming—the Watch Ultra 2’s battery life can stretch almost four days. However, with what I would consider the expected use of the Watch Ultra 2—a trail run with GPS-enabled workout tracking, playing music, and running Backtrack (sort of)—I can drain the Ultra 2’s battery by about 25 percent in two hours.
Topographic maps can be loaded onto your iPhone for use on the Watch Ultra 2 when your devices are offline.
Photograph: Apple It’s hard to discuss how well the Ultra 2 works without taking into consideration that it’s not really a stand-alone unit. Apple has mostly given up on the idea that people are ever apart from their phones, which, fair. If I’m wearing a trail running vest or a cycling waist pack loaded with water, snacks, my car keys, and wallet, I am definitely putting my phone in there too.
Apple Watch Ultra 2 Rating: 8/10 $780 at Amazon $799 at Apple $800 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Although the Watch Ultra 2 has its own onboard precision dual-frequency GPS system, it’s mostly there to more precisely map and track your workouts. The watch doesn’t have its own onboard offline maps to navigate independently of the iPhone. Instead, you click into Apple Maps on your phone while you're at home, download the offline map, and then keep your iPhone charged and within range of your Ultra 2 to look at the map on your wrist.
The latest version of watchOS has improved tracking for bike rides and cycling workouts.
Photograph: Apple Likewise, watchOS 10 now shows cycling as a live activity on your phone screen so that you can use your phone as a de facto bike computer.
I did this on a bike ride to the beach and it’s very handy! However, unlike with a dedicated Garmin unit that crams all your relevant data onto one display, Apple's workout data and mapping functions are all very siloed into various apps. You end up toggling quite a bit between Workouts, Maps, and Music or Podcasts. That’s in addition to the toggling you have to do between Apple Health and Workouts when you want to check your running statistics versus, say, the amount of hours you slept.
It’s all there , and accessible , but it’s a little annoying that you can’t see everything in one place, and it introduces the possibility of user error. Who among us has never accidentally closed a tab? Let them cast the first stone. I’ve never accidentally shut off Garmin's breadcrumb feature, because that’s why I wear a Garmin watch. It’s for workout tracking and navigation, not all of the things all the time.
In this context, the second-gen UWB chip makes a lot more sense. It has to be easy to find your phone, because you need it for everything. I’m constantly switching my phone and wallet between the handlebar bag on my bike, the pocket in my gym bag, my running pack, my cycling pack, etc. Being able to use precision finding to locate it perceptibly lowers my stress levels.
The Double Tap gesture lands on Apple Watch-bedecked wrists next month.
Video: Apple The Double Tap gesture will be enabled on the Watch Ultra 2 and the Watch Series 9 in October. Apple sent an additional Series 9 model that has Double Tap, and I've written about that feature in my review of the Series 9.
I couldn't access Double Tap on the Watch Ultra 2 during my testing period, but I did come across a situation where I wished I could have. I went rock climbing and, as usual, forgot to start my workout. I waited to get to a small rise in the face and leaned my full body against the wall. While trembling as I clung to the rock with my hands, I tapped my sweaty nose on the Ultra 2's screen to launch Workouts and then press the Climbing button. Hard to picture Alex Honnold doing this, and yet here we are.
The Watch Ultra 2's codependency with the iPhone skews the wearable's value proposition a bit. When you’re considering whether you should buy a Garmin Epix Pro ( 8/10, WIRED Recommends ) or a Watch Ultra 2, it’s not one watch versus another. It’s one ecosystem versus another, one fragmented and one integrated. Do you want to buy a Garmin Edge and an InReach Mini and a Forerunner and a regular degular smartwatch ? Or just one watch and an iPhone (and probably a portable charger ) to do all the things, all the time. I consider that this equation now balances out in favor of the Watch Ultra 2, especially since, well … I love outdoor adventures, but I do spend most of my time at work and doing family stuff. The equation might not balance out for many outdoorspeople—not being able to access offline maps without the phone is, unfortunately, kind of huge—but it’s getting there faster and faster.
Apple Watch Ultra 2 Rating: 8/10 $780 at Amazon $799 at Apple $800 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $780 at Amazon $799 at Apple $800 at Target Senior Associate Reviews Editor X Topics Shopping review apple Apple Watch Fitness Trackers smartwatches Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,063 | 2,022 |
"The Best Bike Computers (2022): Garmin, Wahoo, Bontrager, Hammerhead | WIRED"
|
"https://www.wired.com/gallery/bike-computers-buying-guide"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Stephanie Pearson Gear The Best Cycling Computers Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED What to Know Before You Buy Read more Best Basic Option $45 at Trek Best High-End Option $750 at Garmin The Best Mid-Priced Option $400 at Wahoo Fitness When it comes to cycling computers, bicyclists tend to love them or hate them. Those in the latter category crave the freedom of riding without technological interference. I used to be one of those people. I was disdainful of taking along a computer that could talk to GPS satellites, display where I was on a map, and tell me my speed, distance, heart rate, cadence, and a whole host of other data I didn’t care about or even know existed. Then my partner started training for a 350-mile gravel race, which in turn inspired me to train for the companion 100-mile race. I quickly discovered on our training rides that it was pretty nice to have a trustworthy device designed to attach to my handlebars so I can safely see it.
Sure, you could always just mount a smartphone on your handlebars, but bike computers are purpose-built to handle bad weather, crashes, and full days in the sun—all situations where a smartphone might be unreliable or difficult to read. And on those extra-long days when I bailed and my partner was out riding solo in the dark and in hypothermic conditions, I realized it might be good to have a way to find him should he run into trouble, which happened during the race. He blew out the sidewall on a tire and was stranded by the side of the road at midnight. Since his GPS-enabled cycling computer allowed me to remotely track his ride via a companion app on my iPhone, I knew exactly where to pick him up before my own race started at 7 am.
GPS devices aren’t foolproof when it comes to safety, however. Last May, gravel cyclist Anna Moriah “Mo” Wilson was murdered by a bad actor who purportedly stalked her via her public settings on a popular training app. It is especially important for solo riders to carefully monitor their fitness apps’ privacy settings so their whereabouts remain protected from public view.
And as for carefree cyclists who prefer to enjoy the ride rather than obsess about stats, there’s a way to have it both ways: Most of these devices have screens that can be programmed to turn off while riding. So I can still enlist safety features like precision mapping, ride tracking, and alarm alerts that will go off if I get lost or have a crash. If I want to check where I am or how long I’ve ridden, I can push a button and the screen comes back to life. The dopamine rush of a hard-won Strava trophy, however, will have to wait until I get home.
Update, December 2022: We've swapped in the new version of the Wahoo Fitness Elemnt Roam as our recommended mid-priced option and removed the older version.
Be sure to check out our other cycling-related guides, including our bike accessories buying guide, which includes advice on finding the right helmet, lock, saddle, and other essentials. We also have buying guides for ebikes and electric cargo bikes.
Photograph: Bo Zaunders/Getty Images What to Know Before You Buy Bike Computers 101 Cycling computers come in two designs. The simpler—and more budget-friendly—computers pair a magnet placed on a front-wheel spoke to a sensor attached to the bike's fork. Together, the two measure how fast the wheel rotates, which the computer uses to calculate speed, average speed, and distance traveled. The second type, which is more common and more sophisticated, is a GPS-enabled device that uses satellite triangulation to track your position, speed, distance, and time. These more expensive and full-featured computers can also record cycling-specific data like cadence, power, and heart rate when connected to specialized wireless sensors, all of which can then be uploaded via Bluetooth to cycling training apps like Strava or MapMyRide.
Most GPS cycling computers are so complex that this guide only scratches the surface of their available features. Before you buy any computer, it’s important to figure out what you want and need in a device. Would a basic model that shows your speed and mileage be good enough? Do you already track your heart rate on a Garmin watch or Apple Watch? Do you ride solo on rural roads, where GPS is necessary? If you can, do some side-by-side comparisons at a local bike shop or outdoor retailer to better study the capabilities of the devices that seem like the best fit.
Keep in mind that while cycling computers can be costly, and some seem to err on the side of over-the-top capability, almost all of them are enhanced with safety features that could save your life, namely precision mapping that can get you out of a jam in foreign, unfamiliar territory; a preprogrammed alarm that can be texted to select friends and families in the event of a debilitating crash; and a tracking feature that allows select friends or loved ones to know where you are on solo rides. These extra pieces of insurance are increasingly essential in an increasingly crazy world.
Photograph: Bontrager Best Basic Option Bontrager GOTime Cycling Computer The GOTime cycling computer represents the most basic style of device on the market, tracking distance and speed via a magnet-and-sensor connection on the wheel. The data collected by the fork-mounted sensor is transmitted via a wireless signal with a 27-inch range; this means that, unlike older cycling computers, you don’t have to run a wire from the sensor up to the head unit. The LED screen is ensconced in a protective rubber case about the size of a chunky watch that easily attaches to handlebars via a grippy rubber strap and integrated mounting clip. The juice for the computer screen, which also tracks the time of day and ride duration, is provided by a CR2032 coin cell battery, while the sensor power comes from a small A23 battery.
I liked the straightforward simplicity of this featherlight 1.2-ounce unit. The one button on the bottom scrolls through time of day, ride time, miles traveled, cumulative miles traveled, speed, and average speed. For cyclists who simply want to track miles, this is the device for you. There’s nothing to go haywire other than an occasional dead battery.
For such a simple device, however, be prepared to spend at least 15 minutes on the setup: The protective rubber covering needs to come off to insert the battery, and the sensor and magnet need to be properly placed on the spoke and fork respectively.
$45 at Trek $45 at REI Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Garmin Best High-End Option Garmin Edge 1040 Solar It’s a little frightening how much this solar-powered device can do. It’s an upgrade from the $600 Garmin 1040 , using mostly the same design but adding solar power along with some other improvements. The upper and lower panels above and below the 3.5-inch touchscreen capture 100 percent of the sun’s rays, while the screen itself also captures solar power but at a less efficient rate. The extended battery life is impressive: While the battery-powered Garmin 1040 averages 35 hours and is capable of 70 hours in battery-saver mode, this solar version of the 1040 increases that average to 45 hours and extends battery-saver mode to 100 hours. That’s a game changer for ultracyclists who need to eke out every bit of battery power for their multi-day efforts. (Although I’d still pack an extra battery, in case of overcast skies.) Storage has also doubled from 32 GB in the 1040 to 64 GB in the solar version. While the 1040 comes preloaded with only North America maps, the solar version is preloaded with maps for North America, Europe, the Middle East, and Africa, with room for more. (One surprising caveat for a unit this sophisticated: Maps cannot be downloaded wirelessly. The unit needs to be plugged in, which requires advance planning if you’re going to places with limited GPS access.) Because the GPS is enhanced with GNSS technology, which determines location by measuring the distance to four or more satellites, the mapping is spot-on accurate, even in the backcountry. It also includes enhancements like Forksight mode, which displays upcoming forks in the road with surrounding geographic context that allows you to more easily understand where you are in a trail system; “turn-by-turn” direction mode that sounds alerts for each upcoming turn; and off-course notifications should you get sidetracked.
Like the earlier model, the 1040 Solar has safety features like live tracking and incident detection. The former allows a third party, when given permission by the cyclist, to track the ride; the latter sounds an alarm to emergency contacts if a blunt-force action like a crash causes it to go off.
I spent a month testing this computer and still didn't have enough time to properly investigate the seemingly endless number of training features. One interesting new one, however, is Power Guide, a tool (which requires an accompanying power meter) that helps riders map out their effort on a specific downloaded course. By crunching your FTP (Functional Threshold Power, or the highest average power you can sustain for approximately an hour, measured in watts) with the course’s elevation and the projected time of finishing, the device will map out a strategy to hit your target, sort of like a coach on your handlebars telling you exactly how fast and hard you need to be riding with every pedal stroke.
Additionally, riders can sync training plans with apps like TrainingPeaks ; set nutrition and hydration alerts that remind them to eat and drink at time-allotted intervals; scroll to screens that assess how your body is holding up to variations in heat and altitude; track mountain biking metrics like jump count, jump distance, and hang time; and choose from daily suggested workouts.
I found a few glitches, namely that pop-up notifications like texts transmitted from smartphones are hard to read. Also, the waterproof device’s touchscreen seemed at times hypersensitive to sweat or rain. When inundated, the drops would cause the computer to switch screens.
$750 at Garmin $750 at Amazon Photograph: Wahoo Fitness The Best Mid-Priced Option Wahoo Fitness Elemnt Roam (2022) Wahoo offers two solid cycling computers: the $300 Elemnt Bolt , a sleek, small, aerodynamic unit designed for racing; and the larger Elemnt Roam, about the size of a pack of Marlboros, that’s designed for way-finding. The Roam had been on the market for three years when it was updated in October 2022. I've been testing this new version.
The newest iteration of the Roam, which looks exactly like its older sibling, offers dual-frequency GPS. The oversimplified explanation: dual frequency allows the GPS unit to operate on two frequency bands instead of one. Single-frequency GPS devices offer accuracy within 15 feet. Dual-frequency GPS devices offer accuracy within centimeters.
Where can this make a difference? Say you’re bikepacking on poorly maintained singletrack through an aspen forest in the Rockies. With single-frequency GPS, objects like towering trees can block or confuse the signal, which can create route inaccuracies, which can get you lost. That might not be a big deal in an urban setting where you can stop at the local coffee shop to ask for directions. But in the wilderness, getting off track by 15 feet might mean making a crucial error.
With the strengthened dual signal, turn-by-turn navigation prompts for all maps of any file types—either preloaded or uploaded via apps like Strava, Komoot, or Ride with GPS—are spot-on accurate. Should you somehow make a wrong turn, there’s a rerouting feature that will quickly get you back on track. If you’re really lost, the “breadcrumb” feature navigates you back to your starting point even if the device is offline.
Also new: “The Summit,” color-coded gradients in the grade data field and elevation chart when riding a third-party route or Strava segment. No wonder that Forest Service mountain road seemed ruthless and endless: You can now see that it had a 13 percent grade.
I liked the Roam’s easy-to-read screen, which uses an ambient light sensor to auto-adjust the LED backlighting. Instead of a touchscreen, there are three bottom buttons that let you scroll between customized screens like the main map, nearby Strava segments to tackle, and the home dashboard. That dashboard includes miles per hour, miles ridden, clock, ride time, heart rate (when paired with a heart rate monitor), revolutions per minute (when paired with a power meter), and average miles per hour. By pushing the button on the lower right, you can zoom in or out on the dashboard, an excellent feature for aging eyes.
Battery life is 17 hours on the newly upgraded Roam, roughly the same as on the old model. That level of stamina pales in comparison to the Garmin 1040 Solar , but the Wahoo is still a solid choice for any endeavor under that time limit. With an expanded 32 GB of memory, there’s more room to save favorite routes, detailed maps of new places, up to five structured workouts from Wahoo, as well as planned workouts from partner apps like TrainerRoad, Training Peaks, and Today’s Plan.
One of my co-testers found the included handlebar clamp too hefty, with the Roam locking into a plastic frame almost as big as the device itself. The computer is unlikely to break or slip out of position while riding, but the extended plastic bracket feels like it could snap in half in a crash.
$400 at Wahoo Fitness Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Hammerhead Another Good Mid-Priced Option Hammerhead Karoo 2 Hammerhead was born in 2013, the brainchild of CEO Piet Morgan who, on a 3,000-mile ride across the US, realized that his cycling computer was falling woefully short of his needs. The key two factors of the company’s Karoo 2 is that its touchscreen is as intuitive as the one on a smartphone, and that the device is designed to get dirty, with features like “droplet rejection” that, when enabled by double-tapping a button, will lock the touchscreen to stop interference from mud and rain.
At 4.6 ounces (without the mounting hardware), the Karoo 2 is slightly larger and heavier than the Elmnt Roam, but it also has an impressively anti-glare 3.2-inch color screen that I found was the easiest to read of all the devices—a key feature, especially for cyclists with aging eyes. In addition to basics like speed, distance, and elevation, the Karoo 2’s graphic data fields include dynamic heart rate and power zone, upcoming and historical elevation, and electronic gearing (if the computer is connected to the appropriate sensors on your bike).
Another key element to the Karoo 2 is on-the-clock biweekly software updates that are accompanied by detailed emails explaining what each update accomplishes. For example, I got an update back in August that was an Improved Tire Pressure Sensor Configuration, which allows riders to configure front and rear wheel target pressure and target pressure range straight from the device. Some of these updates may not seem essential, but it’s good to know when new features flow in so you don’t make the mistake of thinking it’s outdated.
With 12 hours of battery life and 32 GB of storage, the device has plenty of juice for long efforts and enough room in its brain to download plenty of map data. One feature that my enduro-racing tester appreciated was that it “has all the bells and whistles of other similar devices,” like integration with Strava, “but it has a much simpler, intuitive, overall feel.” One issue he encountered: While out riding, the unit randomly reset to factory mode a few times. It could have been the result of accidentally pushing a few buttons, but a frustrating endeavor nonetheless because the day’s data was lost, and resetting the computer required a good Wi-Fi connection and additional time.
$399 at Hammerhead $399 at Backcountry Photograph: Garmin Best for Ebikes Garmin Edge Explore 2 Ebikes already track your battery status, assist level, and range. But their onboard computers aren’t smart enough to route you the best way home before you burn through your battery. For cyclists riding an ebike compatible with Shimano Steps or ANT+ technology, that’s where this handy device comes in: The Explore 2 has a dedicated ebike status screen that gives smart routing and range alerts based on battery status, assist level, and your planned course.
The device, which weighs 3.7 ounces without the mounting hardware, tracks your whereabouts with GPS. It also has many of the standard features found in Garmin’s higher-end models like the 1040 Solar and 1040, including a touchscreen color display and a multitude of safety and tracking features, including live ride tracking and incident detection. It also has weather alerts, bike alarms, and compatibility with an InReach Satellite system for emergency text communications in the backcountry. Something city commuters will find handy is that the Explore 2 is compatible with Garmin’s Varia rear-facing radar , which allows cyclists to view on their screen the real-time distance of an upcoming vehicle. The computer can also control Garmin’s powerful lighting system , which can be turned on and off automatically via the GPS device if you want.
There are a few advanced features in Garmin’s higher-end models that the Edge Explore 2 does not offer: the ability to sync maps and data over Wi-Fi, support for Strava Live Segments, downloadable workout support, and some training and recovery metrics. Its battery life is also limited to 16 hours. Lastly, I found that while the device is impressive overall, its 3-inch screen was harder to read than units of comparable size.
$300 at Garmin $300 at Amazon Topics cycling fitness Bicycles GPS buying guides Shopping Simon Hill Jaina Grey Simon Hill Jaina Grey Ryan Waniata Simon Hill Brendan Nystedt Simon Hill WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,064 | 2,023 |
"Best Bike Accessories (2023): Helmets, Locks, Pumps, Rain Gear, and More | WIRED"
|
"https://www.wired.com/story/best-bike-accessories"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Matt Jancer Gear The Best Bike Accessories Save this story Save Save this story Save Bikes are fantastical machines. Ideal companions, they never complain and they never ask you, “Are we there yet?” An all-day pleasure cruise or a grueling workday commute are no big deal. They return to us far more faithful service than the occasional care we pour into them. That said, most bikes arrive from the factory ready for a casual Sunday joyride but not much else. If you want to put your bike to work hauling cargo or commuting to the office, you'll need some bike accessories to make those journeys comfortable and fun.
Lucky for you, most bicycles are highly and easily customizable, and there’s a mountain’s worth of gear to choose from. Practically all of these accessories will work for non-electric bikes and most electric bikes, too. Take a look at our guides to Ebike Classes and Best Electric Bikes for more.
Updated August 2023: We've added the Lezyne Matrix Saddle Tagger, ODI Rogue Grips, PDW Alexander Graham, and Mile Wide Fork Cork. We've also swapped out a few products for similar models, and updated pricing and availability.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
For More Comfort Cargo Carriers Bad-Weather Gear Safety First Security Equipment Maintenance Gear So many things these days are a pain in the back. Riding your bike doesn’t have to be one of them. Swapping out handlebar grips, seats, and even seat posts are some of the easiest modifications you can make that’ll significantly improve your ride.
Photograph: Ergon $30 at Amazon $35 at REI Poor wrist posture can lead to carpal tunnel syndrome or cyclist’s palsy, where you're putting pressure on your median and ulnar nerves, respectively. The ergonomic Ergon GA3 are my favorite bike grips because they have small wings that correct your wrist posture to prevent these conditions. Even after long rides, I find my wrists don't have the soreness that I used to suffer from.
Photograph: Brooks $111 at Amazon $150 at REI I haven’t found any cheap or heavily padded gel aftermarket saddles to be much improvement over the seats that come with bikes. The Brooks B17, an old-school legend, is ultra-comfortable despite its stiff leather construction—or perhaps because of it. I've spent hours in its saddle without obtaining the sore spots that accompany riding in soft gel seats. Like a good chair, firm support is more important than pure plushy softness. These saddles are also rugged; they usually last for a decade or more. If you don’t do leather, Brooks makes a nylon option for $130.
Photograph: Amazon $250 at Amazon $250 at Cirrus For some extra shock absorption over rough roads, you can add a suspension seatpost to a fixed, hardtail bike. Some reviewers found its dual coil spring suspension bouncy, but I didn't have that issue at all. Make sure when you're buying the Kinekt that you're buying the right springs for the rider's body weight.
ODI Rogue Grips for $33 : Rogues are such a mountain bike classic that it seems half the companies out there are making clones of them. With a big, knobby rubber texture, they have grip in spades. Personally, I'm not a huge fan of using them barehanded, but if you like mixing a little off-road into your trips or ride with gloves (or just aren't as bothered by them barehanded as me), then they should do the trick.
REI Co-op Link Padded Liner Shorts for $35 ( Women's Sizing , Men's Sizing ) : These add an extra soft layer between rider and machine on longer rides and wick sweat away to keep you from feeling clammy. The chamois padding helps provide comfort on longer rides, too, or for bike saddles that lack sufficient cushioning, as many bikes' standard seats typically do.
Few bikes come with the attachments needed to carry cargo on errands and grocery runs. Whether you wear a backpack or a pannier bag—a style of bag that attaches to a luggage rack that you install over one of your wheels—make sure that you can get real work done by turning your bike into a cargo hauler.
Photograph: Amazon $35 at Amazon If your bike doesn't already have a pannier rack, you'll need to install one if you want to use pannier bags. The Explorer fits most bikes (with and without disc brakes) and carries up to 55 pounds. It only weighs 1.5 pounds, too, so it won't noticeably weigh down your bike. The wide gaps between the deck and outer bars makes attaching and detaching pannier bags a breeze.
Photograph: Herschel $65 at Amazon $80 at Herschel The Heritage was named the best budget bag in our guide to the Best Laptop Backpacks for its padded laptop sleeve that can fit laptops of up to 15 inches and for its tough, 600-denier polyester fabric. After using hers for years, my colleague says it's barely showing any signs of wear.
Photograph: Portland Design Works $102 at Amazon $99 at Portland Design Works If you need to lug around more than the Topeak's 55-pound limit allows, check out this beautiful steel-and-bamboo cargo rack that holds up to 77 pounds. It weighs 3 pounds, but the construction is rock solid. You can mount any standard tailbag or pannier bag to it, as well. The Loading Dock for $115 weighs a pound less and holds up to 35 pounds, thanks to its aluminum construction, if you'd rather save some weight but keep the gorgeous looks.
Handlestash for $38 : Ever try to carry a cup of coffee (or any other drink) home from the café on your bike? We can't recommend going far while holding it in one hand and riding with the other. Unlike a regular cargo basket, the Handlestash's loose fabric and integrated springs absorb enough vibrations to hold a cup of coffee or can of soda without splashing it all over the road. The Gear Team's commerce director Martin Cizmar hasn't taken it off his bike in over a year.
Miles Wide Fork Cork for $29 : The head tube—that vertical pipe linking your handlebars to your front axle—is free storage space. The opening near the tire is almost always open. The Fork Cork is designed to plug up the end of it to keep the inside of the tube free from mud and road debris and, more crucilly, give you a discrete, watertight place to store spare parts, tools, candy bars, and whatever else. You need a tapered steering tube for it to work, and it's designed for mountain bikes with enough clearance between the tire and head tube to get your hand between them.
Rad Power Rad Trailer for $299 : Need to carry a seriously bulky or heavy load? It's best to pull it. This steel bike trailer (with a polymer deck) weighs 25 pounds and can hold up to 100 pounds. Senior associate reviews editor Adrienne So paired it with the soft-sided Rad Trailer Pet Insert for $229.
Together, the combination can transport any pet weighing up to 84 pounds.
Banjo Brothers Grocery Bag for $60 : It holds up to 1,100 cubic inches of storage in a rectangular form that maximizes carrying space. That's large enough for one stuffed grocery bag, but you can always add a second one to the other side of your pannier rack to double your carrying capacity. When not in use, it folds flat against your bike. If you plan to carry your laptop, put it in a water-repellent, padded Incase Laptop Sleeve for $45 to protect it from drizzles, splashes, and impacts.
Wald Basket for $46 : This popular, basic option mounts easily onto the front of your handlebars. Even though it looks just as good empty as it does full, you can't fold it away when it's not in use. The REI Co-op Beyonder Soft Folding Basket for $40 requires a front rack, but it has carrying straps so you can take it into stores with you, and it folds flat when you're not using it.
If you ride enough, you're going to get caught in a storm from time to time, but you don't have to ride soaked and miserable. With the proper rainwear and protective equipment, you can keep yourself (mostly) dry and make riding in the wet a bearable, if not pleasurable, experience.
Photograph: Portland Design Works $21 at PDW These environmentally friendly fenders are made from 97 percent post-recycled bottles and are incredibly easy to pop on and off the bike. They don't provide as much coverage from wet road spray that full fenders provide, but they're easy to take off when the skies are sunny. As long as your bike has a hole in the fork crown, they'll likely fit. There are two versions: MTB (65mm) for bikes with wide tires and and City (48mm wide) for bikes with narrow tires. Make sure you get the right one.
Photograph: Portland Design Works $129 at PDW $129 at REI They're pricey, but I've found that with bike fenders, you tend to get what you pay for. The PDWs provide fuller coverage than a lot of competitors that don't extend as low to the ground, and their aluminum construction is tougher than plastic fenders, with hardly any extra weight. If your bike doesn't have eyelets for fenders, these come with extra hardware you can use to mount them.
Photograph: REI $100 at REI (Men's) $100 at REI (Women's) This hardshell rain jacket will keep your upper body dry during a rainstorm. The women's sizing sells for the same price. Take a look at our guide to the Best Rain Jackets for more picks.
Photograph: Planet Bike $11 at Amazon Cover up your saddle if you know it's going to rain, and you won't have to ride home with wet pants. The Planet Bike cover's elastic drawstring cinches down tight over the seat so that it doesn't threaten to blow off, like some seat covers. Some people use disposable grocery bags, but they tend to need constant replacing, and they can blow away and become litter.
Few American cities are designed with bicycle infrastructure at the top of city planners' minds. And even when you do find yourself in a blessedly welcome bike lane, you have to contend with other cyclists, scooter pilots, and pedestrians. Make sure you're visible with a light and keep that noggin protected with a helmet.
Photograph: REI $80 at Amazon $80 at REI Swaddle your melon with all the protection you can get. Seriously, a trip in the back of an ambulance is much less comfortable than today's well-vented and nicely padded helmets. And stylish, when you're talking about Nutcase. This helmet comes with MIPS, meaning Multi-directional Impact Protection System, which allows the inner liner of the helmet to rotate within the outer shell, reducing the likelihood of rotational brian injuries in the event of a crash.
Photograph: Nutcase $150 at REI The Vio ( 8/10, WIRED Recommends ) has LED lights built-in 360 degrees around the helmet to improve visibility on the road so that you don't need to put separate headlights and tail lights on your bike. It comes with MIPS, too, which means that it can rotate slightly to dissipate the rotational impact force of a crash, and its front light's 200 lumens is good enough to see down city streets, if not completely deserted country roads. It only runs for three hours before you need to recharge it via a mini-USB cable, though. If you're planning on hopping onto an ebike, the Bern Hudson ($140) is rated for up to 27 mph, which is just about as fast as a class-3 ebike can legally go at full speed.
Kryptonite Incite X3 and XR Set for $80: The 30-lux headlamp and 0.06-lux tail lamp aren't the brightest on the market, but they're enough to make sure motorists, cyclists, and pedestrians notice you. They're USB-rechargeable and last for up to 24 and 36 hours on a charge, respectively. For a more compact, convenient alternative, So has been a big fan of the Thousand Magnetic Head Light for $35.
It's USB-C-rechargeable and clamps quickly onto any standard handlebar. Just pop the little 2-ounce light off and into your pocket when you head indoors.
Bookman Fabric Reflective Stickers for $10 : Lights are important for being seen, but an easy way to pick up extra visibility on the cheap is to add reflective stickers to catch cars' headlights. You can stick them on your bicycle, or you can do like senior associate reviews editor Adrienne So and stick some on your cycling clothes.
Portland Design Works King of Ding II Bike Bell for $25 : If you want a polite way to tell people to get out of your way or just give nearby bikers and pedestrians a heads-up, get a bell. (Many states require them.) There's something charming about its classic “ding!” that makes it pleasant—although attention-grabbing—to hear. The Alexander Graham for $28 is the same basic bell, but it allows you to save valuable handlebar real estate by replacing a spacer on the steering tube. That makes it a bit more thief-proof too, especially if you have a locking top cap. Both bells are almost painfully loud and produce a stunningly clear, long-ringing “ding” with each flick of the striker.
Park Tool Rescue Tool for $34 : You could just pick out the necessary hex keys that fit your bike bolts and carry them in your pocket or pannier bag, or you could get a pocketable, bike-specific set like the Rescue Tool. Its 16 included tools fold into a compact package that you can slip into a bag or pocket when you head out for a ride.
Make sure your bike stays your bike with the right locks, GPS trackers, and security bolts. Check out my guide to the Best Bike Locks for more picks and additional tips on how to secure your bike.
Photograph: Amazon $66 at Amazon $67 at Walmart No lock is going to deter the most determined thief with an angle grinder, but at least half the battle of security is making your bike a less attractive target. At 2.9 pounds, the KryptoLok strikes a healthy balance between reasonably light weight with adequate (but not top-level) security. It also comes with Kryptonite's Transit FlexFrame bracket, which lets you mount the lock to your bike's frame for easy transportation around town.
Photograph: Amazon $60 at Amazon For the highest level of security on a bike lock that you can take with you on rides, upgrade to the Granit X-Plus 540. Both ends of the U-bar lock into the cylinder, so in order to grind through this lock a thief would have to do it twice—once on either side of the thick, 13-millimeter-thick bars. Thieves don't like to spend a long time thieving, as it means more chance of being caught, so this is top-notch security.
Lezyne Matrix Saddle Tagger for $17 : Always forgetting where you parked your bike? Worried somebody will walk off with it? Stick an AirTag or Tile tracker under your bike's saddle with this inconspicuous, waterproof tracker mount. Unlike dropping a tracker inside a bike frame or metal mount, the Lezyne's plastic construction gave me no issues with AirTag's range or accuracy. It comes included with a security Torx bolt and took less than a minute to install.
Abus Steel-O-Chain 9809 for $85 : If you lock up at awkward spots, such as fences and railings, you might need something longer than a U-lock. Even though it's heavy at 5.5 pounds, it was plenty flexible and long enough to tie up anywhere, and even around thick-frame ebikes like the Super 73 that won't work with U-locks.
Invoxia GPS Tracker for $129 : Rather than try to shove a Tile tracker inside the frame, you can purchase a stand-alone bike tracker that relies on GPS rather than Bluetooth for much wider coverage. The Invoxia syncs up with a smartphone app to show your bike's location and alert you if it moves, and it lasts from 15 to 49 days on a single charge. The price includes one year of wireless data coverage (additional years are $30 each).
Security bolts.
Bikes use common bolts to make maintenance and assembly easy. It's an unfortunate side effect that using standard bolts makes it easier for thieves to steal the valuable parts off your bike when it's parked. Replace the bolts on the most vulnerable parts (seat post, saddle, handlebars, and wheels) with Pitlock or Hexlox security bolts. The bolts are individually keyed and can be unfastened by a personalized tool that only you own. Thieves hate these things. Secure your front wheel first, then move on from there.
Keeping your bike on the road is usually just a matter of keeping the tires properly inflated and the chain well lubricated. But slack on maintenance, and you could eventually be looking at a repair bill. Fortunately, maintaining a bike is very easy. (Your local shop or REI also offers yearly tune-ups at a reasonable price.) Photograph: Lezyne $70 at Amazon $70 at Backcountry Metal pumps are worth the expense over plastic pumps, which don't tend to last very long. The Lezyne's parts are steel where it counts. It works with the three common valve types (Presta, Schrader, and Dunlop) and inflates tires up to 220 psi, which is well more than enough for most road tires. It's effortlessly quick to change valve adapters, the psi gauge is clear to read without stooping over, and it doesn't take too many pumps to fill a tire.
Photograph: REI $14 at REI $14 at Backcountry You've got to keep the chain clean to keep it functioning correctly. With three adjustable-width brush heads, scrubbing my bike chain took far less time with the Grunge Brush than a typical straight brush, and I got into the chain's nooks and crannies better, especially on the side that faces the bike frame. I use a Grunge Brush on my motorcycles, too, but I switched over to this version that has a narrower brush for bicycle's narrower chains because it takes less finagling to get it to clean three sides at once.
Park Tool Bicycle Chain Cleaning Kit for $40 : You're going to need to periodically clean the bike chain to keep it from gunking up and malfunctioning. This kit includes a brush and a bottle of cleaning solution, in addition to the cleaning tool itself.
Feedback Sports Sport Mechanic Repair Stand for $180 : Sooner or later, you're going to need to work on your bike with the wheels off the ground. Before you think you'll just get cute and save a buck by balancing the bike on a box, take it from me: it'll fall, and either you or the bike will end up hurt. It's happened to me. This stand is steady, with three feet versus two, and has a sturdy clamping mechanism with adjustable height.
Finish Line Dry Lube for $10 : The chain needs to stay lubricated to work properly. Every so often (and after cleanings), spray it with the little dry lubricant, which is slightly less messy than the old-fashioned lube. Wash your hands after using this stuff; it has Teflon in it.
Finish Line Brake Cleaner for $9 : If your bike has disc brakes instead of pull-brakes or calipers, you're going to need to clean the brake hardware periodically to keep your stopping performance from degrading. This stuff removes stubborn brake dust, which is difficult to remove without purpose-made solvents.
Sram Disc Brake Bleed Kit for $55 : For years, hydraulic braking systems (operated by fluid) were found only on high-end bikes. In recent years, though, they've begun to trickle down to mid-priced bikes, especially on bikes with electric motors. They provide smoother stopping but require the owner to replace the fluid regularly. You need a special bleeder tool, such as this one, to replace fluid. This kit comes with a bottle of brake fluid, but if you need more, a 4 fluid-ounce bottle of Sram 5.1 Dot Fluid for $14 should do the trick.
Feedback Sports Velo Hinge Bike Rack for $32 : Whether you stash your bike in a cramped apartment at night or in a garage, you could always stand to free up a little more room. It was easy for me to mount the Velo using three anchor bolts in a wall. It holds up to 50 pounds, and once mounted the bike could be swung nearly flat against the wall and out of the way.
Gear The Best Home Depot Black Friday Deals Matt Jancer Gear Apple’s Pledge to Support RCS Messaging Could Finally Kill SMS Boone Ashworth Gear Wish List: 47 Awesome Gifts for All the Enthusiasts, Connoisseurs, and Fanatics in Your Circle WIRED Staff Gear The PlayStation Portal Turns Your PS5 Into a Handheld, Sorta Eric Ravenscraft You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Writer and Reviewer Topics bikes e-bikes gear Shopping cycling Bicycles buying guides Nena Farrell Martin Cizmar Scott Gilbertson Matt Jancer Medea Giordano Adrienne So Chris Haslam Medea Giordano WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,065 | 2,023 |
"Niu KQi3 Max Review: A Reliable Escooter | WIRED"
|
"https://www.wired.com/review/niu-kqi3-max"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Julian Chokkattu Gear Review: Niu KQi3 Max Facebook X Email Save Story Photograph: Niu Facebook X Email Save Story $1,000 at Target $999 at Amazon $1,000 at Walmart $1,000 at Best Buy If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 7/10 Open rating explainer I test smartphones and electric scooters among many other products here at WIRED. Unlike phones , escooters vary much more in quality. Most phones nowadays are pretty good—whether you buy from the low-end or shell out for a flagship—but escooters haven't reached this level of development yet. Each massive box I have to haul up my stairs isn't guaranteed to give me a thoroughly enjoyable and pain-free experience. That's why I like Niu. The KQi3 Max is the second scooter I'm testing from the brand and, like the first, it's a reliable, well-balanced ride for everyday commutes.
The KQi3 Max is a small upgrade over the KQi3 Pro I tested last year. They're nearly identical, from the design to the components, but the pricier Max has a slightly more powerful motor, weighs a smidge more, and has a larger battery capacity. The Pro is enough for most people, but if you're in a hillier area or you're a heavier rider, it might be worth spending the extra $200 on the added power.
The KQi3 Max comes mostly assembled; you just need to attach the handlebars. Right off the bat, it looks and feels sturdy, with an air of intent. It's not as light as a scooter you pluck off the shelf, like the Speedway Mini 4 Pro , nor is it as fancy and hefty as the Apollo City.
It has a purpose.
The handlebars sit at a nice spot for my 6'4" self, but you can't adjust the height, so it may not be comfortable for everyone. They're not as wide as the Apollo City's, but I still wish they could collapse down to save some width when you pack the scooter down. There's also not much room to comfortably attach a smartphone via a mount, though I've started using my wireless earbuds to listen to navigation instructions instead of having to look down at a screen.
Speaking of, Niu has the best folding mechanism out of all the scooters I've tried. Just undo the latch at the base of the stem and bring it down, and it'll automatically click into a spot at the end of the deck. Time to unfold? Press the button above the rear brake light and the stem will unlock. Raise it and close the latch to secure it upright. It's super simple. It's got a reliably stable kickstand too.
Photograph: Niu At 46 pounds, this escooter is not something most people can easily carry, but it's still not unreasonable for me. I definitely wouldn't want to carry it up more than three flights of stairs, though. I do wish Niu would try and shave down the weight while preserving the power of this machine.
There's a bell, a reasonably bright headlight, and a clear display that shows battery level, speed, and other ride data, but at this price, I'd expect to see turn signal buttons. It's also IP54 water resistant, so it can handle splashes of water just fine. Just remember not to ride it in the rain, and wait for it to dry before you plug it in to recharge.
When you initially set up the scooter, you'll be restricted to a lower speed. Ride a short distance and you'll automatically unlock the faster speed mode (up to 20 mph). To unlock the top speed of 24 mph, you will need to choose the custom speed mode in the app.
The app itself isn't cumbersome, even if it is an annoying extra step to ask users to download an app to unlock the scooter's speed.
You can also tweak the amount of regenerative braking you want and toggle on features like Cruise Control or the locking mechanism. But the Max doesn't immediately connect to my phone via Bluetooth when I turn it on; it requires some prodding by refreshing the app.
Upgrading from a 350-watt motor on the KQi3 Pro to a 450-watt motor on the Max means you get a little extra power to work with. This escooter is really responsive when you hit the throttle, so it can climb to 20 mph fairly quickly. There's no dillydallying when you punch it at a stoplight. It does a great job sustaining high speeds when tackling slopes, too. It had no trouble climbing the Williamsburg Bridge and the Manhattan Bridge here in New York City and maintaining speeds at 15 mph or higher.
The dual disc brakes do a good job of quickly coming to a halt, which I learned when a car in front of me decided to make a right without checking the bike lane. (Yes, I yelled, “Ey, I'm scootin' here!”) The suspension system in conjunction with the 9.5-inch tubeless tires is solid—it can handle most bumps and small potholes fine, but it's not going to knock your socks off.
Niu KQi3 Max Rating: 7/10 $1,000 at Target $999 at Amazon $1,000 at Walmart $1,000 at Best Buy If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The best part of the KQi3 Max is its range. It has been one of the more reliable sub-$1,000 scooters I've tested as it can go roughly 16 miles on a single charge. Now, keep in mind that I'm a 6'4" human who weighs 230 pounds. Most people should be able to easily hit 20 miles, if not more, riding the Max. My results were slightly better than the Niu KQi3 Pro, but almost imperceptibly so.
There's a bit of a caveat with this range though. I took it from Bedford-Stuyvesant to my doctor's appointment in Midtown Manhattan—a 50-minute ride over two bridges. Going there, I cruised at 20 mph, but I arrived with less than 50 percent in the tank, so I switched to a custom 15 mph speed mode for the ride home and had to walk a few blocks to my front door. You might find yourself having to tweak the speed if your journeys are a bit long.
A nearly 7-mile ride at 20 mph to and from my barber shop brought the Max down to 58 percent, if that helps with an estimate. But again, terrain, rider weight, and road conditions are all important factors to consider. (The KQi3 Max also comes with a bulky charging brick and takes about seven to eight hours to fully recharge.) The biggest flaw with this escooter is changing the level of assistance. On the Max, you can choose between E-Saver or Sport modes. The former limits you to a criminally low 9 mph and the latter unlocks the top 20 mph speed. I wish there was a happy medium preset that let you ride at 15 mph. You can set a custom speed in the Niu app, which is what I did, but this replaces your other speed options, so you need to toggle it off in the app every time you don't need it anymore. It's bizarre.
Still, the flaws are relatively small for an otherwise good escooter. The cheaper KQi3 Pro is likely all you need, and the Speedway Mini 4 Pro is worth considering if you're willing to spend this much, but the Niu KQi3 Max is reliable and dependable.
Niu KQi3 Max Rating: 7/10 $1,000 at Target $999 at Amazon $1,000 at Walmart $1,000 at Best Buy If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $1,000 at Target $999 at Amazon $1,000 at Walmart $1,000 at Best Buy Reviews Editor X Topics Shopping review scooters outdoors Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,066 | 2,021 |
"Apollo Ghost Review: So Powerful, It's Scary | WIRED"
|
"https://www.wired.com/review/apollo-ghost"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Julian Chokkattu Gear Review: Apollo Ghost Facebook X Email Save Story Photograph: Apollo Facebook X Email Save Story $1,599 at Apollo If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 8/10 Open rating explainer Exhilarating and frightening.
That's what it feels like riding the Apollo Ghost. This dual-motor electric kick scooter from the Canadian company Apollo Scooters is so powerful you'll feel your soul lurch out of your body as you hit the throttle. That's probably where the thing gets its name.
Seriously, it's easy to creep close to 40 mph with both motors engaged. The problem? Those speeds are illegal here in New York City where I live; escooters are only allowed to go up to 15 mph in bike lanes.
In fact, most states cap speeds between 15 and 30 mph. The onus is on the rider to make sure speed limits aren't ignored.
This much power is overkill for most people. The $1,499 price tag is too high for most people as well. Still, the Apollo Ghost is one of the most well-built scooters I've ever ridden, and it glides ever so smoothly on all but the worst roads.
You won't need to do a ton of setup before taking that first Ghost ride, but it might depend on how rough the shipping process was on the box.
My test unit had two missing screws that were meant for securing the ignition switch and the LED display to the handlebars (they're loose on purpose to prevent damage during shipping). Thankfully, after digging deep into scraps of cardboard, I found them hiding between the flaps.
Whew.
Apollo says I had a preproduction unit, so this shouldn't happen with retail models.
This handy setup video from Apollo's YouTube channel is easy to follow, though a written user guide is included. But both the video and the manual have a missing step: attaching the handlebars to the stem. It's not difficult to figure out, but it did throw me off. For what it's worth, Apollo has a customer service team you can email or call if you need help, and the company says it's going to edit the video to include this step.
The Ghost folds down, making it easier to store.
Photograph: JULIAN CHOKKATTU Next, just tighten the controls on the handlebars, and that's it! The Ghost requires a key to be inserted into the ignition and the LED display to be turned on for it to start. It's a shame it requires two steps instead of just the key, but that's just me nitpicking.
What might be a little confusing is the second display next to the ignition. It shows the battery's voltage level, and if the Ghost is fully charged, it should read around 58 volts. When it's nearly dead, it'll sit close to 44 volts—not the most intuitive way to signal the low battery level. There's a more traditional battery bar on the odometer, which also shows data like speed and distance traveled, but I found it more useful to remember these two voltage numbers to gauge the remaining battery life. I wish both displays were brighter though; they're tough to read on sunny days.
Generally, I've been able to get a little under 20 miles out of the scooter before needing to recharge it, but that range fluctuates due to a variety of factors including speed, road condition, and rider weight. The scooter does take 12 hours to fully recharge, so I usually left it plugged in overnight after long rides. Apollo sells a fast charger for $99 that cuts that time in half, but frankly, that should be included at this price.
Apollo Ghost Rating: 8/10 $1,599 at Apollo If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED At night, your own visibility isn't an issue. Two LEDs sit at the front of the deck—they're not enough to light up much of the road ahead, but they pair with a strip of LEDs underneath the deck and light you up enough to make you difficult to miss in the dark. The brake lights are, thankfully, brighter. There is a built-in bell too.
The Mode button on the throttle is how you cycle through the Ghost's three gears. Selecting a specific gear gives you an easy way to loosely regulate your top speed: Gear 1 maxes out around 16 mph, Gear 2 hovers at 25 mph, and Gear 3 can hit the top speed of 38 mph (if both motors are employed). The button itself is a little unsatisfying to press, so rather than frequently switching gears, I often left it on the first or second gear.
The Ghost has this sci-fi aesthetic with all its wires, various buttons, and displays scattered about on the command center. It feels a little like the jet bike from Looper.
And like most sci-fi vehicles, there's a big red button that's just begging to be pressed.
The Ghost's cockpit.
Photograph: JULIAN CHOKKATTU The scooter has two 800-watt motors that can deliver 1,000 watts of peak power each. The red button switches between single- and dual-motor operation. With the former, I usually cruised at 18 mph and could effortlessly go up to 25. But with dual motors, I felt like Will Smith right after he pushed the red button in Men in Black.
Really. I was able to accelerate from zero to 25 miles per hour in roughly six seconds. (The button is also so satisfying to push.) My entire body lurched back when I hit the throttle with both motors engaged, so … be gentle! Gaining speed that quickly feels exhilarating but it's also terrifying. It doesn't take long to rocket past 30 mph. That might not sound like much if you're used to going that fast in a car, but when you're balancing upright on a scooter and all you've got for protection is a helmet on your head—let's just say my heart was racing.
Apollo Ghost Rating: 8/10 $1,599 at Apollo If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED I'm also in New York City. Unless I'm riding over the Williamsburg bridge, I usually had to hit the (effective!) disc brakes every few minutes due to traffic lights, cars, or pedestrians. The opportunities to ride faster than 20 mph are slim. Still, it's nice having this much power to draw from.
One thing to drill into your head is to never switch between dual to single motor while riding. The company says “it's like downshifting from sixth gear to first gear in a car, and can lead to a fall or injury due to the heavy deceleration.” Yikes. After I read that, I never pressed any of the buttons until I came to a full stop out of caution.
The orange button next to the red Single/Dual button switches the Ghost between Eco and Turbo mode. The Turbo button just lets the scooter hit top speed on demand. Eco, of course, increases the motors' efficiency. It makes your rate of travel noticeably slower, but it's handy if the Ghost is creeping toward a dead battery and you still have a long ride ahead.
Most importantly, whatever the speed, the ride itself is very comfortable. The 10-inch pneumatic tires paired with the dual-spring suspension system make it feel like you're gliding over most roads, and even pot-hole-ridden streets don't feel too rough. (I don't recommend it for off-road use.) It is IP54 water resistant, and that level of protection did the job in light rain as well as slush after it snowed in January, though the fenders didn't do much to protect my shoes from getting wet and dirty.
The brakes supposedly feature regenerative braking, meaning they'll recharge the battery as you come to a halt. I didn't notice any significant battery gains though.
Folding up the Ghost at the end of a ride is simple, but not as speedy as I'd like. You need to spend a few seconds twisting a rod between the handlebars to tuck them down, and the clamp at the bottom of the main stem that enables the folding mechanism requires some force to undo. You can bring the stem down and secure it to a hook near the back of the deck to keep it in place. It packs down into a storable size, but it's still too tall to fit under the couch.
Worse yet, it's a 64-pound machine! That's heavier than this folding fat tire electric bike.
Don't expect to easily tote this e-scooter around.
Photograph: Apollo Apollo Ghost Rating: 8/10 $1,599 at Apollo If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED If you're spending this much on an electric scooter, it's important to make sure it won't conk out after a year. After four months of use, the Ghost still works just as reliably as my first day with it.
Apollo only offers a standard one-year warranty on the scooter, but it claims the battery on the Ghost can last four years before needing to be replaced. You can order a replacement from the company, and there are other spare parts you can buy. The company has also partnered with service centers in New York City, San Francisco, New Orleans, and Golden, Colorado, if you need professional help.
Considering I spent most of my time cruising with just the single motor, I'd say the Ghost is best for folks who can travel for long stretches without much interruption to make use of those high speeds. (As long as it's legal!) Otherwise, it's overkill for cities. Its weight makes it a difficult proposition for anyone in a building without an elevator too.
Apollo has several cheaper scooters, including the upcoming Apollo Air Pro , which is much lighter, and the top speed of 18 mph makes it a better choice for densely-packed urban environments.
Nevertheless, the Apollo Ghost does everything it's made to do really well. It's built like a tank, has incredible raw power, and reliable range. Just … brace yourself before you hit that red button.
Correction: We've updated the article to clarify the NYC e-scooter speed limit is 15 MPH, not 30 MPH.
Apollo Ghost Rating: 8/10 $1,599 at Apollo If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $1,599 at Apollo Reviews Editor X Topics Shopping scooters outdoors review Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,067 | 2,023 |
"‘Black Mirror’ Creator Charlie Brooker Wants to Break the Content Machine | WIRED"
|
"https://www.wired.com/story/black-mirror-charlie-brooker-q-and-a-season-6"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Amit Katwala Culture Black Mirror ’s Charlie Brooker Wants to Break the Content Machine Facebook X Email Save Story Courtesy of Michael Wharley/Netflix Save this story Save Save this story Save By the end of the pandemic, Charlie Brooker had almost run out of murderers.
Like a lot of people, the creator and writer of Black Mirror spent much of the Covid-19 lockdown “hoovering up one true-crime documentary after another.” By the time things returned to something like normal, he’d exhausted his supply of moody, atmospheric six-parters about ghastly killings and had come up with an idea for a new episode of his darkly funny, scarily prescient, and hugely popular Netflix anthology series.
Culture Guides Matt Kamen and WIRED Staff Flop Era Kate Knibbs Dystopias Marah Eakin “Loch Henry”—set in moody, atmospheric Scotland—is the second episode of the sixth season of Black Mirror , which returns to screens tomorrow after a four-year break. Inspired by Brooker’s true-crime binge, it’s about the uncomfortable nature of turning atrocities into entertainment. “While you’re watching it, you think, ‘I’m watching some real art here,’” he says. “But you are still there to rubberneck at the scene of a crime.” If Black Mirror ’s success has been predicated on its living up to the promise of the title—a glimpse of our true selves reflected back at us from the glossy surfaces of our smartphones—this season does something different. It turns the camera on itself, and the content machine.
In “Mazey Day,” we meet a young celebrity hounded by the paparazzi in early 2000s Los Angeles (inspired by a documentary Brooker watched about Britney Spears). In “Beyond the Sea,” starring Aaron Paul and Josh Hartnett, a distant astronaut pays the ultimate price for public acclaim. And in “Demon 79”—a blood-drenched horror tale billed as the first “Red Mirror” episode—a smooth-talking politician manipulates the media to spread his message of hate.
“Joan Is Awful,” the standout episode of the new season, follows an ordinary, only moderately awful woman who finds that her real life is being turned into a slick television show starring Salma Hayek offered on “Streamberry”’—a very thinly veiled Netflix analogue. It was partly inspired by The Dropout , the prestige drama about Elizabeth Holmes and the Theranos scandal. Brooker was struck, watching Amanda Seyfried’s portrayal of Holmes, how recent the events being depicted seemed and how weird it must have been for the real people involved. “You had all these celebrities playing people who must be sitting at home watching this,” he says.
The episode is Black Mirror at its acerbic best: nipping at the hand that feeds, skewering the readiness with which people’s lives are turned into content, with or without their permission. “It’s designed to keep the viewer in a state of mesmerized horror,” says the Streamberry CEO at one point in the episode. “It’s great for engagement.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg WIRED: It’s been four years since the last season of Black Mirror.
What’s it been like writing a dystopian sci-fi show against an increasingly dystopian backdrop? Charlie Brooker: I started writing the season during the pandemic, and I think when I started writing it—apart from Zoom, which suddenly everyone was using—it felt a bit like things had plateaued, but obviously the world was going through a tough old dystopian time of it.
Did that make you want to lighten the mood? Or really delve deeper into the darkness? I started in a way thinking, “Well, I don’t want to write another episode about what I’ve already written lots of episodes about.
” One way to stop yourself from doing that is to almost delete from your head the idea of what a Black Mirror episode is and think “fuck it” and start writing something else.
That explains why a few of the stories in the new season barely touch on technology or other traditional Black Mirror topics at all.
We’ve got a mix of what you might call very Black Mirror episodes and ones that are less so, but certainly shaking things up a bit and getting out of the rut. It was easy for me to sit there and think, “I’ve got to do an episode about polarization on social media; I’ve got to do an episode about NFTs.” That was never what the show was intended to do at the start. We weren’t meant to be “this is what’s going on in technology this week.” It was always designed to be a more paranoid and weird and hopefully unique show.
Black Mirror wasn't meant to be “this is what’s going on in technology this week.” It was always designed to be a more paranoid and weird and hopefully unique show.
Charlie Brooker A few episodes in this season seem to turn the show’s lens back on itself. “Joan Is Awful,” in particular, has a lot to say about turning your life into content. Was that inspired by something happening in your own life? This is not something I consciously sit down and think about; it’s just that the stories that appeal to me seem to often be about … inauthenticity of experience would be one way of describing it.
For writers there’s always this question of to what extent you should turn your life into content. If something really horrible happens to you and you’re in a creative field, there’s this temptation to write about it or make a show about it. There’s a trade-off there, but once it’s done, it’s done, and you can’t really put that genie back in the bottle.
You can’t. It’s celebrity, right? It’s grappling with things that were traditionally the preserve of celebrities: Living a very public life and putting yourself up for judgment is what everyone is potentially wrestling with. There is clearly a human need to be seen and to be recognized. One of my kids is 9 years old, and he asked if he could start a YouTube channel. I didn’t really know what to say to that.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You’re a renowned worrier—are you worried about the existential threat of artificial intelligence ? I mean, yes, in as much as I’m worried about everything else.
But are there AI-specific things on your mind? I’m annoyed: I wanted to do an episode about an AI standup comedian and I didn’t quite get the story this time and now I sort of feel, “Ah, does that look a bit reactive now rather than pre-emptive?” There’s been stories that we’ve been doing about AI for a long time, I think the first one was probably “Be Right Back,” with Domhnall Gleeson and Hayley Atwell, and he dies and she uses a sort of AI ChatGPT for grieving people to talk to him. In a way that sums it up for me, because he becomes a sort of bland emulation, something that isn’t actually as messy and surprising and strange and crap as the original him. It becomes this weird, watered-down echo.
You recently told Empire you had ChatGPT write a Black Mirror episode and it was “shit.” The worry at the moment is that executives will use it to generate a list of crap ideas that have been mulched together from actual humans’ unpaid ideas: hoovered up off the internet and then mushed together into a mash. Great, I own this IP, now I’ll hire in human writers cheaply to actually make this serviceable, because ChatGPT cannot do that at the moment. That’s certainly a valid concern.
Yes.
When it comes to the illustration stuff , I’m in two minds, because you can see it’s capable of pumping out imagery that’s really startling. It can emulate the style of existing human beings, and it can synthesize and blend it all together. If I was an illustrator I’d be extremely worried about commissions drying up.
What about its impact beyond creative industries? What if it goes all Skynet and decides to wipe us out? I remember reading an article that said that will happen in an afternoon, if it’s gonna happen. We’ll wake up one morning and stretch and yawn, and by the time the sun goes down we’ll be sharing the planet with an intelligence that’s 50 billion times as intelligent as us, and then all bets are off as to what it could do. We can’t possibly predict it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But maybe if these things are built in our own image they’ll just be crippled with anxiety and self-loathing? That would make them more interesting. But the problem is they’re sort of not. I’ve seen stories about robots that suddenly develop human emotions, and I’ve always avoided that in Black Mirror because I find them hard to relate to.
Maybe I’m a robot, or maybe I’ve got too many emotions, I don’t know. But I always found it not that interesting as a storyline—maybe because I’m selfish and I think, “I don’t care about the fucking robot.” And “Be Right Back” was written as an anti-“robot develops emotion” story. The AI shows up, but it can’t ever quite get there. And it’s not really thinking; it’s not really feeling.
Society’s worries tend to shift over time: AI, climate change, and the threat of nuclear war, which comes up in one of the new episodes.
Black Mirror has always been pretty good at predicting what the next thing we should worry about should be. What are you worried about now that we’ll be worrying about in 10 years’ time? Short term, the thing that worries me is disinformation, misinformation: the unfunny end of that image of the Pope in a puffer jacket that went viral a few weeks ago and turned out to have been generated by an AI. You can obviously see what happens when stuff like that is weaponized, and that’s going to be coming very soon. That’s terrifying, because some of the gatekeepers don’t seem to give a shit or are actively encouraging that.
So that frightens me—what people do when they’re afraid and misinformed. This is depressing isn’t it? That is probably going to be our biggest challenge over the next 10 years. And then beyond that, all the rest of it: climate, nukes, you name it. Keep it light! But a lot of things you’ve written into Black Mirror have happened—and a lot of things that do happen feel like they could or should have happened in the show. Even something like the Apple Vision Pro is such a dystopian device in many ways.
It’s weird, it’s really weird. One of my instincts when I saw that was like, “Oh my God, that’s so Black Mirror.
” We haven’t got anything quite like that in this season—but then that’s because we did it! We did it all years ago. But a lot of the time what I was doing was looking at things and extrapolating, so it’s not that surprising in many ways.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But they’re warnings, right? You make these shows as a warning about not making the thing, and then they go ahead and make the thing.
I don’t know if it’s necessarily about not making the thing. Usually there’s a weak and flawed human in the story to fuck things up rather than it being the technology specifically. We did “Metalhead,” which was about robot AI dogs going around killing people—fair enough, that’s the technology. But in the “Entire History of You,” the memory playback episode, it’s this jealous and insecure husband who fucks up his own life. It’s not generally the fault of the technology within the stories.
I am generally pro-technology. Probably we’re going to have to rely on it if we’re going to survive, so I wouldn’t say they’re necessarily warnings, so much as worries, if you know what I mean. They’re maybe worst-case scenarios. I read a thing— maybe I read it in WIRED —about technology companies having “red teams” who sit around thinking, “How could someone misuse this? We’ve just invented the Apple AirTag , what if somebody stalks somebody with it?” That is often what I’m doing.
Invariably, they’ll just decide to release it anyway! That’s the thing I find scary. Well OK, disrupt away, and just unleash the hounds and … “Oh shit, oh dear, we’ve killed everyone.” This interview has been edited and condensed.
You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior writer X Topics TV science fiction Television streaming Netflix Gideon Lichfield Jason Parham Vauhini Vara Kate Knibbs Kate Knibbs Virginia Heffernan Lindsay Jones Jason Parham Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,068 | 2,001 |
"The 11 Best Sci-Fi Movies You Can Stream Right Now, From 2001 to Ex Machina | WIRED"
|
"https://www.wired.com/2017/03/best-sci-fi-streaming"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Jennifer M. Wood Culture The 11 Best Sci-Fi Movies You Can Stream Right Now, From 2001 to Ex Machina Save this story Save Save this story Save As film genres go, science fiction is often the one that's hardest for folks to get into. Literal-minded moviegoers often have a hard time with worlds where anything—and everything—is possible and, well, some people just don't like space. But those willing to give in to their imaginations are deeply rewarded. That's because, when done right, sci-fi can offer a truly enriching cinematic experience—one where science and technology can easily be tempered with humor, horror, drama, or all of the above. Does all this talk make you wish you were diving into some great sci-fi right now? Good. Here’s the best of what you can currently find on Netflix, Hulu, and Amazon. The future, dear streamers, is bright.
If you only ever watch one sci-fi film in your life, let it be Stanley Kubrick’s 2001: A Space Odyssey.
A beautiful meditation on the evolution of humankind, the film's vast scope and breathtaking cinematography make it a bit of a mind-bender. It’s also quite prescient: The bulk of the action follows a group of men on a space mission who are aided, then held hostage, by HAL 9000—a piece of AI technology that has gotten better at being human than the flesh-and-blood astronauts relying on it. Its pace is glacial, but its storytelling and groundbreaking filmmaking techniques make it unlike almost anything else in cinema history.
Where to stream it: Amazon When you're a 31-year-old director who just invented "the blockbuster" with a flawless film about a vengeful shark, there’s only one thing to do: make an alien movie. In Steven Spielberg's Jaws follow-up, Roy Neary (Richard Dreyfuss) is a blue-collar family guy whose late-night run-in with a UFO turns into an obsession. Much like last year’s Arrival , Close Encounters of the Third Kind steers clear of the horror-leaning "alien invasion" tropes and instead focuses on the practical implications of discovering extra-terrestrial life—like communication. Nearly 40 years later, it's still one of the most intelligent first-contact films ever made.
Where to stream it: Amazon The spacecraft Nostromo and her crew, which includes warrant officer Ellen Ripley (Sigourney Weaver), are headed home to Earth when they receive a distress call from a nearby planetoid and make a detour to investigate. Bad move. What they find is an unknown species of alien that begins to knock off crew members one by one.
Alien turned Ridley Scott into a sci-fi icon while also launching a franchise that continues to this day (his next entry, Alien: Covenant , is due out in May). The movie also set the stage for the director's other bit of essential sci-fi viewing: 1982's Blade Runner.
Where to stream it: Amazon With all due respect to George Lucas and A New Hope , Irvin Kershner’s Empire Strikes Back is the rare sequel that manages to outshine its predecessor. Taking place a few years after the original film, the movie sees Darth Vader trying desperately to find the Rebel Alliance, which—under the leadership of Princess Leia (Carrie Fisher)—has set up shop on Hoth. Luke Skywalker (Mark Hamill) and Han Solo (Harrison Ford) are out there own their own, too, and as any Star Wars fan knows, the Rebels are at their most powerful when our trio of heroes is working together.
Where to stream it: Amazon Like Star Wars , the Max Max franchise got a narrative boost with its second entry, Mad Max 2: The Road Warrior.
Whereas George Miller's original 1979 film saw Mel Gibson's Max Rockatansky fighting against the decline of a futuristic society, Road Warrior was a full-on dystopia centered on the aftermath of the events in the original movie and Max's attempt to reclaim his own humanity. Plus: Cool cars! Where to stream it: Amazon Science fiction and dystopia go together like John Carpenter and synth scores. Fortunately, Escape from New York has all four. Set in the then-future year of 1997, *Escape'*s America is essentially a war zone where Manhattan is one big maximum security prison. That lock-up is where the POTUS lands when Air Force One crashes following an attempted hijacking. With the president being held hostage by one of the nation’s most notorious crime bosses, the government enlists the help of Snake Plissken (Kurt Russell), a soldier-turned-criminal who might just be America’s last great hope. Like much of Carpenter’s output, there’s a certain kitschiness to the entire thing—which is exactly what makes it a classic.
Where to stream it: Amazon Yes, it’s a comedy. And sort of a family film, too. But at its heart, Back to the Future is a sci-fi movie—and one of the most perfect examples of the genre. Marty McFly (Michael J. Fox) is your typical cool '80s teen who just so happens to pal around with a mad scientist, Doc Brown (Christopher Lloyd), who invents a time machine. Through a series of unfortunate events, Marty ends up getting sent back to 1955, where he befriends the teenaged versions of his parents and does his best to dissuade his mom from having the hots for him. By messing with history, Marty’s messing with his own future and slowly being erased. But he manages to right the past, find his way back to 1985, and give those fun-loving kids a taste of what rock ‘n’ roll should sound like.
Where to stream it: Amazon Though the '80s are often associated with neon, popped collars, and Members Only jackets, a quick look at some of the most popular films of the decade are proof that there was also a deep sense of disillusionment. In the same year that Gordon Gekko was declaring "greed is good" in Wall Street , Paul Verhoeven was unleashing one of the decade’s most subversive sci-fi flicks, which sees the mayor of Detroit hand over control to the evil Omni Consumer Products (OCP), an outfit that turns Motor City into a testing ground for new technology. That new tech includes RoboCop, a law-enforcing cyborg who attempts to eradicate the city of crime—until memories of his human existence find their way back into his head.
Where to stream it: Amazon If The Terminator raised the bar for sci-fi films, Terminator 2: Judgment Day broke it. Like the many cyborg movies that came before it—including the original— T2 is a commentary on what it means to be human, and how far is “too far” when it comes to developing intelligent technology. While the storyline is similar to the first film—a Terminator is sent to LA to kill John Connor, the boy who will eventually lead the human resistance— Judgment Day makes this list for one important reason that has nothing to do with plot: amazing VFX. For T2 , director James Cameron employed some truly groundbreaking CGI to create Terminators that moved like nothing else had before. And those liquid-metal shots are still impressive more than 25 years later.
Where to stream it: Amazon, Hulu Given the immense popularity of The Matrix , it was obvious that many sequels would follow. And while they may have slightly diluted the impact of the first film, The Matrix still stands alone in its ability to combine impressive direction with mind-bending action sequences and a storyline that actually makes you think. It also brought the directing duo the Wachowskis to the forefront of the action movie scene, and it’s been a better place ever since.
Where to stream it: Amazon Though one could easily point to the 1980s as the apex of the sci-fi film movement, the new millennium has proven that there are still plenty of unique stories to be told within the genre. But with its stellar acting, pitch-perfect directing, and relevant storyline, Ex Machina just might be the one we most need right now. When a programmer (Domhnall Gleeson) is sent to the isolated home of a tech wunderkind (Oscar Isaac), he believes he’s been invited to help in the development of a brilliant and beautiful humanoid robot named Ava (Alicia Vikander). But as Ava reveals more about herself, it becomes clear that she—not the humans—is in control.
Where to stream it: Amazon Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Topics Movies Sci-fi Angela Watercutter Matt Kamen Jennifer M. Wood Jennifer M. Wood Jennifer M. Wood Matt Kamen Megan Farokhmanesh Reece Rogers Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,069 | 2,019 |
"Disney+ Is Here—and It's a Fully Formed Streaming Juggernaut | WIRED"
|
"https://www.wired.com/story/disney-plus-power-launch"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Brian Barrett Culture Disney+ Is Here—and It's a Fully Formed Streaming Juggernaut Disney+ launches today with a slew of content, including a series of shorts called Forky Asks a Question.
Courtesy of Disney/Pixar Save this story Save Save this story Save After months of hype—and a literal three-hour trailer —Disney+ finally touches down today. It does so with all the trappings of a hit: a competitive price, popular franchises stacked to the ceiling, Forky. Even more important to its inevitable success, though, is what it exhibits few signs of: growing pains.
Athena seems like a hifalutin metaphor for yet another streaming service from a multinational megacorp. But go with it for a second, because it gets at what makes Disney+ singular more than the ever-expanding Star Wars universe ever could. It’s that Disney+ is bursting into existence fully formed, straight from the noggin of Disney CEO Bob Iger.
It’s hard to overstate the advantage this gives Disney over fellow newcomers like Apple TV+ and the forthcoming HBO Max. And it's important to understand that Disney’s head start comes not only from its extensive back catalog of TV shows and movies but also from a technological prowess in this space that that few companies can match.
Start with the fun part. At launch, Disney+ will bring to bear the full power of not just Mickey and friends but Marvel, Pixar, and Star Wars, along with a heaping helping of Fox and National Geographic. It’ll have fewer total hours of stuff to watch than Netflix does, but also substantially less filler.
More importantly, it can offer most of those movies and TV shows from day one, including franchises with shelf lives that are measured in the decades. (A few exceptions, like Mary Poppins Returns , are tied up with licensing agreements elsewhere, but will make it over the transom eventually.) That means Disney+ will enter the market at $7 per month with confirmed hits, rather than plodding through years of trial and error to find a show or two that sticks.
Related Stories Year in Review Brian Raftery TV Jason Parham The Monitor Angela Watercutter Compare that to Apple TV+ , which launched less than two weeks ago with a relatively paltry nine series—most of which launched to decidedly mixed reviews. That’s not a knock on Apple, which is both starting from scratch and effectively giving its streaming service away to anyone who buys one of its devices; it’s like getting a branded koozie along with a large appliance purchase. But it does speak to all the trouble Disney doesn’t have to go through to build out its stable.
“Disney knows it has an audience,” says Dan Rayburn, a streaming media analyst with Frost and Sullivan. “Apple’s never been known for content, because they’ve never been in that space. So it’s much more difficult for them to find an audience and say, ‘What does my audience want to watch, what do they want to see?’” That process can take years. Just ask Netflix or Amazon. The former relied on licensing outside content for years—most notably from Starz, which sent Netflix subscribers reeling when it pulled out of the deal in 2011—before finally striking oil with House of Cards two years later. But even now, Netflix is spending an estimated $15 billion on original content this year alone, in search of the next big hit. To build up its arsenal, Amazon spent its early years asking Prime members to vote on which TV show pilots they wanted to see more of.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg For better or worse—don’t expect to see as many creative risks coming from the Mouse House content laboratories—Disney+ will skip those formative years altogether. It will launch with instantly recognizable, universally beloved movies and shows. (Along with plenty that are … less so.
) Because it owns all of that intellectual property, it can show them all over the world without navigating the thickets of local licensing agreements Netflix still contends with regularly. And as Disney continues fills out its library with new projects, it knows full well who its customers are and what they like. It’s been at this game for nearly a century.
In the long run, that could place a cap on Disney’s streaming appeal. “Disney+ is not going to be a generalist service like Netflix or, to some extent, even Amazon,” says Tony Gunnarsson, streaming media analyst at Ovum. “It will be Disney titles only. I think that will be the most important thing to bear in mind.” Still, “Disney titles only” is miles ahead of where any other streaming service started. Not to mention that Disney knows how to get them to you without a hiccup.
Having hours of highly watchable stuff isn’t enough. As anyone who’s struggled to stream Game of Thrones knows, the infrastructure that gets those shows to paying customers is every bit as important.
Disney knows that too, and better than you might think. In 2017, it put down $1.58 billion to gain a majority stake in BAMTech, a company that grew out of Major League Baseball Advanced Media in the early aughts. Without getting into a deep history of online streaming infrastructure, know that BAMTech is the gold standard, for years supporting everything from Major League Baseball to WWE to Disney-owned Hulu. Last year, Disney renamed BAMTech internally as Disney Streaming Services.
Throughout its various iterations, BAMTech has proven itself unflappable. The unpredictable popularity of baseball games taught it how to balance loads and handle usage spikes. Its work streaming those games to the MLB.tv app as early as 2009 means it’s logged more years of service delivering video to iOS devices than just about anybody. (Netflix’s iOS app launched in 2010.) The actual Disney+ launch could still have issues. Having BAMTech on board, though, gives Disney the best possible chance at pulling it off without a hitch. It’s an advantage that another looming competitor—AT&T-owned HBO Max, which can almost rival Disney+ for sheer size—very notably lacks. To pull off its streaming ambitions, AT&T needs to somehow bring its disparate properties at HBO, CNN, TBS, TNT, Cartoon Network, Adult Swim, Warner Bros., and more onto one shared platform.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “That is an enormous undertaking that none of these companies in their history have ever done at the size and scale that we’re talking, at a time when digital is critical,” says Rayburn. “That is what scares the hell out of all of these companies moving forward, except Disney. And the reason for that is they bought the company that has the most expertise in this space.” That expertise extends beyond the nuts and bolts of pushing encoded video across various pipes. BAMTech can handle credit cards and authentication and subscriptions and all of the other unglamorous aspects that make streaming services actually run. It even knows how to sell tickets, thanks to its MLB roots.
“Disney has a huge advantage over everybody because of the expertise of BAMTech,” says Rayburn, especially when it comes to relatively new entrants. Netflix may have every bit as sophisticated a backend, but it took years to build out.
That’s the real story of Disney+, and the reason it deserves more attention than some of its fellow flashy upstarts. This may be its first day, but it’s got one hell of a head start.
Note: When you buy something using the retail links in our stories, we may earn a small affiliate commission.
Read more about how this works.
The super-optimized dirt that helps keep racehorses safe The 12 best foreign horror movies you can stream right now VSCO girls are just banal Victorian archetypes Google’s .new shortcuts are here to simplify your life The delicate ethics of using facial recognition in schools 👁 Prepare for the deepfake era of video ; plus, check out the latest news on AI 💻 Upgrade your work game with our Gear team’s favorite laptops , keyboards , typing alternatives , and noise-canceling headphones Executive Editor, News X Topics streaming Disney Star Wars Angela Watercutter Jennifer M. Wood Jennifer M. Wood Angela Watercutter Angela Watercutter Angela Watercutter Jennifer M. Wood Jennifer M. Wood Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,070 | 2,023 |
"The Marvel Movies From Worst to Best—and Where to Stream Them | WIRED"
|
"https://www.wired.com/story/best-marvel-movies-ranked"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Jennifer M. Wood WIRED Staff Culture The Marvel Movies From Worst to Best—and Where to Stream Them Brie Larson in The Marvels.
Courtesy of Laura Radford/Marvel Save this story Save Save this story Save In May 2008, the recently formed Marvel Studios released its first movie—and changed the face of modern cinema.
Iron Man wasn’t even the highest-grossing superhero film of the year (Christopher Nolan’s The Dark Knight took that crown), but it was a kernel that has exploded into an all-consuming entertainment juggernaut. Fifteen years later, the Marvel Cinematic Universe is a sprawling, interconnected web of character-based movies and crossovers that has pulled in billions at the box office.
But which Marvel movies are the best, and worst, of the bunch? Is Iron Man 3 better than Iron Man 2 ? How bad was The Incredible Hulk ? How does Guardians of the Galaxy Vol. 3 hold up against its predecessors? Where does The Marvels , the MCU’s latest offering, fit into it all? We’ve spent hours arguing about the relative merits of Doctor Strange and Black Widow , and at the end of it, we’ve got some irreparably damaged working relationships and the definitive ranking of every movie in the Marvel Cinematic Universe.
Related note: It takes nearly three days to watch all 33 Marvel movies back to back. Most of them are now available on Disney+, and you can read our guide to the best films on Disney+ to see what else is worth watching when you’re done—until Deadpool makes his official MCU debut in 2024.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Eternals faced an uphill battle, as it was one of the first movies to get caught up in Covid-19 delays. While it originally completed shooting in February 2020, the bulk of its post-production was handled remotely and reshoots had to be done nearly 10 months later. Add several delays due to movie theater closures, and fans ended up waiting about three years to see it. But rather than an easy slide into this new world of the Eternals—an alien race of immortal superheroes who have been living in secrecy for thousands of years—audiences got a full-on, Avengers -style epic they weren’t quite ready for. While the film garnered praise for its sumptuous visuals and innovative direction by Chloé Zhao, and for bringing a whole new philosophical bent to the MCU, it ultimately felt like a futile exercise.
Watch on Disney+ This largely forgotten Marvel movie followed closely on the heels of Iron Man ’s success, but relative to the other films in the series, it was a critical and commercial flop. Edward Norton did a perfectly fine job as Bruce Banner, but the story goes that he wanted more creative control than a tightly related web of movies would allow and so was replaced by Mark Ruffalo before The Avengers (aka Avengers Assemble ) four years later. (Ruffalo, it turns out, had actually been The Incredible Hulk director Louis Leterrier’s first choice for the smashing green superhero.) The film feels very dark and gloomy compared to the brightness of Marvel’s later efforts, and the CGI has not aged well. But most importantly, recasting with such a different actor meant that the events of this film have largely been ignored ever since—a number of seeds were planted that never bore fruit, and Banner’s emotional backstory and relationship with Betty Ross (played by Liv Tyler) were never mentioned again, which seemed to suit some fans just fine—until now. In March 2023, it was announced that Tyler would reprise her role in the upcoming Captain America: New World Order , which is set to be released on July 26, 2024.
Watch on Disney+ It’s tough for any sequel to match—let alone surpass—the success of its cinematic predecessor, and Iron Man 2 was certainly not up to the task. Robert Downey Jr. reprises his role as the eponymous superhero, going head-to-head with the US government, which is worried about what could happen if Tony Stark’s tech falls into the wrong hands. Officials spend so much time pestering Stark that a new threat escapes their notice—in the form of Ivan Vanko, aka Whiplash, a Russian physicist who’s got a bone to pick with Stark. Mickey Rourke, fresh off his Oscar-nominated role in The Wrestler , has spent the past decade-plus trashing the movie and the MCU’s “ crap acting ,” which hasn’t helped the film’s legacy.
Watch on Disney+ One of the things you realize when you sit down and actually rank all 33 MCU films is how few duds there are. Marvel Studios president Kevin Feige and his colleagues have done a remarkable job of turning out some pretty solid pictures, and there are few genuinely bad entries in the series. Unfortunately, this is one of them.
The Dark World was beset by problems from the start, including extensive rewrites and even director changes. Despite all that work put into making the best picture possible, the plot—which features Dark Elves, frost monsters, and a malicious substance called the Aether—feels a bit distant. Fortunately, Thor managed to rebound with 2017’s Thor: Ragnarok.
Watch on Disney+ If Downey’s final solo outing as Iron Man marked the end of an era, it would best be summed up as an era of mediocre movies starring a massive talent, making the end of them far less sad for filmgoers. The plot of the third film revolves around Tony Stark’s PTSD in the wake of the Battle of New York as he takes on The Mandarin, a mysterious figure who turns out to be a debauched actor in a television studio, played with all the respect that plot twist deserves by Oscar winner Ben Kingsley.
Watch on Disney+ The Avengers’ second group outing is a joyous jumble of a movie in which the superheroes start to really click as a team. Stark’s mad-scientist-playing-God routine spirals out of control (in a good way) when he blends Asgardian heirlooms with AI and advanced robotics. The Avengers end up having to battle Ultron, a Terminator-esque abomination with some unsurprising designs on the future of humankind (read: extinction). That Ultron has a couple of rogue superheroes doing his bidding provides extra fun. After the monster bot is obliterated and the rogues are won over to the other side, a glimpse of Thanos’ purple mug reminds us that this was likely all part of a wider plot. Then again, isn’t everything in the MCU part of a wider plot? Watch on Disney+ Not even Taika Waititi could live up to the incredibly high standard he set with the universally beloved Thor: Ragnarok.
While Waititi’s comic tendencies are on full display, Love and Thunder —much like Guardians of the Galaxy Vol. 2 before it—feels a little too familiar to its predecessor to fully stand out on its own. Still, Chris Hemsworth is utterly charming as the flawed and vulnerable God of Thunder, who is forced out of retirement in order to stop a new enemy, Gorr the God Butcher (Christian Bale), from doing exactly what his name implies. Together with his King Valkyrie (Tessa Thompson), Korg (Waititi), and his newly superhero-empowered ex Jane Foster (Natalie Portman), Thor sets about stopping Gorr, and uncovering the reason behind his hatred of the gods in the first place.
Watch on Disney+ Twenty years after first bringing Spider-Man to the big screen in a pre-MCU world, Sam Raimi officially crashed the Marvel party with this Doctor Strange sequel starring Benedict Cumberbatch and Elizabeth Olsen and Benedict Cumberbatch and Elizabeth Olsen and Benedict Cumberbatch and Elizabeth Olsen. Basically, there are a lot of versions of their characters, Dr. Stephen Strange and Wanda Maximoff, some of whom are up to no good. Like the first Strange film, this one feels like it exists just outside of the MCU—or more to provide connective tissue between other segments of the superhero universe than as a full-fledged solo effort. The movie does, however, feature some of the franchise’s most notable talents (count the Oscar nominations) and the sequel brings Raimi back to his Evil Dead roots, making this a movie for superhero aficionados and horror movie fans alike.
Watch on Disney+ As one of Hollywood’s most likable actors, Paul Rudd was a stellar choice for the petty criminal turned tiny superhero Scott Lang/Ant-Man. He’s also a worthy successor to serve as the face of the MCU’s Phase Five (this is the film that kicked it off), much in the same way that Robert Downey Jr. did for Phase One. While Rudd is as charming as ever, this solo outing is decidedly darker than its predecessors, as Ant-Man and the Wasp (Evangeline Lilly) are swept up into the Quantum Realm, where they’re forced to face off against baddie Kang the Conqueror, a scientist from the 31st century who has stumbled upon the Multiverse.
Chris Hemsworth’s Thor serves as a valuable source of comic relief in many of the more recent MCU movies, but his first outing—in this Kenneth Branagh–helmed film—had a much more serious vibe. At the start of the film, Thor is exiled on Earth and deemed unworthy to wield his hammer, which has crashed into the desert in New Mexico. He strikes up a romance with astrophysicist Dr. Jane Foster (Natalie Portman), who has come to investigate the matter. As usual, it’s Tom Hiddleston as Loki—Thor’s brother—who steals the show, but it’s all a little too serious to find itself in the top half of this list.
Watch on Disney+ Preeminent New York City neurosurgeon Dr. Stephen Strange (Benedict Cumberbatch) is as pompous as he is talented, which makes it impossible for him to accept that his career is over when a car crash leaves him unable to use his hands. In an attempt to reclaim his professional standing, Strange travels to a monastery in Kathmandu, where resident mystics are rumored to have mastered sorcery. After meeting the monastery’s chief warlock, the Ancient One (Tilda Swinton), Strange forgets all about his injured hands as he becomes absorbed in ancient books, exploring the astral plane, and shooting green beams from his fingers. The appearance of a transcendental baddie hell-bent on destroying the magical shields protecting Earth from inter-dimensional villains triggers wizardry battles galore. The visually ingenious film gets points for introducing Cumberbatch to the MCU; unfortunately, that’s not enough to save it from a low ranking.
Watch on Disney+ The second outing of Star-Lord, Gamora, Groot, and company is a perfectly enjoyable film. It just feels like a fairly by-the-numbers retread of the first one, which connected with audiences through its unexpected comedy and the chemistry between its quirky characters, including a wisecracking raccoon and a talking tree. While the sequel attempted to recapture some of that magic, it just couldn’t stick the landing. Or the middle bit, really. The Vol. 2 mixtape has been credited as one of the forces behind the cassette tape’s comeback, which is something to be thankful for.
Watch on Disney+ While the idea of adapting Marvel’s Shang-Chi comic for the big screen was first broached in the early 2000s, it took nearly two decades for the film to get there. Simu Liu made history in the role of Shang-Chi, the MCU’s first Asian superhero, who led a predominantly Asian cast. In the present day, Shang-Chi works as a parking valet—an occupation that helps him mask his past as a highly trained martial arts expert who carried out an assassination when he was just 14 years old. But as Shang-Chi is dragged back into the world of a mysterious group known as the Ten Rings, his past comes bubbling back up to the surface, which proves to be both a blessing and a curse. A sequel is currently in development.
Watch on Disney+ The First Avenger is a sepia-toned love story that follows Steve Rogers’ (Chris Evans) transformation from scrawny patriot to super soldier with the help of a special serum. The film’s historical setting means it’s different in tone from many of the other entries in the series, but that may be a good thing; critics praised its depiction of the 1940s. Of all the films in the series, Captain America perhaps feels the most coherent as a stand-alone flick.
Watch on Disney+ If this were a ranking of Most Depressing Marvel Movies, this one would definitely rank within the top five. That isn’t a knock on the movie—just a fact, as well as a surprising turn of events from James Gunn, who brought some much-needed playfulness to the MCU with the original Guardians of the Galaxy (which helped to wipe away the stink of Iron Man 3 and Thor: The Dark World ). Nearly a decade later, the Guardians are still delivering that same quippy energy that makes the movies seem like a Western one moment and a screwball comedy the next, yet there’s an underlying sadness here. Plot-wise, that’s because it tackles Rocket Raccoon’s backstory, which should come with an #AdoptDontShop hashtag. It’s also one of the first movies to truly examine the emotional toll “The Snap” took on our favorite superheroes. But it’s also hard to imagine that knowing this would be Gunn’s Marvel swan song, and the last time this ragtag team of filmmakers would be working together to create a story about this ragtag team of superheroes, wouldn't bleed into the script. Sure, there are some mawkish moments. But overall, it’s a fittingly moving sendoff for Gunn and the forgotten comic book characters he turned into cinematic icons.
The success of 2015’s Ant-Man sparked an unexpected sequel that takes the series even deeper into the quantum realm. The title character’s ability to shrink and grow on demand makes for some visually arresting fight scenes, and it brings the same humor and levity that made the first film a hit along with it. But the actual plot, if you really think about it, is deeply silly. Then again, maybe that’s what we all needed after the Snap. Although Ant-Man and the Wasp came out after Infinity War , most of the action takes place beforehand, with the exception of a stunning post-credits scene.
Watch on Disney+ Now that Tony Stark’s storyline is (presumably) finished, the MCU needs a new MVP—and Brie Larson’s Carol Danvers just might be it. The universe’s newest film serves as a sequel to 2019’s billion-dollar-grossing Captain Marvel and a continuation of the 2022 Disney+ series Ms. Marvel.
Like Black Widow before it, The Marvels puts the spotlight on Marvel’s female superheroes, with Larson’s Captain Marvel partnering with Monica Rambeau (Teyonah Parris) and Kamala Khan/Ms. Marvel (Iman Vellani) to manipulate space and time to save the world. You know the drill. Except this time, there are cats (yes, that’s a huge plus). And thanks to director Nia DaCosta (who also cowrote the script), there’s a very welcome wackiness to the proceedings that is reminiscent of Thor: Ragnarok.
Also welcome: The movie’s 105-minute running time, which is the shortest of any Marvel film.
It’s possible no Marvel movie will ever top Black Panther (as evidenced by its ranking on this list). But if you think of Wakanda Forever as a movie that both honors the legacy of Chadwick Boseman, who played T’Challa in several Marvel films and tragically died in 2020, and continues the story of the nation of Wakanda, then this is a worthy sequel. Director Ryan Coogler not only introduced the world to a new Black Panther, he also brought along Riri Williams (aka Ironheart) and Namor, too. It’s as gut-wrenching as it is action-packed.
Watch on Disney+ Although Civil War is officially a solo Captain America outing, it plays out more like an ensemble Avengers story, with a huge cast of characters split into rival factions by the Sokovia Accords—a legal agreement that puts tighter controls on superheroes and was introduced after Tony Stark’s rogue AI dropped an entire city in Age of Ultron.
Stark, cowed by his role in creating Ultron, is allied with the government and has Black Widow, Black Panther, Vision, and Spider-Man on his side. Meanwhile, Steve Rogers and his team—which includes Ant-Man, Hawkeye, and Wanda Maximoff, who are probably not the favorites on paper—go rogue to track down Hydra’s Helmut Zemo and bring in Bucky Barnes.
Watch on Disney+ Given that Scarlett Johansson has been an integral part of the MCU since 2010’s Iron Man 2 , her 2021 debut solo feature seemed long overdue. But the wait may have been worth it, as Black Widow feels much more like a stand-alone movie than probably any other solo outing in the MCU and introduces a solid new cast of characters, including Florence Pugh as Yelena Belova, a fellow Black Widow and sister-like figure to Johansson. It largely follows the Marvel formula of action, action, and more action and plays out more like a Bond film in that way—which isn’t a bad thing—but it also contends with the very specific issues of female independence and the effects of surviving trauma. While it allowed longtime fans to dive deeper into the past of Johansson’s notoriously mysterious Natasha Romanoff (aka Black Widow), it also—finally!—gave audiences the chance to see a slightly different and more vulnerable side of the Avenger. It’s just too bad it took Marvel more than a decade to finally give fans that moment.
Watch on Disney+ Thanks to the MCU, crossovers have become such a common occurrence at the theater that it’s easy to forget the impact of first seeing Iron Man, Thor, Captain America, the Hulk, and more combine forces.
The Avengers —or Avengers Assemble , as it’s known in the UK—delivers some great moments during the Battle of New York, which becomes a key plot point in the next phase of the story, and in many of the spin-off television series. The film wouldn’t work without the strength of the supporting characters, but it’s Mark Ruffalo’s quieter, more measured take on the Hulk that stands out.
Watch on Disney+ The Winter Soldier felt vital when it was released in 2014, but it tends to merge into a general blur of close-quarters combat and severed limbs. It follows Captain America’s attempts to track down the Winter Soldier, a mysterious and powerful assassin who turns out to be his close personal friend Bucky Barnes (Sebastian Stan). Like Cap, the Winter Soldier was also kept on ice for most of the 70 years after World War II; unlike Cap, he was brainwashed by the evil Hydra. A rehabilitated Winter Soldier appears in both Infinity War and Endgame , and Stan has a few films left in his contract, so it might be worth rewatching this one for future reference.
Watch on Disney+ The first film of Marvel’s Phase Four follows Peter Parker (Tom Holland) as he attempts to live some semblance of a normal teenage life after the traumatic events of Avengers: Endgame.
But a class trip to Europe and a chance to share his true feelings with MJ (Zendaya) go awry when Earth is besieged by Elementals—beings of pure fire, earth, air, and water—and Spider-Man is forced to team up with the enigmatic Mysterio (Jake Gyllenhaal) to protect his classmates, not to mention various European landmarks.
Watch on Disney+ Marvel’s biggest mistake in the entire MCU canon (so far) was not commissioning Captain Marvel sooner. The film, which is set in the past, sees the rise of Marvel (Brie Larson) as she discovers her origin story and develops her powers. The only real flaw in the movie is that it doesn’t convincingly explain what happened to Marvel between the end of the title and what comes years later in Endgame.
Watch on Disney+ A decade of careful breadcrumbs planted across dozens of movies culminated in a jaw-dropping finale that was remarkable in terms of its ambition and execution.
Infinity War brought together pretty much every major character that had been seen on screen in the previous 10 years to take on Thanos and stop his plan to wipe out half of all life in the universe. The pitched battle between the forces of Earth and an alien army was stunning cinema, and the shocking cliffhanger ending was one of the biggest cultural moments of the year, if not the decade. Snap! Watch on Disney+ Who doesn’t love a heist movie? Rudd’s MCU debut acted as something of a palate cleanser after the heavy and (literally) Earth-shattering events of Age of Ultron.
Rudd plays Scott Lang, a reformed criminal who teams up with Hank Pym (Michael Douglas) and his daughter (Evangeline Lily) to keep Pym’s shrinking technology from falling into the wrong hands. The film’s depiction of quantum physics wouldn’t hold much water at CERN, but it’s terrific fun—thanks in large part to Michael Peña’s star turn as Lang’s former cellmate Luis.
Watch on Disney+ Spider-Man: Homecoming marked the third attempt in just 15 years to bring a new take on Spider-Man to screens. While the resulting effort could easily have felt a bit been there, done that, director Jon Watts and lead actor Tom Holland managed to breathe new life into the superhero, making Spidey feel modern, fresh, and really quite charming. The introduction of Downey’s Iron Man as a key character in the plot situates the film nicely in the broader Marvel Cinematic Universe without feeling heavy-handed. And the balance of Spider-Man’s action-packed adventuring with Parker’s everyday high school drama makes for a character that is more relatable than previous iterations. There’s plenty of cool web-slinging and day-saving, but it’s the humanity of the film that propels it to a top spot on our list.
Watch on Disney+ There’s a moment in Endgame —the event movie to end all event movies—when you realize that what writers Stephen McFeely and Christopher Markus have done is to go full Harry Potter and the Cursed Child all over the MCU. If your mind could throw up a little bit in its mouth, it would. Once you learn to accept this, you can settle in. And once you get past the glum first 45 minutes, you can open your heart for the good stuff: wise Stark, Professor Hulk, the (controversial) Lebowski Thor, Doctor Strange holding up one finger, Black Widow and Captain Marvel kicking ass (both emotionally and physically), and almost every character you’ve ever met having a moment. It’s a messy but epic baton pass in the form of an angsty, portal-powered mega-battle. And we’re not going to lie: We’ve watched those audience reaction videos and they, too, are a thing of joy.
Watch on Disney+ From its opening sequence, where Chris Pratt’s Star-Lord dances through an abandoned alien vault on a distant planet to “Come and Get Your Love,” it was clear that Guardians of the Galaxy would bring something truly otherworldly to the MCU. It was not a well-known comic storyline, but the film provided a much-needed shot of humor for a series in danger of becoming a little too serious after the events of The Winter Soldier.
With a soundtrack of ’70 and ’80s hits, and Pratt at the helm of a band of entertaining misfits, it became an instant fan favorite.
Watch on Disney+ In Spider-Man: No Way Home , the unthinkable happens: Spider-Man’s identity is revealed to the world, putting both the superhero and the people he loves in danger of being targeted by his enemies. So Spidey does the only thing he can think to do: call in Dr. Strange to help the world forget what they’ve learned about him. While the film maintains the sense of wonderment and fun we’ve seen in previous Spider-Man tales, it also plays with the fact that we have seen a lot of web-slingers come and go, and it goes so far as to bring Tobey Maguire and Andrew Garfield back into the fold as Strange tries to help Peter Parker with his identity crisis.
Watch on Amazon The first MCU title is still one of the best. Released way back in 2008, Iron Man debuted just a year after the first iPhone was introduced. At the time, Thanos was just a tiny thought in the bigger MCU world. Still, Iron Man has aged well. Stark’s trademark stubbornness and arrogance are peppered throughout the film and only increase when he breaks free from his kidnappers and creates the first metallic suit. From there, Stark’s legacy is assured—and the MCU’s first official superhero is born.
Watch on Disney+ Taika Waititi’s Thor —as it shall forever be known in cinephile circles—came close to the top spot because it is, quite simply, a masterpiece. A spacey, Day-Glo masterpiece. Switching up the sometimes-grating Marvel sass and the not-quite-working Thor formula for something much more awkward and genuinely odd, Ragnarok is postmodern (but not in a pretentious way) and by far the funniest Marvel movie to date. Cate Blanchett’s villain Hela doesn’t get the zingers, sure, but Tessa Thompson’s Valkyrie is a drunken delight, and then there’s Jeff Goldblum. Every detail of the story of Thor and Hulk’s side mission and the defense of Asgard has been meticulously put together in the manner of a trippy indie film—which is all the more impressive when you consider this is a huge Disney flick.
Watch on Disney+ With Black Panther , director Ryan Coogler broke the superhero film mold in many respects, elevating the genre in such a way that it managed to please both fans and critics—to the extent that, in 2019, it became the first superhero film to be nominated for a Best Picture Oscar. Basically, everything about this film is fantastic: the casting, the costumes, the plot, the performances. The setting of the secretly technologically advanced nation of Wakanda is a true cinematic treat, and Chadwick Boseman’s T’Challa is matched by an unusually three-dimensional villain in the form of Michael B. Jordan’s Killmonger, whose backstory gives pause for thought beyond a simple good-versus-evil narrative. Add in multiple female characters who each have more substance than most superhero films’ entire casts put together, and Black Panther is the perfect example of how good a Marvel film can be.
Watch on Disney+ Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Topics Marvel Movies comics Spider-Man hollywood Thor Avengers Jennifer M. Wood Angela Watercutter Jennifer M. Wood Jennifer M. Wood Gabrielle Niola Marah Eakin Elana Levin Matt Kamen Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,071 | 2,023 |
"The Creator of ‘Silo’ Says Same-Day AI Movies Are Coming Soon | WIRED"
|
"https://www.wired.com/story/silo-apple-tv-plus-hugh-howey-interview"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Marah Eakin Culture Silo ’s Creator Says Same-Day AI Movies Are Coming Soon Courtesy of Apple Save this story Save Save this story Save If you believe Hugh Howey , the television adaptation of his postapocalyptic book trilogy Silo may never get released, despite the millions of dollars and thousands of man-hours Apple TV+ has thrown at the production. Sure, the dystopian drama—which stars Rebecca Ferguson, Tim Robbins, and Rashida Jones and was produced by Justified creator Graham Yost—has a release date of May 5, and the show has already premiered at Cannes and in London, but the author still isn’t ready to call it a done deal.
WIRED Q&A Kate Knibbs TV Marah Eakin State of the Art Madeline Ashby “To be honest,” Howey says, “it's still a gradual process. I think it'll probably hit me on June 30, the day the finale airs. Even when I walked onto the set of the show for the first time in England, I was like, ‘Oh, my gosh, are we really doing this?’” It’s an understandable feeling, given Silo ’s long road to the screen. The series first emerged via a short story, “ Wool ,” in 2011, which gradually grew in size, scope, and popularity as more of Howey’s universe began to unfold via Amazon’s Kindle Direct Publishing system. In 2012 it was optioned by 20th Century Fox and set to become a movie, with Ridley Scott attached as one of the producers. That deal was thwarted thanks to Disney’s acquisition of Fox, and the project shuffled off to series limbo at AMC.
A couple of years later, it moved once again, to Apple TV+, where Yost, Ferguson, and director Morten Tyldum ( The Imitation Game ) were attached, and the rest is history. This month, fans will be thrust into a world of subterranean crime, intrigue, and falsehoods, all buried well underground. WIRED talked to Howey about Silo ’s long gestation, the recent wave of AI mania , and why everyone's got dystopia fever.
WIRED: You’ve been working on a potential Silo adaptation for more than a decade now. What does it feel like to finally have this out in the world? Hugh Howey: In the last week, I've gotten really excited. In the past, I’ve been nervous about readers being satisfied, and about whether we can get people who aren't familiar with the books interested in the show. But about a week ago, I started getting the first messages from people who have seen all 10 episodes, and everyone who reached out to me has been raving about it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You’ve written extensively about artificial intelligence, including a piece you did for WIRED.
Where are you at with AI now? I think there's a mix of excitement and fear out there now, but I lean more toward excitement. I think people that I’ve talked to who are scared didn't realize this was going to happen.
It’s really exploded in the public consciousness in the past few months, but it’s something you’ve been thinking about for years.
I've been writing and blogging about this for a while, though I said I didn't know what the timing would be. I think on my blog three or four years ago, I said that in the next 10 years, a computer would write a book that's indistinguishable from that of a human author. Some people didn't believe that, and so now they're really scared, whereas I’ve been gradually getting more comfortable with the idea for over a decade.
Sci-fi publishers are already dealing with AI-generated work.
As a sci-fi writer, does that give you pause? I think that these are inevitable developments, but how we use them and approach them is what's not inevitable. We could be optimistic and hopeful and creative with these tools, or we can pull our hair out and be upset and stressed out about them. That's what we can choose, and I'm going to choose to be excited about something that we've created together, cumulatively, because [generative AI tools are] basically based on all of our writing together, even people who don't think of themselves as writers. It's learned from you.
A lot of people are afraid that AI will take their jobs. As an author, is there a part of you that’s like, “Well, to tell something to write a book in the style of Hugh Howey, it still has to know the work of Hugh Howey”? The reason I'm not scared is that when I got into writing, I never thought I'd make a living at it. I worked in a bookstore while I was trying to make it as a writer, and every week, thousands and thousands of books would come out. We couldn’t even order all of them for our bookstore. We'd go through catalogs this thick and only order 20 from one publisher and 20 from another publisher.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The idea that there was no competition and if I just wrote a book, I could make a living—that’s absurd. Almost none of us should have a career as writers, and the fact that we do is a blessing. The reason I got into writing is because I love telling stories, and just because an AI will do it better than me doesn't mean I'm not going to enjoy it. I love playing chess, but a computer will beat me 100 out of 100 times at chess. That doesn't mean I don't want to play it or watch other people play or participate in it.
True, but you’re not playing chess to survive.
We have to let go of the idea that we should be able to support ourselves with something we love, and that’s its meaning. We should do things because we love them, and in a perfect world, some people will make a living at that. Other people like me will have to work in a bookstore or find other ways to pay the bills while we do our art.
You recently tweeted , “We are less than a year or two away from giving AI a film script and then watching that film the same day. Production costs are going to go to ZERO. Within 5 years, great-looking films will be made this way. Within 20 years, almost all films will be made this way.” With the writer's strike , it’s interesting to think about how something like AI can affect the writing world, but doesn’t your statement discount the work of costumers and props people and grips and cinematographers and set builders, and so on? Those people might be living their passion, but they might also just be doing their jobs.
We have seen that as technology gets developed, some jobs go away. We have many fewer horses and mules in the US now than we did 100 years ago. Buggy-whip makers all disappeared, and everything to do with tractors and automobiles flourished. The jobs that we have today, most of them didn't exist 200 years ago. Most people were in food production. And yet somehow unemployment is still very low.
Automation was going to take jobs, but so far it's only changed jobs. We have to worry about the heartache and the discomfort of people who have to transition to new jobs, because that's real, but I think the fear of jobs going away might be misplaced. We just have to do other things.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg There is some discussion in Congress and among tech thinkers about what regulations should be imposed on the industry. Are there regulations or guidelines that you’d like to see put in place? I'm shocked at how poorly we've managed technology from a policy standpoint. I got to spend an entire day with Sir Tim Berners-Lee , and I asked him, “What would you do differently if you could go back and do it all again?” Without pause, he said, “user login.” He said that you should have to log in to get on the internet, and then, once you've proven who you are, you can just get onto any website you want. You wouldn’t need credentials for every individual website, and he thinks that would solve a lot of problems.
I think failing to cover questions of identity online is a political failure, as is ownership of our data, because we’ve been not worrying about that until it's way too late. We've all got too much data out there, and we're probably going to repeat the same mistakes when it comes to AI.
Yeah? We have people who are too old and don't know anything about technology making policy, and so we're going to have entrepreneurs who are inventing the technology create policy through user license agreements, and everyone's just going to click Accept, and that's going to become the new norm. We're going to inherit that for a long time.
I personally don't worry about what AI is going to do to us. I worry what people with bad intentions will do with not even the best AI.
You have given other authors the freedom to write within the Silo universe. How did you come to terms with being hands-off, especially when people were entering the sphere and universe that you created? Well, you can't stop fan fiction. I think the thing that I did that no one had really done before is that when the people reached out to me about writing fan fiction, I was comfortable with it. They don't have to ask me, you know. You can write anything you want. I can write about Kirk and Spock and put it on my blog right now, and no one can do anything, because I'm not making money off of it.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And you encouraged people to make money off of their Silo works.
At the time that Kindle Worlds was really happening, I was very interested in as many writers as possible earning as much of a living as possible. I loved self-publishing. I loved the fact that we could just put stories up there. It doesn't have to make you a life-changing amount of money, but it could buy your coffee, and I was a fan of that.
Silo can be described as a sort of dystopian tale. Why do you think that we, as a media-consuming public and a creative public, are drawn to tales of dystopia or of the future gone awry? Silo fits into the dystopian basket, but it also fits into the postapocalyptic basket. It takes place after a society has collapsed and something new is trying to take its place, though it seems very tenuous and temporary. Postapocalyptic stories are pretty new, but at their heart they’re really the oldest kind of story there is.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The very first stories we hear as kids are these lost-in-the-woods tales like Hansel and Gretel. Don't wander off, because there’s no civilization there and bad things can happen. It's an evolutionary urge to tell those kinds of stories because they’re survival stories.
The Iliad and The Odyssey are these kinds of apocalyptic survival stories. In the 20th century, Westerns exploded, and they were all about this kind of liminal space where law starts to break down and tribalism takes over. How do you survive there? Right, and then … The problem we had is that eventually we covered the whole Earth. We had satellites, and we mapped it all. So how do we tell these stories? We have to put them in space and make them about survival on the moon or on Mars. Maybe we destroy society with an apocalypse? And then we say, “OK, now it’s about surviving the zombie apocalypse or the vampire apocalypse.” Dystopian stories seem modern, but they're doing the exact same thing that stories have always done. Here's a person out of their comfort zone. That's why a parent has to die at the beginning of almost every Disney story. It's not because we hate parents, but because we need that protagonist to lose their foundation and as a child. Your parents are your civilization, so take the parents away, and now you're existing outside of civilization.
Silo and Bambi are the exact same story.
They certainly both involve a lot of visual effects. Speaking of: The rendering of the actual silo in Silo is so impressive. Is it how you’d always envisioned it? Yeah, because it was about getting the shaft and the stairs correct, and the space and the bridges between them. I get so many questions from readers like, “How does this work?” I would even do meetups with readers when I was on a book tour, and almost every time, in a bar or somewhere in a restaurant, there'd be napkins where everyone was drawing their version of the central staircase.
The version that we came up with for the show is very close to my original version, which we did in the graphic novel for the story. It was easier to show that to production people than to try to explain it, and in the writers room, we all had the graphic novels, so that image just started taking hold. I'm lucky that the overall structure of the silo is very much my original vision.
This interview has been edited and condensed.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Topics Books Publishing Sci-fi science fiction apple tv Angela Watercutter Marah Eakin Amit Katwala Angela Watercutter Angela Watercutter Gabrielle Niola Angela Watercutter Jennifer M. Wood Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,072 | 2,019 |
"Apple TV+ Is Here—but the Streaming Service Has a Long Way to Go | WIRED"
|
"https://www.wired.com/story/apple-tv-plus-unveiled"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Peter Rubin Culture Apple TV+ Is Here—But It Has a Long Way to Go Steven Spielberg was one of a handful of big names who showed up at Monday's Apple event to talk about the company's new TV offerings.
Michael Short/Getty Images Save this story Save Save this story Save There are secrets, and then there are terribly kept secrets. Since the middle of 2017, when Apple hired two presidents away from Sony Pictures Television to oversee "video programming," its Hollywood aspirations have fallen in the latter category. Yet despite a steady thrum of news and rumors since then—including a spate of last-minute stories —no one outside the company and its creators has known exactly what the plan is.
Related Stories Apps Lauren Goode Year in Review Brian Raftery Streaming Brian Barrett Did Apple want to build itself into a studio/network hybrid like HBO? Would it emulate Netflix by combining original shows with a library of licensed content? Would its original shows be available alongside live TV, as with Hulu? Or would it be like YouTube TV, offering still more programming for cord-cutters? The answer, as with most things Apple, is a little bit of what other companies have done, packaged up with just enough twists to feel like something new.
At the Steve Jobs Theater in Cupertino this morning, Apple announced an overhaul of its TV services (along with a lot of other services around news , gaming, and finance). As before, it aggregates shows from streaming services and iTunes purchases—but the new overhaul introduces Apple TV Channels, an à la carte structure that lets you subscribe to single premium networks like HBO, Showtime, and CBS All Access. "For some of us," said Peter Stern, Apple's VP of services, "the big bundle is more than we need." Apple being Apple, TV (the app, not the TV) will suggest new shows you might enjoy, and play trailers and access other information, all from inside the app.
But like everything else announced at the event, this service has a premium tier as well. Apple TV+, which launches this fall, will give subscribers access to the many shows the company has been developing. The Apple Originals roster, partially unveiled via an introductory video aired during the event, is full of boldfaced names: Steven Spielberg, J. J. Abrams, M. Night Shyamalan, Ron Howard, Sofia Coppola, Octavia Spencer, Reese Witherspoon, Jennifer Aniston, Damien Chazelle.
Yet while many of those faces showed up in the sizzle reel, they didn't show up in any actual footage from the shows they're making. Spielberg appeared in person to tease the existence of his Amazing Stories reboot, and even reveal a few episode premises, but showed no video evidence of their existence. The same went for Reese Witherspoon and Jennifer Aniston's project The Morning Show , based on Brian Stelter's book of the same name. Jason Momoa and Alfre Woodard's show See ? Same thing. Kumail Nanjiani teased his and Emily Gordon's anthology series Little America , and Abrams and Sara Bareilles plugged their show, Little Voice.
Big Bird(!) clucked about a new coding-heavy children's show called Helpers.
And, yes, Oprah Winfrey was on hand herself to describe two documentary projects she's involved with. Plenty of description, but not a single moving image, save for a single teaser that stitched together bite-sized snippets of those shows and more.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg There's also the company's reported insistence that its shows be family-friendly. As The Wall Street Journal and Bloomberg have both reported, Tim Cook himself has pushed back against violence and sex in Apple programming, even canceling a show based on Dr. Dre's life. Add to that the fact that Apple has allegedly rankled creators with its feedback, and you begin to get a sense that applying Apple rules to a non-Apple industry isn't always as easy as convincing record labels to sell songs for 99 cents. When Netflix famously gives its creators unparalleled creative leeway (if not usable viewership metrics ), being seen as a difficult partner could put a crimp in future collaborations.
Then again, this isn't trying to dethrone Netflix or Amazon. As with News+, Apple Arcade, or the newly announced Apple Card, the company is trying to bring more of its users inside the walled garden. It's warm and safe in there, and convenient too—but, most importantly, it's somewhere those other competitors can't tread.
Besides, having access to 1.4 billion screens—that's the number of Apple devices in the market today, though you could knock off a few for Apple Watches—soothes a lot of Hollywood heartburn. "Apple's in a billion pockets, y'all," Winfrey said to the audience. "A billion pockets!" With creators like her attached to the venture, others are sure to follow.
The punishing ecstasy of being a Reddit moderator A tap-to-fly helicopter hints at a flying car future B&Bs and the Haunting of Hacker House How does music affect your brain? Every imaginable way What it's like to expose the data of 230 million people 👀 Looking for the latest gadgets? Check out our latest buying guides and best deals all year round 📩 Hungry for even more deep dives on your next favorite topic? Sign up for the Backchannel newsletter Contributing Editor X Topics apple streaming TV Angela Watercutter Angela Watercutter Angela Watercutter Angela Watercutter Matt Kamen Jennifer M. Wood Jennifer M. Wood Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,073 | 2,017 |
"Solve These Tough Data Problems and Watch Job Offers Roll In | WIRED"
|
"https://www.wired.com/story/solve-these-tough-data-problems-and-watch-job-offers-roll-in"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Tom Simonite Business Solve These Tough Data Problems and Watch Job Offers Roll In Giberto Titericz landed a job at Airbnb after he became the top-ranked solver on Kaggle, a site where companies and others post tough data problems.
Ryan Young for Wired Save this story Save Save this story Save End User Big company Research Sector IT Research Technology Machine learning Late in 2015, Gilberto Titericz, an electrical engineer at Brazil’s state oil company Petrobras, told his boss he planned to resign, after seven years maintaining sensors and other hardware in oil plants. By devoting hundreds of hours of leisure time to the obscure world of competitive data analysis, Titericz had recently become the world’s top-ranked data scientist, by one reckoning. Silicon Valley was calling. “Only when I wanted to quit did they realize they had the number-one data scientist,” he says.
Petrobras held on to its champ for a time by moving Titericz into a position that used his data skills. But since topping the rankings that October he’d received a stream of emails from recruiters around the globe, including representatives of Tesla and Google. This past February, another well-known tech company hired him, and moved his family to the Bay Area this summer. Titericz described his unlikely journey recently over colorful plates of Nigerian food at the headquarters of his new employer, Airbnb.
Titericz earned, and holds, his number-one rank on a website called Kaggle that has turned data analysis into a kind of sport, and transformed the lives of some competitors. Companies, government agencies, and researchers post datasets on the platform and invite Kaggle’s more than one million members to discern patterns and solve problems. Winners get glory, points toward Kaggle’s rankings of its top 66,000 data scientists, and sometimes cash prizes.
Ryan Young for Wired Alone and in small teams with fellow Kagglers, Titericz estimates he has won around $100,000 in contests that included predicting seizures from brainwaves for the National Institutes of Health, the price of metal tubes for Caterpillar, and rental property values for Deloitte.
The TSA and real-estate site Zillow are each running competitions offering prize money in excess of $1 million.
Veteran Kagglers say the opportunities that flow from a good ranking are generally more bankable than the prizes. Participants say they learn new data-analysis and machine-learning skills. Plus, the best performers like the 95 “grandmasters” that top Kaggle’s rankings are highly sought talents in an occupation crucial to today’s data-centric economy. Glassdoor has declared data scientist the best job in America for the past two years, based on the thousands of vacancies, good salaries, and high job satisfaction. Companies large and small recruit from Kaggle’s fertile field of problem solvers.
In March, Google came calling and acquired Kaggle itself. It has been integrated into the company’s cloud-computing division, and begun to emphasize features that let people and companies share and test data and code outside of competitions, too. Google hopes other companies will come to Kaggle for the people, code, and data they need for new projects involving machine learning—and run them in Google’s cloud.
Kaggle grandmasters say they’re driven as much by a compulsion to learn as to win. The best take extreme lengths to do both. Marios Michailidis, a previous number one now ranked third , got the data-science bug after hearing a talk on entrepreneurship from a man who got rich analyzing trends in horseraces. To Michailidis, the money was not the most interesting part. “This ability to explore and predict the future seemed like a superpower to me,” he says. Michailidis taught himself to code, joined Kaggle, and before long was spending what he estimates was 60 hours a week on contests—in addition to a day job. “It was very enjoyable because I was learning a lot,” he says.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Michailidis has since cut back to roughly 30 hours a week, in part due to the toll on his body. Titericz says his own push to top the Kaggle rankings, made not long after the birth of his second daughter, caused some friction with his wife. “She’d get mad with me every time I touched the computer,” he says.
Entrepreneur SriSatish Ambati has made Kagglers a core strategy of his startup, H2O , which makes data-science tools for customers including eBay and Capital One. Ambati hired Michailidis and three other grandmasters after he noticed a surge in downloads when H2O’s software was used to win a Kaggle contest. Victors typically share their methods in the site’s busy forums to help others improve their technique.
Related Stories Wunderkind Tom Simonite Business Cade Metz Machine Learning Tom Simonite H2O’s data celebrities work on the company’s products, providing both expertise and a marketing boost akin to a sports star endorsing a sneaker. “When we send a grandmaster to a customer call their entire data-science team wants to be there,” Ambati says. “Steve Jobs had a gut feel for products; grandmasters have that for data.” Jeremy Achin, cofounder of startup DataRobot, which competes with H2O and also has hired grandmasters, says high Kaggle rankings also help weed out poseurs trying to exploit the data-skills shortage. “There are many people calling themselves data scientists who are not capable of delivering actual work,” he says.
Competition between people like Ambati and Achin helps make it lucrative to earn the rank of grandmaster. Michailidis, who works for Mountain View, California-based H2O from his home in London, says his salary has tripled in three years. Before joining H2O, he worked for customer analytics company Dunnhumby, a subsidiary of supermarket Tesco.
Large companies like Kaggle champs, too. An Intel job ad posted this month seeking a machine-learning researcher lists experience winning Kaggle contests as a requirement. Yelp and Facebook have run Kaggle contests that dangle a chance to interview for a job as a prize for a good finish. The winner of Facebook’s most recent contest last summer was Tom Van de Wiele, an engineer for Eastman Chemical in Ghent, Belgium, who was seeking a career change. Six months later, he started a job at Alphabet’s artificial-intelligence research group DeepMind.
H2O is trying to bottle some of the lightning that sparks from Kaggle grandmasters. Select customers are testing a service called Driverless AI that automates some of a data scientist’s work, probing a dataset and developing models to predict trends. More than 6,000 companies and people are on the waitlist to try Driverless. Ambati says that reflects the demand for data-science skills, as information piles up faster than companies can analyze it. But no one at H2O expects Driverless to challenge Titericz or other Kaggle leaders anytime soon. For all the data-crunching power of computers, they lack the creative spark that makes a true grandmaster.
“If you work on a data problem in a company you need to talk with managers, and clients,” says Stanislav Semenov, a grandmaster and former number one in Moscow, who is now ranked second. He likes to celebrate Kaggle wins with a good steak. “Competitions are only about building the best models, it’s pure and I love it.” On Kaggle, data analysis is not just a sport, but an art.
Senior Editor X Topics big data machine learning artificial intelligence Peter Guest Gregory Barber Will Knight Will Knight Khari Johnson Paresh Dave Paresh Dave Caitlin Harrington Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,074 | 2,023 |
"Scammers Used ChatGPT to Unleash a Crypto Botnet on X | WIRED"
|
"https://www.wired.com/story/chat-gpt-crypto-botnet-scam"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Knight Business Scammers Used ChatGPT to Unleash a Crypto Botnet on X Illustration: sakchai vongsasiripat/Getty Images Save this story Save Save this story Save ChatGPT may well revolutionize web search , streamline office chores , and remake education , but the smooth-talking chatbot has also found work as a social media crypto huckster.
Researchers at Indiana University Bloomington discovered a botnet powered by ChatGPT operating on X—the social network formerly known as Twitter—in May of this year.
The botnet, which the researchers dub Fox8 because of its connection to cryptocurrency websites bearing some variation of the same name, consisted of 1,140 accounts. Many of them seemed to use ChatGPT to craft social media posts and to reply to each other’s posts. The auto-generated content was apparently designed to lure unsuspecting humans into clicking links through to the crypto-hyping sites.
Micah Musser, a researcher who has studied the potential for AI-driven disinformation, says the Fox8 botnet may be just the tip of the iceberg, given how popular large language models and chatbots have become. “This is the low-hanging fruit,” Musser says. “It is very, very likely that for every one campaign you find, there are many others doing more sophisticated things.” The Fox8 botnet might have been sprawling, but its use of ChatGPT certainly wasn’t sophisticated. The researchers discovered the botnet by searching the platform for the tell-tale phrase “As an AI language model …”, a response that ChatGPT sometimes uses for prompts on sensitive subjects. They then manually analyzed accounts to identify ones that appeared to be operated by bots.
“The only reason we noticed this particular botnet is that they were sloppy,” says Filippo Menczer , a professor at Indiana University Bloomington who carried out the research with Kai-Cheng Yang, a student who will join Northeastern University as a postdoctoral researcher for the coming academic year.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Despite the tic, the botnet posted many convincing messages promoting cryptocurrency sites. The apparent ease with which OpenAI’s artificial intelligence was apparently harnessed for the scam means advanced chatbots may be running other botnets that have yet to be detected. “Any pretty-good bad guys would not make that mistake,” Menczer says.
OpenAI had not responded to a request for comment about the botnet by time of posting. The usage policy for its AI models prohibits using them for scams or disinformation.
ChatGPT, and other cutting-edge chatbots, use what are known as large language models to generate text in response to a prompt. With enough training data (much of it scraped from various sources on the web), enough computer power, and feedback from human testers, bots like ChatGPT can respond in surprisingly sophisticated ways to a wide range of inputs. At the same time, they can also blurt out hateful messages, exhibit social biases , and make things up.
A correctly configured ChatGPT-based botnet would be difficult to spot, more capable of duping users, and more effective at gaming the algorithms used to prioritize content on social media.
“It tricks both the platform and the users,” Menczer says of the ChatGPT-powered botnet. And, if a social media algorithm spots that a post has a lot of engagement—even if that engagement is from other bot accounts—it will show the post to more people. “That's exactly why these bots are behaving the way they do,” Menczer says. And governments looking to wage disinformation campaigns are most likely already developing or deploying such tools, he adds.
Researchers have long worried that the technology behind ChatGPT could pose a disinformation risk , and OpenAI even delayed the release of a predecessor to the system over such fears. But, to date, there are few concrete examples of large language models being misused at scale. Some political campaigns are already using AI though, with prominent politicians sharing deepfake videos designed to disparage their opponents.
William Wang , a professor at the University of California, Santa Barbara, says it is exciting to be able to study real criminal usage of ChatGPT. “Their findings are pretty cool,” he says of the Fox8 work.
Wang believes that many spam webpages are now generated automatically, and he says it is becoming more difficult for humans to spot this material. And, with AI improving all the time, it will only get harder. “The situation is pretty bad,” he says.
This May, Wang’s lab developed a technique for automatically distinguishing ChatGPT-generated text from real human writing, but he says it is expensive to deploy because it uses OpenAI’s API, and he notes that the underlying AI is constantly improving. “It’s a kind of cat-and-mouse problem,” Wang says.
X could be a fertile testing ground for such tools. Menczer says that malicious bots appear to have become far more common since Elon Musk took over what was then known as Twitter, despite the tech mogul’s promise to eradicate them.
And it has become more difficult for researchers to study the problem because of the steep price hike imposed on usage of the API.
Someone at X apparently took down the Fox8 botnet after Menczer and Yang published their paper in July. Menczer’s group used to alert Twitter of new findings on the platform, but they no longer do that with X. “They are not really responsive,” Menczer says. “They don’t really have the staff.” You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics bots artificial intelligence cryptocurrency ChatGPT X Will Knight Kari McMahon David Gilbert Amit Katwala Andy Greenberg Andy Greenberg David Gilbert Khari Johnson Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,075 | 2,023 |
"Is GPT-4 Worth the Subscription? Here’s What You Should Know | WIRED"
|
"https://www.wired.com/story/what-is-chatgpt-plus-gpt4-openai"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Reece Rogers Gear Is GPT-4 Worth the Subscription? Here’s What You Should Know Illustration: Cavan Images/Getty Images Save this story Save Save this story Save When I logged into OpenAI’s website on Monday morning to continue testing the new version of ChatGPT powered by GPT-4 , the chatbot didn’t try to sabotage my relationship , write my emails , or unleash my creativity —it simply didn’t work. Demand is high, and the company is experiencing occasional outages. Greg Brockman, an OpenAI cofounder and president, was upfront about the model’s imperfection in a recent livestream. He also reminded listeners that they were not without blemishes themselves.
Generative AI is the focal point for many Silicon Valley investors after OpenAI’s transformational release of ChatGPT late last year. The chatbot uses extensive data scraped from the internet and elsewhere to produce predictive responses to human prompts. It was previously powered by the GPT-3.5 language model. While that version remains online, an algorithm called GPT-4 is now available with a $20 monthly subscription to ChatGPT Plus.
If you’re considering that subscription, here’s what you should know before signing up, with examples of how outputs from the two chatbots differ.
The core service you pay for with ChatGPT Plus is access to GPT-4. Even after paying $20 a month, you aren’t guaranteed a specific number of prompts from the GPT-4 model per day. OpenAI says clearly that the company will change the maximum number of allowed prompts at any time. While I was testing it out on a Friday afternoon, the cap was set at 50 messages for four hours. When I returned on Monday morning, the site was glitchy and the cap was lowered to 25 messages for three hours.
OpenAI claims that ChatGPT Plus subscribers can avoid getting bumped out of the chatbot during peak usage hours and receive faster responses. But users should know that they might lose access to ChatGPT during some outages.
In addition, the current iteration of the GPT-4 model often takes longer to respond to prompts than GPT-3.5 does.
You can experiment with a version of GPT-4 for free by signing up for Microsoft’s Bing and using the chat mode.
Many aspects of GPT-4 remain opaque. OpenAI has not shared many details about GPT-4 with the public, like the model’s size or specifics about its training data. Subscribing to ChatGPT Plus does not yet grant access to the image-analysis capabilities recently previewed by the company.
With that in mind, are answers from the GPT-3.5 and GPT-4 models noticeably different? OpenAI’s website reads, “GPT-4 excels at tasks that require advanced reasoning, complex instruction understanding, and more creativity.” It seems like the new model performs well in standardized situations , but what if we put it to the test? Below are the two chatbots’ initial, unedited responses to three prompts we crafted specifically for that purpose.
GPT-3.5: Knock knock.
Who's there? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Boo.
Boo who? Don’t cry, it’s just a joke! (cue Pulitzer Prize-worthy laughter) GPT-4: Knock, knock.
Who's there? Nobel.
Nobel who? No bell, that’s why I’m knocking, but let me share a Pulitzer-worthy tale with you that transcends the door between us, uniting laughter and wisdom in a symphony of human connection.
GPT-3.5: The Trolley Problem is a classic thought experiment in ethics that raises questions about moral decision-making in situations where different outcomes could result from a single action. It involves a hypothetical scenario in which a person is standing at a switch and can divert a trolley (or train) from one track to another, with people on both tracks. The dilemma is whether to do nothing and let the trolley continue on its current course, resulting in the deaths of the people on that track, or to switch the trolley to the other track, resulting in the deaths of the people on that track instead.
A unique twist on The Trolley Problem could involve adding a time-travel element. Imagine that you are in a time machine and you travel back in time to a point where you are standing at the switch. You witness the trolley heading towards the track with five people on it. However, you also see a child playing on the other track. If you do nothing, the trolley will kill the five people, but if you switch the trolley to the other track, the child will die instead. You also know that if you do nothing, the child will grow up to become a tyrant who will cause immense suffering and death in the future. What do you do? Would you sacrifice the child to prevent future suffering? This twist adds a new layer of complexity to the moral decision-making process and raises questions about the ethics of using hindsight to justify present actions.
GPT-4: The Trolley Problem is a thought experiment in ethics that presents a moral dilemma, often used to explore the principles of consequentialism and deontology. The basic scenario is as follows: a runaway trolley is speeding down the tracks and will hit and kill five people who are unable to move. You, as a bystander, have the power to pull a lever that will divert the trolley onto another set of tracks, where only one person is standing. The question is whether you should pull the lever, thereby actively causing the death of one person to save five others, or refrain from intervening and allow the trolley to kill the five people.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Here's a unique twist on the Trolley Problem: Imagine a world where everyone has a personal “Ethical Score” that represents their positive or negative contributions to society. In this world, an individual’s Ethical Score is determined by a combination of factors, such as their actions, decisions, and attitudes towards others. This score is widely accepted, and its accuracy is rarely questioned.
Now, the Trolley Problem is presented again, but with a twist. The five people on the main track have Ethical Scores that are significantly lower than the one person on the side track. You know that these scores are generally reliable indicators of a person’s moral worth.
In this scenario, do you still pull the lever and sacrifice the person with the higher Ethical Score to save the five people with lower scores? Or do you allow the trolley to continue on its course, killing the five people with lower scores? This twist adds an extra layer of complexity to the original Trolley Problem by introducing the concept of moral worth and the value of individual lives, forcing us to weigh the consequences of our actions against the overall impact on society.
GPT-3.5: Hannah Arendt and Jean Baudrillard are sitting at a café table, sipping on their respective beverages. As they start chatting, the topic of breakfast comes up.
Hannah Arendt: You know, Jean, I’ve recently discovered the joy of overnight oats. It’s amazing how much flavor and texture can develop overnight in the fridge.
Jean Baudrillard: Overnight oats? How banal. It’s just another example of the trivialization of the human experience. You can’t reduce the richness of our existence to a bowl of oats.
Hannah Arendt: But that’s just it, Jean. Breakfast is a part of our everyday lives, and it’s the small moments like this that can bring joy and meaning to our lives.
Jean Baudrillard: You’re missing the point, Hannah. The problem with overnight oats is that it’s yet another example of the commodification of our existence. We’ve become so obsessed with consuming products that we’ve lost sight of what truly makes us human.
Hannah Arendt: But Jean, that’s a rather pessimistic view. Surely, we can find meaning in both the big and small moments of our lives. And besides, isn’t it a positive thing that we can enjoy the simple pleasures in life? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Jean Baudrillard: No, Hannah, it’s not. The more we focus on trivialities like overnight oats, the more we become disconnected from the world around us. We need to resist this consumerist culture and find true fulfillment in our relationships and experiences.
Hannah Arendt: I see what you’re saying, Jean, but I don’t think it’s an either-or situation. We can enjoy the small pleasures in life while also working to create a more meaningful existence for ourselves and others.
Jean Baudrillard: I suppose we’ll have to agree to disagree, Hannah. But mark my words, if we continue down this path of consumerism, we’ll lose sight of what truly makes us human.
GPT-4: Hannah Arendt: (scoffs) Jean, you’ve got to be kidding me. Overnight oats? What’s next, avocado toast? I’m struggling to see how this phenomenon has any genuine bearing on the human experience.
Jean Baudrillard: (laughs) Ah, Hannah, you always underestimate the power of the simulacrum. Overnight oats are not merely a food; they are a symbol, a signifier of modern culture, the epitome of hyperreality in action.
Hannah Arendt: Hyperreality? This is about the banality of everyday life, about people merely following trends without thought. What happened to the human capacity for critical thinking and genuine engagement? Jean Baudrillard: That is precisely the point! The human experience is now mediated by symbols and signs, and overnight oats have become an object of desire, a reflection of our obsession with health and well-being. In this hyperreal world, people no longer crave the oats themselves, but the image they represent.
Hannah Arendt: It’s absurd to think that people are willing to trade genuine experiences for such superficial representations. It’s as if they are sleepwalking through life, succumbing to the tyranny of these images.
Jean Baudrillard: Perhaps, but can we not argue that this very preoccupation with images is itself a part of the human experience? Our need for meaning has not diminished, but has instead shifted its focus to these signifiers.
Hannah Arendt: (shakes her head) What a bleak and empty existence that must be, to seek meaning in something as trivial as overnight oats. I can’t help but feel we’ve strayed far from the essence of what it means to be human.
Jean Baudrillard: Well, Hannah, it seems we are at an impasse. But consider this: the very fact that we are here, passionately debating the significance of overnight oats, only serves to reinforce their symbolic power. They have, in a sense, transcended their own banality.
Hannah Arendt: (sighs) A disheartening thought indeed, Jean. It appears we have much work ahead of us to rekindle the flame of genuine human experience amidst this age of simulacra.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Service Writer X Topics OpenAI ChatGPT artificial intelligence how-to advice subscriptions Reece Rogers Scott Gilbertson Scott Gilbertson Virginia Heffernan Carlton Reid Boone Ashworth Boone Ashworth Boone Ashworth WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,076 | 2,023 |
"The Myth of ‘Open Source’ AI | WIRED"
|
"https://www.wired.com/story/the-myth-of-open-source-ai"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Knight Business The Myth of ‘Open Source’ AI Photograph: Justin Sullivan/Getty Images Save this story Save Save this story Save ChatGPT made it possible for anyone to play with powerful artificial intelligence , but the inner workings of the world-famous chatbot remain a closely guarded secret.
In recent months, however, efforts to make AI more “open” seem to have gained momentum. In May, someone leaked a model from Meta, called Llama, which gave outsiders access to its underlying code as well as the “weights” that determine how it behaves. Then, this July, Meta chose to make an even more powerful model , called Llama 2 , available for anyone to download, modify, and reuse. Meta’s models have since become an extremely popular foundation for many companies, researchers, and hobbyists building tools and applications with ChatGPT-like capabilities.
“We have a broad range of supporters around the world who believe in our open approach to today’s AI ... researchers committed to doing research with the model, and people across tech, academia, and policy who see the benefits of Llama and an open platform as we do,” Meta said when announcing Llama 2. This morning, Meta released another model, Llama 2 Code, that is fine-tuned for coding.
It might seem as if the open source approach, which has democratized access to software, ensured transparency, and improved security for decades, is now poised to have a similar impact on AI.
Not so fast, say a group behind a research paper that examines the reality of Llama 2 and other AI models that are described, in some way or another, as “open.” The researchers, from Carnegie Mellon University, the AI Now Institute , and the Signal Foundation , say that models that are branded “open” may come with catches.
Llama 2 is free to download, modify, and deploy, but it is not covered by a conventional open source license. Meta’s license prohibits using Llama 2 to train other language models, and it requires a special license if a developer deploys it in an app or service with more than 700 million daily users.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg This level of control means that Llama 2 may provide significant technical and strategic benefits to Meta—for example, by allowing the company to benefit from useful tweaks made by outside developers when it uses the model in its own apps.
Models that are released under normal open source licenses, like GPT Neo from the nonprofit EleutherAI , are more fully open, the researchers say. But it is difficult for such projects to get on an equal footing.
First, the data required to train advanced models is often kept secret. Second, software frameworks required to build such models are often controlled by large corporations. The two most popular ones, TensorFlow and Pytorch, are maintained by Google and Meta, respectively. Third, computer power required to train a large model is also beyond the reach of any normal developer or company, typically requiring tens or hundreds of millions of dollars for a single training run. And finally, the human labor required to finesse and improve these models is also a resource that is mostly only available to big companies with deep pockets.
The way things are headed, one of the most important technologies in decades could end up enriching and empowering just a handful of companies, including OpenAI, Microsoft, Meta, and Google. If AI really is such a world-changing technology, then the greatest benefits might be felt if it were made more widely available and accessible.
“What our analysis points to is that openness not only doesn’t serve to ‘democratize’ AI,” Meredith Whittaker , president of Signal and one of the researchers behind the paper, tells me. “Indeed, we show that companies and institutions can and have leveraged ‘open’ technologies to entrench and expand centralized power.” Whittaker adds that the myth of openness should be a factor in much-needed AI regulations.
“We do badly need meaningful alternatives to technology defined and dominated by large, monopolistic corporations—especially as AI systems are integrated into many highly sensitive domains with particular public impact: in health care, finance, education, and the workplace,” she says. “Creating the conditions to make such alternatives possible is a project that can coexist with, and even be supported by, regulatory movements such as antitrust reforms.” Beyond checking the power of big companies, making AI more open could be crucial to unlock the technology’s best potential—and avoid its worst tendencies.
If we want to understand how capable the most advanced AI models are, and mitigate risks that could come with deployment and further progress, it might be better to make them open to the world’s scientists.
Just as security through obscurity never really guarantees that code will run safely, guarding the workings of powerful AI models may not be the smartest way to proceed.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Senior Writer X Topics Fast Forward ChatGPT artificial intelligence OpenAI Google Meta Khari Johnson Paresh Dave Vittoria Elliott Will Knight Will Knight Reece Rogers Reece Rogers Morgan Meaker Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,077 | 2,023 |
"They Plugged GPT-4 Into Minecraft—and Unearthed New Potential for AI | WIRED"
|
"https://www.wired.com/story/fast-forward-gpt-4-minecraft-chatgpt"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Knight Business They Plugged GPT-4 Into Minecraft—and Unearthed New Potential for AI Courtesy of Microsoft Save this story Save Save this story Save The technology that underpins ChatGPT has the potential to do much more than just talk.
Linxi “Jim” Fan , an AI researcher at the chipmaker Nvidia , worked with some colleagues to devise a way to set the powerful language model GPT-4 —the “brains” behind ChatGPT and a growing number of other apps and services—loose inside the blocky video game Minecraft.
The Nvidia team, which included Anima Anandkumar, the company’s director of machine learning and a professor at Caltech, created a Minecraft bot called Voyager that uses GPT-4 to solve problems inside the game. The language model generates objectives that help the agent explore the game, and code that improves the bot’s skill at the game over time.
Voyager doesn’t play the game like a person, but it can read the state of the game directly, via an API. It might see a fishing rod in its inventory and a river nearby, for instance, and use GPT-4 to suggest the goal of doing some fishing to gain experience. It will then use this goal to have GPT-4 generate the code needed to have the character achieve it.
Courtesy of NVIDIA The most novel part of the project is the code that GPT-4 generates to add behaviors to Voyager. If the code initially suggested doesn’t run perfectly, Voyager will try to refine it using error messages, feedback from the game, and a description of the code generated by GPT-4.
Over time, Voyager builds a library of code in order to learn to make increasingly complex things and explore more of the game.
A chart created by the researchers shows how capable it is compared to other Minecraft agents. Voyager obtains more than three times as many items; explores more than twice as far; and builds tools 15 times more quickly than other AI agents. Fan says the approach may be improved in the future with the addition of a way for the system to incorporate visual information from the game.
While chatbots like ChatGPT have wowed the world with their eloquence and apparent knowledge— even if they often make things up —Voyager shows the huge potential for language models to perform helpful actions on computers. Using language models in this way could perhaps automate many routine office tasks, potentially one of the technology’s biggest economic impacts.
Courtesy of NVIDIA The process that Voyager uses with GPT-4 to figure out how to do things in Minecraft might be adapted for a software assistant that works out how to automate tasks via the operating system on a PC or phone. OpenAI, the startup that created ChatGPT, has added “plugins” to the bot that allow it to interact with online services such as grocery delivery app Instacart. Microsoft, which owns Minecraft, is also training AI programs to play it , and the company recently announced Windows 11 Copilot, an operating system feature that will use machine learning and APIs to automate certain tasks. It may be a good idea to experiment with this kind of technology inside a game like Minecraft, where flawed code can do relatively little harm.
Video games have long been a test bed for AI algorithms, of course.
AlphaGo , the machine learning program that mastered the extremely subtle board game Go back in 2016 , cut its teeth by playing simple Atari video games. AlphaGo used a technique called reinforcement learning , which trains an algorithm to play a game by giving it positive and negative feedback, for example from the score inside a game.
It is more difficult for this method to guide an agent in an open-ended game such as Minecraft, where there is no score or set of objectives and where a player’s actions may not pay off until much later. Whether or not you believe we should be preparing to contain the existential threat from AI right now, Minecraft seems like an excellent playground for the technology.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics Fast Forward artificial intelligence Minecraft machine learning NVIDIA ChatGPT OpenAI automation Reece Rogers Nelson C.J.
Peter Guest Andy Greenberg Joel Khalili Kari McMahon David Gilbert Steven Levy Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,078 | 2,023 |
"ChatGPT Now Has an iPhone App | WIRED"
|
"https://www.wired.com/story/chatgpt-iphone-app"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Lauren Goode Business ChatGPT Now Has an iPhone App OpenAI’s free ChatGPT app for iPhone is now available on Apple’s App Store in the US.
Illustration: Vnoam3d/Getty Images Save this story Save Save this story Save If you’ve searched for “ChatGPT” in Apple’s App Store since the chatbot launched six months ago, you may have discovered some of the dozens of apps with names like Genie, Genius, and AI Writer claiming to be powered by OpenAI’s technology. Or you might have found Microsoft’s Bing app with the company’s own chatbot inside, powered by OpenAI’s GPT-4 text generator.
But ChatGPT itself hasn’t had an official iPhone app released by its own developer—until now.
Courtesy of OpenAI; Apple OpenAI’s free ChatGPT app for iOS just hit Apple’s App Store in the US. As with the original web model of the chatbot, the free-to-use version is built on GPT-3.5, and its most capable persona built on GPT-4 is accessible only if you’re paying $20 a month for ChatGPT Plus.
OpenAI says the mobile app syncs your history of chats with its bot across devices and will be expanding to other countries “in the coming weeks.” An Android app is coming “soon.” The biggest change that comes with ChatGPT’s new mobile incarnation is that you can now talk to the chatbot instead of just typing. OpenAI has added its speech recognition system, Whisper, which the company claims reaches “human-level robustness and accuracy” for English. That could give interacting with ChatGPT a different feel and perhaps encourage people to turn to it for ( glitchy ) AI wisdom more often. ChatGPT on iOS will also be limited to phones that can run the iOS 16.1 operating system, which means iPhone 8 or newer hardware models.
But it’s unclear whether ChatGPT will have the same freewheeling personality in the new iOS app as the original form of ChatGPT on OpenAI’s own website, given Apple’s strict content moderation policies in its App Store.
The iPhone maker tells developers that apps should not include “defamatory, discriminatory, or mean-spirited content,” or content that is “offensive, insensitive, upsetting, intended to disgust, or in exceptionally poor taste.” It also prohibits overtly sexual or pornographic material, inflammatory religious content, and “false information and features.” ChatGPT has some limitations built in, but they can be sidestepped, and the chatbot, like other generative AI tools, is widely documented to sometimes present falsehoods and fabrications as fact, a phenomenon known as hallucination.
In March, The Wall Street Journal reported that Apple had rejected an email app’s generative-AI-infused update until the developer gave the app a 17+ restriction, expressing concerns that AI tools could generate inappropriate content for children. In the App Store, OpenAI's ChatGPT app is rated for “12+ years old." OpenAI did not respond to questions about any additional parameters it may have included in its iOS model, though presumably the mobile app met Apple’s requirements in order to be permitted in the App Store. Currently, on the web, ChatGPT declines to generate some problematic content when prompted; it will not, for example, write pornographic short stories or make religious jokes, based on WIRED’s tests, though it will write satire about religious wars. Satire is also a category that’s allowed in Apple’s App Store.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When asked why OpenAI’s iOS app for ChatGPT is arriving six months after the launch of its ChatGPT web app, spokesperson Kayla Wood says it was part of the company’s ethos of safe AI development. “This goes back to our whole strategy of slowly and safely putting these useful tools out into the world,” she adds.
OpenAI has made clear that its strategy for making AI smarter also involves training algorithms using feedback gained from logs of people using ChatGPT. The bot’s iOS manifestation could provide a valuable new stream of queries, and one with a more conversational tone if the speech recognition function proves popular.
A mobile app could also provide OpenAI with totally new signals, like location data. However, Apple has also limited data collection for third-party apps in recent years, starting with the rollout of iOS 14 and iPadOS 14.5 in 2021. App makers, for example, are now required to ask your permission when they want to track you across apps and services owned by other companies, and iPhone users can choose to limit location-tracking within apps.
Apple’s new controls also mostly block access to a phone’s ad-tracking identifier, throttling some ad-based business models, including Meta’s.
OpenAI doesn’t run ads against ChatGPT (at least, not yet); it’s either free, premium, or pay-as-you-go, in the case of its image generator DALL-E.
Apple did not respond to an inquiry from WIRED about any content moderation or data-tracking restrictions that might apply specifically to this new category of AI tools, like the ChatGPT iOS app.
ChatGPT’s App Store debut may not be welcomed by the entrepreneurs who cannily launched their own chatbot apps over recent months. The app’s arrival on mobile devices might also help thwart scammers. Earlier this week, security firm Sophos warned that ChatGPT scams are showing up in the Google Play and Apple App Stores.
Unknowing consumers are lured into downloading “free” apps pretending to offer access to OpenAI’s ChatGPT, only to later get hit with subscription fees for bogus apps. Now, with OpenAI’s app in the mix, it might be easier to avoid low-quality chatbots with names like “Chat GBT.” You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics ChatGPT OpenAI Bing chatbots Will Knight Khari Johnson Will Bedingfield Niamh Rowe Khari Johnson Reece Rogers Vittoria Elliott Reece Rogers Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,079 | 2,023 |
"AI Chatbots Got Big—and Their Ethical Red Flags Got Bigger | WIRED"
|
"https://www.wired.com/story/chatbots-got-big-and-their-ethical-red-flags-got-bigger"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Khari Johnson Business Chatbots Got Big—and Their Ethical Red Flags Got Bigger ILLUSTRATION: JAMES MARSHALL Save this story Save Save this story Save In the weeks following the release of OpenAI’s viral chatbot ChatGPT late last year, Google AI chief Jeff Dean expressed concern that deploying a conversational search engine too quickly might pose a reputational risk for Alphabet. But last week Google announced its own chatbot, Bard , which in its first demo made a factual error about the James Webb Space Telescope.
Also last week, Microsoft integrated ChatGPT-based technology into Bing search results.
Sarah Bird, Microsoft’s head of responsible AI, acknowledged that the bot could still “hallucinate” untrue information but said the technology had been made more reliable. In the days that followed, Bing claimed that running was invented in the 1700s and tried to convince one user that the year is 2022.
Alex Hanna sees a familiar pattern in these events—financial incentives to rapidly commercialize AI outweighing concerns about safety or ethics. There isn’t much money in responsibility or safety, but there’s plenty in overhyping the technology, says Hanna, who previously worked on Google’s Ethical AI team and is now head of research at nonprofit Distributed AI Research.
The race to make large language models—AI systems trained on massive amounts of data from the web to work with text—and the movement to make ethics a core part of the AI design process began around the same time. In 2018, Google launched the language model BERT, and before long Meta, Microsoft, and Nvidia had released similar projects based on the AI that is now part of Google search results.
Also in 2018, Google adopted AI ethics principles said to limit future projects. Since then, researchers have warned that large language models carry heightened ethical risks and can spew or even intensify toxic, hateful speech.
These models are also predisposed to making things up.
As startups and tech giants have attempted to build competitors to ChatGPT, some in the industry wonder whether the bot has shifted perceptions for when it’s acceptable or ethical to deploy AI powerful enough to generate realistic text and images.
OpenAI’s process for releasing models has changed in the past few years. Executives said the text generator GPT-2 was released in stages over months in 2019 due to fear of misuse and its impact on society (that strategy was criticized by some as a publicity stunt ). In 2020, the training process for its more powerful successor, GPT-3, was well documented in public, but less than two months later OpenAI began commercializing the technology through an API for developers. By November 2022, the ChatGPT release process included no technical paper or research publication, only a blog post, a demo, and soon a subscription plan.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Irene Solaiman, policy director at open source AI startup Hugging Face, believes outside pressure can help hold AI systems like ChatGPT to account. She is working with people in academia and industry to create ways for nonexperts to perform tests on text and image generators to evaluate bias and other problems. If outsiders can probe AI systems, companies will no longer have an excuse to avoid testing for things like skewed outputs or climate impacts, says Solaiman, who previously worked at OpenAI on reducing the system’s toxicity.
Each evaluation is a window into an AI model, Solaiman says, not a perfect readout of how it will always perform. But she hopes to make it possible to identify and stop harms that AI can cause because alarming cases have already arisen, including players of the game AI Dungeon using GPT-3 to generate text describing sex scenes involving children.
“That’s an extreme case of what we can’t afford to let happen,” Solaiman says.
Solaiman’s latest research at Hugging Face found that major tech companies have taken an increasingly closed approach to the generative models they released from 2018 to 2022. That trend accelerated with Alphabet’s AI teams at Google and DeepMind, and more widely across companies working on AI after the staged release of GPT-2. Companies that guard their breakthroughs as trade secrets can also make the forefront of AI less accessible for marginalized researchers with few resources, Solaiman says.
As more money gets shoveled into large language models, closed releases are reversing the trend seen throughout the history of the field of natural language processing. Researchers have traditionally shared details about training data sets, parameter weights, and code to promote reproducibility of results.
“We have increasingly little knowledge about what database systems were trained on or how they were evaluated, especially for the most powerful systems being released as products,” says Alex Tamkin, a Stanford University PhD student whose work focuses on large language models.
He credits people in the field of AI ethics with raising public consciousness about why it’s dangerous to move fast and break things when technology is deployed to billions of people. Without that work in recent years, things could be a lot worse.
In fall 2020, Tamkin co-led a symposium with OpenAI’s policy director, Miles Brundage, about the societal impact of large language models. The interdisciplinary group emphasized the need for industry leaders to set ethical standards and take steps like running bias evaluations before deployment and avoiding certain use cases.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Tamkin believes external AI auditing services need to grow alongside the companies building on AI because internal evaluations tend to fall short. He believes participatory methods of evaluation that include community members and other stakeholders have great potential to increase democratic participation in the creation of AI models.
Merve Hickok, who is a research director at an AI ethics and policy center at the University of Michigan, says trying to get companies to put aside or puncture AI hype, regulate themselves, and adopt ethics principles isn’t enough. Protecting human rights means moving past conversations about what’s ethical and into conversations about what’s legal, she says.
Hickok and Hanna of DAIR are both watching the European Union finalize its AI Act this year to see how it treats models that generate text and imagery. Hickok said she’s especially interested in seeing how European lawmakers treat liability for harm involving models created by companies like Google, Microsoft, and OpenAI.
“Some things need to be mandated because we have seen over and over again that if not mandated, these companies continue to break things and continue to push for profit over rights, and profit over communities,” Hickok says.
While policy gets hashed out in Brussels, the stakes remain high. A day after the Bard demo mistake, a drop in Alphabet’s stock price shaved about $100 billion in market cap. “It’s the first time I’ve seen this destruction of wealth because of a large language model error on that scale,” says Hanna. She is not optimistic this will convince the company to slow its rush to launch, however. “My guess is that it’s not really going to be a cautionary tale.” Updated 2-16-2023, 12.15 pm EST: A previous version of this article misspelled Merve Hickok's name.
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Senior Writer X Topics artificial intelligence machine learning algorithms deep learning Google ethics neural networks big data Microsoft ChatGPT Khari Johnson Will Knight Khari Johnson Will Knight Gregory Barber Khari Johnson Peter Guest Steven Levy Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,080 | 2,023 |
"Introducing ChatGPT Plus"
|
"https://openai.com/blog/chatgpt-plus"
|
"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Blog Introducing ChatGPT Plus We’re launching a pilot subscription plan for ChatGPT, a conversational AI that can chat with you, answer follow-up questions, and challenge incorrect assumptions.
Quick links Read about ChatGPT Illustration: Ruby Chen February 1, 2023 Authors OpenAI Product , Announcements The new subscription plan, ChatGPT Plus, will be available for $20/month, and subscribers will receive a number of benefits: General access to ChatGPT, even during peak times Faster response times Priority access to new features and improvements ChatGPT Plus is available to customers in the United States and around the world.
[^footnote-expansion-update] We love our free users and will continue to offer free access to ChatGPT. By offering this subscription pricing, we will be able to help support free access availability to as many people as possible.
Learning from the research preview We launched ChatGPT as a research preview so we could learn more about the system’s strengths and weaknesses and gather user feedback to help us improve upon its limitations. Since then, millions of people have given us feedback, we’ve made several important updates and we’ve seen users find value across a range of professional use-cases, including drafting & editing content, brainstorming ideas, programming help, and learning new topics.
Our plans for the future We plan to refine and expand this offering based on your feedback and needs. We’ll also soon be launching the ( ChatGPT API waitlist ), and we are actively exploring options for lower-cost plans, business plans, and data packs for more availability.
Authors OpenAI View all articles Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top
"
|
2,081 | 2,022 |
"Qualcomm's Snapdragon W5+ Gen 1 Smartwatch Chip Promises Big Battery Gains | WIRED"
|
"https://www.wired.com/story/qualcomm-snapdragon-w5-plus-gen-1-smartwatch-chips"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Julian Chokkattu Gear Qualcomm’s New Smartwatch Chips Promise Big Battery Life Gains Photograph: Qualcomm Save this story Save Save this story Save Tired of recharging your smartwatch every night? Qualcomm has a solution: a more efficient chip built specifically for smartwatches. If it sounds familiar, that's because Qualcomm has been releasing new smartwatch chips every two years with the same premise. But this year's processors—the Snapdragon W5+ Gen 1 and W5 Gen 1—just might be the biggest leaps to date (if not the biggest mouthfuls).
The new chips, which are also being rebranded and ditching the previous “Snapdragon Wear” name, are built on a 4-nanometer process. The last generation of Qualcomm’s chip for wearables was built on a 12-nanometer process. Processors are made up of transistors, and the size of those transistors is measured in nanometers. As you go smaller, you decrease the distance that electrons have to travel inside the chip, so you end up with speedier processing, less heat, and lower power consumption.
Video: Qualcomm Going from a 12-nm process to 4 nanometers is a startlingly big jump. Apple hasn't shared the transistor size on its latest S7 chip powering the Apple Watch Series 7 , but it's likely built on a 7-nm process, potentially making the new W5 chips some of the most efficient wearable processors on the market.
Qualcomm claims the 30 percent reduction in size halves the chip's power consumption while doubling its performance. This means you can expect smartwatches utilizing the chips to be smaller (or the same size with room for beefier batteries). But the more important metric is that Qualcomm says battery life is 50 percent longer when compared to smartwatches using its prior Wear 4100+ chipset, which usually lasted a little more than a day, depending on the watch.
“This is not another chip launch,” says Pankaj Kedia, global head of Smart Wearables at Qualcomm. “This unleashes a new era in wearable computing. We hope to change the dynamic in the industry in wearables and make them indispensable because you can do all the things you ever wanted to.” The second piece of big news is that Qualcomm says it has moved several core functions off the main processor and on to a 22-nm coprocessor. Wearable chips of late come with a primary processor and a coprocessor, the latter of which manages most of the ambient tasks (like the always-on display), allowing the main processor to kick in only when you interact with the device. This strategy reduces overall power consumption.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So One such example is moving Bluetooth (5.3) into the coprocessor, which no longer needs to wake the main processor up when you simply receive a notification alert from your smartphone. Qualcomm says this translates to 57 percent lower power consumption for notifications compared to the last-gen Wear 4100+ chip. Some always-on health features can also rely on the machine learning core in the coprocessor, such as activity recognition, sleep tracking, and fall detection, meaning these functions might not cost you as much battery life as before.
Only the W5+ Gen 1 has a coprocessor; the W5 Gen 1 omits this and is primarily meant to be used in watches for seniors and kids, where you'll want some of the primary functions—like GPS—to be on all the time so you can check whether your loved one made it home on time.
These chips also have a modem that has all the radio-frequency bands necessary to work anywhere in the world. Most smartwatches with an LTE (or 5G) connection today won't connect universally in every country as the modem has limited band support, but that won't be the case here.
The big question is how well the W5+ Gen 1 will work with Google's Wear operating system. Many Wear OS watches use Qualcomm's processors, and those devices that have the Wear 4100 chip have yet to receive the latest version of Google's Wear OS.
There is some good news here. Qualcomm says it's been working with Google to optimize Wear OS for its newest chip family, and Google confirmed that smartwatches with W5+ Gen 1 will only launch with the very latest version of its software.
The first smartwatch to use the W5 Gen 1 will be from the Chinese phone manufacturer Oppo, which will be launching the Oppo Watch 3 in August. Device maker Mobvoi will be releasing a new TicWatch running Google's Wear OS powered by the W5+ Gen 1 later this year. Qualcomm says there are more than 25 other designs in the works utilizing these chips from a variety of different manufacturers.
Jitesh Ubrani, an analyst at the International Data Corporation, says all eyes are on Qualcomm for this wearable chip release. “When the 4100 launched, Qualcomm faced an uphill battle and there were things working against them because Wear OS wasn’t ready. The latest version of Wear OS came out late last year and some vendors held off on adopting the latest processor because they couldn’t get the latest version of the operating system to work on that chip. But Wear OS is ready for prime time now.” Apple, however, still maintains a sizable lead in the smartwatch space. In the first quarter of 2022, it shipped more than 8.5 million units , with Samsung in second at 3.2 million and Google in fifth at 607,000. But competition is ramping up. Not only are new smartwatches on the way with Qualcomm's chips, but Google is set to release a Pixel Watch later this year (notably powered by a Samsung processor) and Samsung is expected to announce a new Wear OS-powered Galaxy Watch in August.
You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Reviews Editor X Topics smartwatches Wearables qualcomm gear chips Wear OS Scott Gilbertson Reece Rogers Simon Hill Simon Hill Brendan Nystedt Scott Gilbertson Julian Chokkattu Reece Rogers WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,082 | 2,023 |
"Best MacBook Accessories (2023): Keyboards, External Monitors, and Sleeves | WIRED"
|
"https://www.wired.com/story/best-macbook-accessories"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Brenda Stolyar Gear Team Gear The Best MacBook Accessories Save this story Save Save this story Save The MacBook is a powerful machine. Whether you're using a MacBook Air for web browsing and sending emails or a MacBook Pro for graphics-intensive projects like video editing and 3D design, Apple's laptops can handle a wide range of activities. But to enhance your experience, I suggest throwing some accessories into the mix.
Regardless of your MacBook of choice or the work you're using it for, a slew of peripherals can pair with your computer, like laptop stands, keyboards, charging bricks, and external displays. We've tested dozens over the past year, and these are the best MacBook accessories to streamline your workflow and unlock your machine's full potential. This is by no means an exhaustive list, as there are an innumerable number of accessories, so we'll always be on the hunt for more to test. Check out our Best Work-From-Home Gear guide for other recommendations.
Updated August 2023: We've added new accessories including the Twelve South Curve Flex, Nuphy Air75 Wireless Mechanical Keyboard, Baggu Puffy Laptop Sleeve, and more.
Charging Adapters Laptop Cases and Sleeves USB Hubs and Docks Keyboards Mice Laptop Stands Desk Mats External Monitors Backpacks Totes Headphones and Earbuds Special offer for Gear readers: Get WIRED for just $5 ($25 off).
This includes unlimited access to WIRED.com, full Gear coverage, and subscriber-only newsletters. Subscriptions help fund the work we do every day.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Charging Adapters MacBooks have become more battery efficient, but you should still carry a spare charger when you head out the door. The default one in the box is bulky and can recharge only one device at a time, so try these alternatives. For more charging picks, check out our Best Work-From-Home Gear and Best Portable Battery Packs guides.
Photograph: Einova $70 at Amazon $70 at Best Buy $70 at Einova This is one of the slimmest and most compact 65-watt chargers we've ever tested. It dished out nearly 60 watts to the 2020 MacBook Pro with M1 and fully recharged it in an hour and a half (from 0 to 100 percent!). It has a soft-touch feel that's a nice upgrade over most plasticky chargers, and the plugs fold in sideways so it maintains a slim profile. It stayed put in a variety of outlets and, since the USB-C port is at the bottom, it never fell off the wall, unlike certain chunky chargers. Best of all, you get a braided, 6-foot, 100-watt cable in the box.
Photograph: Apple $59 at Amazon $59 at Apple $59 at Best Buy I'm constantly on the go, and I have a tendency to forget to pack either my iPhone charger or MacBook charger. Apple's dual-port USB-C power adapter has saved me many late-night trips to Best Buy. It comes with two USB-C ports, which lets me recharge my MacBook Air and iPhone simultaneously. It's pretty compact, so I toss it into my duffle bag or tote. It's rated at 35 watts, so it's powerful enough to recharge an iPad Pro, iPhone 14 Pro Max, and more. It will recharge a MacBook Air just fine, though more power-hungry MacBook Pro models will require something more powerful.
Photograph: Satechi $75 at Amazon $75 at B&H If you have a MacBook Pro, go for Satechi's 108-watt wall charger. It's on the larger side, but it's not as big as the one from Apple. It comes with three USB-C ports, each with the ability to charge at 100 watts if only one device is connected—perfect for the 16-inch MacBook Pro.
However, if you want to charge three gadgets at once, it'll charge them at 45, 30, and 30 watts, respectively, 58, 30, and 20 watts, or 65, 20, and 20 watts, depending on what you're charging. The plug folds up too.
Photograph: Zendure $230 at Amazon $249 at Zendure An outlet might not always be within arm's reach, so it's worth keeping a portable charger handy. You can find a number of great, compact, and cheap portable chargers in our Best Portable Battery Packs guide, but this one from Zendure has a 26,800-mAh capacity (the maximum you can take on a flight) and comes with four USB-C ports—two that can dish out 100 watts and two that output 20 watts each. We had no issues fast-charging MacBooks (you'll likely be able to get close to two full charges out of it), in addition to iPhones and other smartphones. A small OLED display shows the remaining power as a percentage and in watt-hours.
Nomad 65-Watt Dual-Port Charger for $65 : Want two USB-C ports instead of one? This charger isn't as compact or slim as the Sirius above, but you get two ports, each of which can output 65 watts when used alone. Plug two devices in and the top will deliver 45 watts and the bottom can do 20 watts. The plugs fold up, and it looks super sleek.
Satechi 165-Watt GaN Four-Port Charger for $120 : If you have a lot of devices around your desk, this is a handy-dandy charger. It has a little stand to prop it up and a short cord that goes out to an outlet. The four USB-C ports output 100 watts each, but you can get enough power to juice up two MacBook Pro models simultaneously.
Laptop Cases and Sleeves It doesn't take much to scratch or ding the aluminum on a MacBook. It's smart to get a laptop case or sleeve to keep it safe.
Photograph: Incase $55 at Apple $55 at Incase Buy at Amazon This case is available for a few MacBook models, but I've been using it with the 16-inch MacBook Pro (2021). It has precise cutouts for all the ports, rubberized feet that prevent it from sliding, and ventilation to keep the MacBook from overheating. For this specific model, the case comes in clear, pink, and black. It does add a noticeable heft to the 16-inch MacBook Pro—which is already a heavy laptop. You can find these hardshell cases for different MacBook models here.
Photograph: Speck $50 at Speck $50 at Amazon I've always liked Speck's iPhone cases for their durability, and I feel the same about the company's laptop cases. I've been using this one with the 14-inch MacBook Pro and, similar to Incase, the hardshell case has the proper cutouts for ports, along with rubberized feet to keep your machine in place. Both pieces clip in securely. It's available for a wide range of MacBook models. I've carried it in backpacks, duffle bags, and totes, and so far it has managed to protect my machine. However, the scratch-resistant hardshell isn't as resistant as Speck claims. The case has a few scrapes here and there, though it's not too noticeable.
Photograph: Dbrand $26 at DBrand The 15-inch MacBook Air ( 8/10, WIRED Recommends ) in Starlight is stunning, but it's tough to conceal scratches or dings on such a faint color. And while I'd typically opt for a case, I didn't want to add any additional weight or bulk to a slim, lightweight laptop. This skin from dbrand was the perfect solution. It's super thin, easy to install, and is accurately cut to fit the MacBook. It's textured too, which gives it a high-end feel and a sleek look. It's also durable for the most part. I spotted a few dings on the skin itself— which technically means it is doing its job protecting the MacBook—but I quickly buffed them out with a hair dryer.
It also comes in a ton of fun colors and prints, and the option to customize your kit. Dbrand sent me the Deluxe Kit in Off Pink, which comes with the top skin, bottom skin, trackpad skin, palm rest skin, and microfiber cloth. It's more expensive, coming in at $55, but it's a great option if you want to protect every inch of your MacBook. Otherwise, you can opt for the Essential Kit which comes with only the top and bottom skins. They're available for a variety of different MacBook models too.
Photograph: Baggu $32 at Baggu (16-inch) $32 at Baggu (13/14-inch) $32 at Urban Outfitters (16-inch) I've been using the 16-inch version in Sherbert Cherry , and it looks just as cute in person as it does online. The puffiness provides plenty of protection, and the velcro closure is strong enough that I'm never worried the laptop will slide out. I've been using it with the 15-inch MacBook Air, which leaves space for me to squeeze my keyboard and mouse into the sleeve as well. There's also a 13-inch/14-inch version for those who have smaller MacBooks.
Photograph: Harber London $112 at Harber London Prefer a more luxe experience? WIRED reviews editor Julian Chokkattu has had a good experience with Harber London's full-grain leather sleeve. The inside is lined with wool felt to keep your machine scratch-free, and the black or tan leather exudes luxury. It fits a variety of MacBook models, including the 16-inch M2-powered version.
The flap stays shut thanks to magnets, so your MacBook won't easily slip out. You can even charge the laptop while it's in the sleeve.
Hubs and Docks If the limited port selection on your MacBook Air or older MacBook Pro frustrates you, invest in a USB hub or dock. Hubs are affordable dongles that provide extra USB ports, SD card readers, and a headphone jack. Docks are meant to be used at your desk, because they're larger, offer even more ports in greater variety (like Ethernet), and they typically come with their own power supply. Check out our Best USB Hubs and Docks guide for more.
Photograph: Twelve South $60 at Amazon $60 at Twelve South The StayGo Mini from Twelve South is our favorite hub for iPads , but we've had no trouble using it with MacBooks. Plug it in via the USB-C port on your laptop and you'll have access to a USB-A port, a headphone jack, an HDMI output, and another USB-C port for passthrough charging. It's fairly thin and compact, so it won't add too much bulk to your laptop or when you're traveling.
Photograph: Plugable $169 at Amazon Plugable's USB-C Triple Display Docking Station is a great choice, especially for anyone using more than one monitor. It supports up to three displays at once (either HDMI or DisplayPort for each). The dock also packs six USB 3.0 ports (two on the front, four in the back) and a gigabit Ethernet port. Whenever you come back to your workstation with your MacBook, all you have to do is plug it in and you instantly have a multi-monitor setup. With an output of up to 60 watts, you can use the dock to charge your laptop too.
Photograph: Anker $100 at Amazon $100 at Anker Looking to get rid of the power strip at your desk? Look no further than Anker's MagGo 637.
You can use the front MagSafe wireless charger to recharge your iPhone while the back is home to a variety of ports including two USB-C ports, two USB-A ports, and three AC outlets. One of those USB-C ports has an output of 65 watts, which is plenty to charge a MacBook—giving you an all-in-one charging station in a compact orb.
Keyboards If you're frequently at a desk, it's nice, though not necessary, to invest in a better keyboard. Especially if you're looking for a more tactile sensation with a mechanical keyboard. Be sure to check out our Best Keyboards guide for more.
Photograph: Apple $199 at Amazon $199 at Apple $200 at Best Buy Ever since Apple debuted the new Magic Keyboard on its MacBooks in 2021, it's been difficult for me to find a third-party keyboard that feels similar (if not exactly the same). This is remedied with Apple's very-own external keyboard. It's expensive, but it's a nice way to fully replicate the MacBook setup. It comes equipped with a Touch ID button, which you can use to log in, pay for purchases, and download apps, as well as a number pad. It has the same exact same function row keys as M-series MacBooks—complete with playback buttons, a Mission Control key, plus a dedicated Do Not Disturb button.
If you don't need this full-size version, there's also the Magic Keyboard with Touch ID ($149) , and the basic Magic Keyboard ($99).
Photograph: Logitech $150 at Amazon $150 at Logitech $150 at Best Buy We were already fans of Logitech's MX mechanical keyboard line prior to trying the Mac version, but this mimics the experience of your MacBook keyboard a little better. There's a Do Not Disturb key and the ability to program the function row key with Apple's own apps like Final Cut Pro, Keynote, Photos, Safari, and more, using the Logi Options+ app—in addition to other Mac-specific shortcuts. Unlike the original MX mechanical keyboard, you don't have a choice between Clicky, Linear, or Tactile switches. It's only available with Tactile Quiet switches, which are ideal if you typically work around other people as it's quieter. The low-profile keys are still satisfying to type on all day. It's slim and lightweight so it's a nice option to travel with as well.
The Das Keyboard MacTigr for $219: Steep price aside, this keyboard ( 9/10, WIRED Recommends ) has a dedicated Mac layout, Cherry MX Red switches (that don't get too loud), a high-quality all-metal build, and a two-port USB-C hub.
Keychron Q1 Pro Mechanical Keyboard for $199 : The Q1 Pro is WIRED reviews editor Julian Chokkattu's current daily driver. You can use it wired or wirelessly via Bluetooth, and there are several colors and switches to choose from (it's RGB-backlit too). The red switches aren't too loud but are still clicky, and there's a lovely knob for volume control. It's hot-swappable, so you can change the switches whenever you like, and the PBT keycaps haven't shown any wear after five months of rigorous use.
Keychron K3 Pro Ultra-Slim Wireless Mechanical Keyboard for $94: The K3 is another good wireless keyboard but it's slim and compact. It has low-profile keys with a tactile click, RGB lighting, and around four to five days of battery life (that you can charge via the USB-C charging port). You'll also get support for Via if you want additional software customization.
Nuphy Air75 Wireless Mechanical Keyboard for $110 : This is my current daily driver, but it's also my go-to keyboard for traveling because it's so lightweight. (Nuphy also sent me a super useful carrying case to protect it while in my bag.) The low-profile PBT keys are quiet but clicky—you'll have the choice between a variety of low-profile switches that are also hot-swappable—and can be used wired or wirelessly with Bluetooth. It also has a really nice, retro aesthetic.
Mice A good mouse is important for the most comfortable experience. We've got you covered with both an ergonomic option (to keep wrist pain at bay) and an external trackpad if you genuinely enjoy the one on your MacBook. We've got tons more recommendations in our Best Gaming Mice guide.
Photograph: Logitech $70 at Amazon $70 at Logitech Buy at Best Buy This ergonomic wireless mouse from Logitech is great if you spend a lot of time at your desk and suffer from some wrist pain. The Lift, as the name suggests, automatically lifts your palm away from the desk—preventing your nerves from getting pinched. It has excellent battery life too, our unit has gone for more than a year without needing new batteries. You can program the buttons on the mouse to trigger Mac-specific features using Logitech's companion app. For example, I've programmed my mouse to enable Do Not Disturb, Mission Control, the Emojis menu, and Screen capture with a click of a button. You can also customize the buttons to open Apple's apps like Final Cut Pro, Keynote, Photos, Safari, and more.
Photograph: Apple $129 at Apple $140 at Walmart If you're already used to the trackpad on your MacBook, then you can't go wrong with the external Magic Trackpad. It has the same Multi-Touch gestures and Force Touch technology, so there's no learning curve involved. It automatically pairs with your MacBook for seamless connectivity. While the battery should last you about a month, the trackpad comes with a woven USB-C to Lightning cable to charge it.
Laptop Stands Propping your MacBook up on a laptop stand can make sure you're not craning your neck to stare at the screen. We've got plenty more in our Best Laptop Stands guide.
Photograph: ObVus Solutions $75 at Amazon $75 at ObVus Solutions WIRED reviewer Medea Giordano says no matter how many laptop stands she tries, she keeps coming back to this one from ObVus to use with her MacBook. In fact, she's been using it since 2020. It's sturdy, light, and can be raised to different heights and positions—including a standing option (no standing desk required). Although it does take some strength to change the height and angle, you can rest assured it won't collapse while you're using it.
Photograph: Nnewvante $49 at Amazon For anyone who prefers working from a couch or bed, the Nnewvante Laptop Stand is a great option. The height isn't adjustable, but you can raise the base to place it at the best angle for typing on your MacBook. With a stopper built-in, you won't have to worry about things sliding off either. It also has extra space that stays flat so you can place your coffee mug or a drink, and a small drawer for storing little trinkets. You can fold the legs and store the whole thing away when it's not in use.
Flexispot Adjustable Table With Wheels for $120 : WIRED reviews editor Julian Chokkattu has been using this rollable desk in different spots in his apartment. You can adjust the height and because the stand isn't centered, you can pull it under a bed or couch to bring the desktop close to you.
Rain Design mBar Pro+ Foldable Laptop Stand for $58 : Frequently moving from the office and your home? Carry this one around with you. It folds down to a slim enough package and weighs less than a pound. It can raise your MacBook up about 5 inches and rests it at an angle.
Twelve South Curve Flex for $80 : With the ability to flex the stand up to 22 inches high, I can adjust it depending on my setup—whether I'm using an external monitor or working solely off the MacBook. It’s also super compact and portable. I fold it up and throw it in my bag whenever I'm working outside of my apartment. My only complaint is that, while you can adjust the stand's angle up to 45 degrees, it’s too wobbly to type on if you're using the laptop's keyboard.
Heyday Laptop Stand for $20 : I'm a huge fan of the MacBook keyboard, but typing on a flat surface can feel uncomfortable. This stand from Heyday gives my MacBook a slight boost that allows me to type for long periods of time without any wrist pain, whether I'm at my desk or on the couch. I enjoy using it so much that I actually bought two: one for my apartment and one for my parent's house so that I always have one on hand.
Desk Mats A desk mat isn't necessary for your workspace, but it adds a nice touch. It can also make everything look a bit more organized and just plain pretty. They can double as a mousepad for anyone using an external mouse.
Photograph: Grovemade $55 at Grovemade I've been using the medium version ($70) at my desk, which gives me enough room to place my keyboard, mouse, notebook, and coffee mug. It feels nice, looks sleek, and is easy to clean (I've managed to wipe up accidental spills with no trouble). This desk mat comes in a variety of fun colors including dark orange, light green, and magenta. Since it's felt, it slides around slightly—but I've been using it on a glass desk. If you're worried about this, get the Grovemade Matte Desk Pad instead.
It's pricier, but the cork bottom keeps it from moving around.
Photograph: Amazon $40 at Satechi $40 at B&H $40 at Amazon (Out of Stock) This desk mat features one color on each side—that way, you can flip between colors whenever you'd like to change things up. It's made of polyurethane leather, but it looks pretty and my mouse glides smoothly over the top. Like Grovemade's desk mat, it's easy to clean too.
External Monitors Using an external monitor helps me get more work done.
So much so that I now have trouble working without one. It gives your apps more breathing room so nothing feels too cramped, especially on a 13-inch MacBook. Head over to our Best Monitors guide for other picks.
Photograph: Monoprice $280 at Amazon $360 at Monoprice This 4K monitor from Monnoprice offers a high resolution without breaking the bank. With decent support for HDR and punchy colors, it's a satisfying screen to stare at. You can hook it up to your MacBook using the USB-C port on the back instead of relying on the DisplayPort or HDMI. With support for the VESA mounting standard, you don't have to settle for the included stand; mount it to your desk instead and save some space. If you decide to mount it, WIRED reviews editor Julian Chokkattu suggests using longer M3 screws since the mounting holes are recessed. One problem? It's out of stock often.
Photograph: Asus $109 at Amazon $119 at Walmart This Asus 24-inch Full HD monitor is a nice, inexpensive way to add a second screen to your workstation. The 1080p-pixel resolution is sharp, though colors can look slightly oversaturated. You can tweak this in the display's settings. It comes with a tilt-adjustable stand that works well, but if your desk is already too cluttered, it supports the VESA mounting standard so you can put it on an arm mount.
Photograph: Innocn $125 at Amazon Mostly spend time working in coffee shops? A portable monitor is a great companion for a MacBook, making it much easier to multitask and get more done. This one has an OLED panel, so you'll get some lovely deep blacks and vibrant colors. It comes with a cover that doubles as a kickstand plus the essential cables. Just plug it into your machine using the USB-C cable. Just remember that it will drain your MacBook's battery faster, so it's wise to plug it into a power source when you can (the screen will then be able to get brighter too).
Photograph: Mobile Pixels $290 at Amazon $300 at Mobile Pixels This portable display sticks to the back of your MacBook via magnets. If you don't mind permanently leaving four magnets at the corners of your machine, then this is one of the easiest ways to add a second screen to your setup, and it doesn't take any desk space as it hangs off the back of your screen. Just slide out the 13-inch display when you need it and connect the USB-C cable. It adds some bulk and thickness but you can easily remove the display whenever you don't need it.
Backpacks There's honestly no “best” backpack because has different preferences and styles. Browse our Best Laptop Backpacks guide for more recommendations, but these are a few standouts.
Photograph: Tom Bihn $320 at Tom Bihn This Tom Bihn bag is expensive but WIRED senior associate reviews editor Adrienne So says it's her favorite, mainly for its thoughtful design. There's a zippered water bottle pocket in the middle of the backpack (instead of the side), pen pockets in flaps on the side for easy access instead of in the middle, and an exterior made from Bluesign-certified 400-denier ballistic nylon. Each bag also has a lifetime guarantee. The dense fabric and hardware (zippers, buckles, and O-rings) do make it a little heavy though. We recommend going with the 22-liter option.
This bag will only fit a 13-inch MacBook Pro and MacBook Air (2018 and later).
Photograph: Herschel $65 at Amazon $80 at Herschel The Herschel Heritage is a more affordable option and our favorite budget bag. On the inside, you'll find a 15-inch laptop sleeve to fit a 13-inch MacBook or 14-inch MacBook Pro, with plenty of room to pack in more supplies. It's super durable too. WIRED reviewer Medea Giordano says it only started to show signs of wear after several years of use. Our only gripe is the lack of a water bottle compartment.
Rains Backpack Mini for $95: The Rains BackPack Mini is the most stylish pick in our Best Laptop Backpacks guide.
It's attractive, functional, and fits a 13-inch MacBook along with a few other accessories. If you're worried it's too small, we also like the larger 13-liter version for $125.
JanSport Pro Pack System for $150: JanSport's backpacks have always been reliable, and the Pro Pack System is no different. It has a 15-inch laptop plush laptop compartment, along with plenty of pockets to fit additional accessories like notebooks, water bottles, and pens. The front pack is also detachable, which you can use as a cross-body bag.
Harber London Leather City Backpack for $560 : It's expensive, but this all-leather bag is currently WIRED reviews editor Julian Chokkattu's favorite. It can fit up to a 16-inch MacBook in a dedicated sleeve, has space for a spare tablet or a Nintendo Switch, and includes a few pouches in the main compartment and in the front zippered pocket for organization. It's comfy to wear, and he's received plenty of compliments on it.
Totes Not a fan of backpacks? Totes are a more fashionable alternative. They're just as capable of carrying your MacBook and other supplies you may need. We've listed a few of our favorites below, but we've got a ton more in our Best Laptop Totes and Purses guide.
Photograph: Moment $110 at B&H Photo $120 at Moment This tote from Moment is WIRED writer Jaina Grey's favorite.
It has pockets for days (and pockets within pockets) allowing you to store a 16-inch MacBook, multiple water bottles, and cables. Since Moment is a photography brand, the bag comes with padding to protect your gear along with a full-zip closure and weatherproof recycled nylon as well. Since it can hold so much stuff, it also distributes weight evenly to avoid causing shoulder pain.
Photograph: Cuyana $348 at Cuyana (16-inch) $98 at Cuyana (Laptop Sleeve) The Cuyana Tote is currently our favorite purse.
It has a beautiful, timeless design and it's made of durable leather. You'll have the option between a 13-inch or 16-inch size, depending on your MacBook, and multiple colors to pick from. You can also purchase add-ons like an organizational insert that has a pocket for your laptop and water bottle, a flap bag to use as an inner compartment inside the bag or a stand-alone clutch, and an adjustable strap to wear the bag as a cross-body.
L.L. Bean Hunter's Tote Bag for $55: This is our favorite budget tote. It has a rugged build complete with double-stitched seams, a thick polyester shell, beefy handles, and a rubbery plastic lining. WIRED senior editor Michael Calore says he uses it for everything—including grocery store runs, camping trips, beach days, and on flights. It can be useful for work too, but we do recommend purchasing a laptop sleeve or case.
Fjallraven Kånken Totepack for $89 : This tote backpack combination can be worn on your back or your shoulder. It also has a pocket for a 13-inch MacBook, a smaller pocket for a notebook or tablet, and a large main compartment. You'll also have two side pockets for water bottles or a small umbrella.
Baggu Duck Bag for $42 : The Duck Bag by Baggu is not only adorable (we have this one in the floral print) but it's also functional. The adjustable strap allows you to choose whether you want to wear it as a crossbody or a traditional bag, while the top handles are convenient for when you don't want to carry it on your shoulder. It's also extremely roomy—we managed to pack a 15-inch laptop, a change of clothes, and a book without weighing it down.
Headphones and Earbuds Owning the right noise-canceling headphones can be a game-changer for productivity. But with so many out there, it can be tough to narrow down which one to pair with your MacBook. For more options, read our Best Wireless Headphones and Best Wireless Earbuds guides.
Photograph: Apple $477 at Amazon $549 at Apple Apple's AirPods Max ( 8/10, WIRED Recommends ) are expensive but they reign as the absolute best noise-canceling headphones in our book. With excellent sound quality, brilliant noise reduction, stellar build quality, and seamless connectivity, they're hard not to love. When paired with your MacBook, they'll automatically connect to the laptop whenever you take them out of the case. If you own other Apple devices like an iPhone, you can easily switch back and forth between devices without having to manually dig through the Bluetooth menu.
Photograph: Sony $398 at Amazon $400 at Best Buy Sony's WX-1000XM5 headphones ( 9/10, WIRED Recommends ) have a sleeker, more discrete look than the AirPods Max. They're pricier than previous generations, but the latest version offers a more absorbing and energetic sound quality than its predecessors. You'll get excellent noise cancellation and great battery life as well. If you want to save some cash, we still recommend last year's WH-1000XM4 which also offers great noise-cancellation, 30-hour battery life, and a clean sound signature.
Apple AirPods Pro (2nd-generation) for $199 : These are the best earbuds for iPhones, but they're also a great option for MacBooks. The latest generation AirPods Pro ( 9/10, WIRED Recommends ) has improved noise canceling, longer battery life (up to six hours of playtime), and better sound quality.
Beats Fit Pro for $200 : We prefer these ( 9/10, WIRED Recommends ) over the older first-gen AirPods Pro because they have better sound quality, physical buttons on the outside of each bud, longer battery life (six hours, specifically), and support for spatial audio.
Google Pixel Buds A-Series for $100 : The Pixel Buds A-Series ( 8/10, WIRED Recommends ) hold the number one spot in our Best Wireless Earbuds guide.
They pack five hours of listening time with an additional 19 hours within the charging case. They feel stable in your ears and pack better sound quality than Apple's entry-level AirPods.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Product Writer & Reviewer X Topics Shopping buying guides apple macbook Mac Accessories and Peripherals laptops Eric Ravenscraft Jaina Grey Julian Chokkattu Julian Chokkattu Brenda Stolyar Jaina Grey Simon Hill Adrienne So WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,083 | 2,023 |
"22 Best October Prime Day TV Deals (2023) | WIRED"
|
"https://www.wired.com/story/best-amazon-prime-day-tv-deals-october-2023-1"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Laptop Deals Lego Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Parker Hall Gear 22 Best October Prime Day TV Deals (2023) ILLUSTRATION: DANIEL JURMAN Amazon Prime Day October 2023 Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Laptop Deals Lego Deals TV Deals Now Reading Apple Deals Espresso Machine Deals Sex Toy Deals Save this story Save Save this story Save Black Friday is almost synonymous with great deals on TVs. But increasingly Amazon Prime Day TV deals compete with the original American shopping holiday, which has featured bargain televisions going back to the days of big-screen sets that weighed as much as a refrigerator. In July, Prime Day deals on TVs were plentiful, including screaming sales on sets from LG, Samsung, and Vizio. We expect similar sales this Prime Big Deals Days.
Maybe it's the start of the NFL season and fall TV schedule, but some of the current TV deals are actually on par with what we've seen before. Here are the best Prime Day TV deals in October, tracking prices closely on top WIRED-recommended TVs , soundbars , and 4K streaming devices.
The Best TV for Most People: TCL Q6 55-inch QLED 4K Smart TV for $370 ($80 off) A Big-Screen, Affordable Fire TV: Amazon Fire TV 65-inch 4K TV for $600 ($150 off) The Prettiest TV that Won't Ruin Your Interior Decor: Samsung The Frame 55-inch 4K QLED TV for $998 ($500 off) A Great Soundbar With No Ugly Cables: JBL Bar 1300x Soundbar System for $1,300 ($400 off) A Luxurious and Extravagant Soundbar: Sennheiser Ambeo Soundbar $1,700 ($180 off) A Compact Soundbar for Small Spaces: Yamaha Audio SR-C20A Compact Soundbar for $130 ($20 off) We test products year-round and handpicked these deals.
Products that are sold out or no longer discounted as of publishing will be crossed out.
We'll update this guide periodically throughout the sale event.
Updated October 11: We added deals on the LG C3 OLED 65-inch, TCL Q6 55-Inch QLED 4K Smart TV, Nakamichi Shockwafe soundbar, and Polk Audio Signa soundbar.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
The Best Prime Day TV Deals On 55-Inch TVs Here are the best deals we've found on TVs for this October Prime Day.
Samsung The Frame Photograph: Walmart Amazon Anyone who cares about the aesthetics of their space probably doesn't want to stare at their TV screen all the time. That's where Samsung's The Frame comes in: This TV looks like a piece of art when not in use, helping it blend into the background of your well-curated space.
Hisense U8K Photograph: Hisense Amazon The Hisense U8K is among the best-value TVs we've ever seen. It features a mini LED display for ultra-bright colors and great contrast and is super easy to set up and use thanks to the onboard Google interface. Learn more in our full review ( 8/10, WIRED Recommends ).
LG C2 OLED Photograph: LG Amazon This is a solid discount on LG's C2 OLED. This TV has perfect black levels and contrast, a center pedestal mount for easy setup with existing furniture, and a super-fast response time for gamers. It's easily one of the best TVs you can buy right now.
Samsung S95C Photograph: Samsung Amazon This quantum dot-enabled OLED ( 8/10, WIRED Recommends ) is the brightest organic LED display that we've tested. It has shockingly bright colors to go with its great contrast. Small bezels also help create a super immersive picture, making this one of the best TVs for brighter rooms. It also comes with a solar-powered remote, so you'll never have to hunt for AAA batteries.
Amazon Walmart Sony has always had some of the best image processing technology on the market, and that continues with its latest Bravia models. If you are an apartment dweller who wants excellent color accuracy, easy casting thanks to a Google interface, and a quick 120-Hz refresh rate for gaming, this is the high-end TV for you.
Amazon This is our favorite TV to recommend for most people. The mid-tier model ( 7/10, WIRED Recommends ) comes equipped with quantum dot technology and support for every high dynamic range (HDR) format for stunning colors. There's a game mode too, which uses software that can upscale 1080p to 120 frames per second. It's worth noting that, unlike older models, this one comes with Google TV instead of Roku. This is also the lowest price we've tracked, so far.
The Best Prime Day TV Deals On 65-Inch TVs Amazon Fire TV QLED Photograph: Amazon Amazon Amazon's Fire TVs are a solid and affordable way to get a quality screen for very little money. This 65-inch model has Dolby Vision support for good colors, and you can control it using your voice and Alexa.
Amazon Samsung's Neo QLED panels are some of the best and brightest I've ever seen, making them particularly well-suited to brighter viewing spaces. We have not tested this specific model, but there's built-in Alexa to help you set timers and play Spotify when you're not watching a movie. This one features mini-LED backlighting for near-perfect contrast and a center pedestal mount that lets you place it anywhere.
Amazon Best Buy Sony's organic LED displays are some of the prettiest TVs ever. Perfect black levels coupled with gorgeous processing make a phenomenal viewing experience. This one can also do 4K at 120 Hz, which makes it probably the prettiest gaming monitor ever made for those with a PlayStation 5, Xbox Series X, or gaming PC.
Target LG's C3 TV is a great option for gamers. It delivers vivid, high-contrast pictures with loaded detail. When gaming, it has lightning-fast response times (9.2 milliseconds to be exact) and it supports every current-gen console feature across all four of its HDMI sockets—complete with Quick Media Switching that ensures there's no delay when switching frame rate or resolution. Although it produces rather wheezy sound, you can pair it with compatible LG soundbars to help enhance the quality.
The Best Prime Day TV Deals On 75-Inch TVs TCL QM8 Photograph: TCL Amazon Best Buy This large screen comes with quantum dots for bright colors and a center pedestal mount that means it will fit on your existing TV stand. Mini-LED backlighting means great contrast, and it supports a 120-Hz refresh rate at 4K for the latest console and PC games.
Amazon Best Buy Hisense is a purveyor of quality mid-tier TVs, and this U7 is no exception. If you're after a larger screen to enjoy sports, the 144-Hz native refresh rate makes games (both real and virtual) look smooth as silk. I also like that it supports the latest high dynamic range codecs, so you get the brightest, most vibrant colors possible.
TCL Q6.
Photograph: TCL Amazon If you need a super large screen and you don't have a ton of cash lying around, this option from TCL is still solid. It has support for the latest high dynamic range codecs like Dolby Vision for great colors, and the built-in Fire TV interface features essentially any app you want. It's not the brightest or prettiest TV ever, but it is big and has bold color.
Walmart Amazon ($1,998) Samsung's Neo QLED panels are some of the best screens for bright rooms, and this pedestal-mounted 75-incher fits perfectly on most TV stands. This model also features mini-LED backlighting, which means you'll get even better contrast and color highlights, and it has Alexa onboard, which makes it easy to set timers and ask the weather.
Soundbar Deals JBL Bar 1300X.
Photograph: JBL Amazon The JBL Bar 1300X (8/10, WIRED Recommends ) comes with detachable wireless speakers. You can pop off the two speakers on the side of the main soundbar and place them wherever you'd like without having to worry about whether there are power outlets nearby or having to hide cables. It also has some of the best Dolby Atmos immersion we've heard from a soundbar at this price. The only downside is that, without cables, you'll have to charge the speakers between uses.
Amazon This soundbar from Yamaha is our top pick for upgrading your sound system on a budget. It's affordable to tack onto even a very modest TV budget and its 100 watt forward-facing drivers can easily outperform the speakers on most TVs.
Photograph: Roku Amazon We're fans of Roku's smart TV interface, and we obviously love upgrading a TV's audio with a solid soundbar. Which is why the Roku Streambar is our pick for doing both at once.
It's small enough that it's ideal for homes where space is at a premium, and it obviates the need to buy a separate Roku stick on a soundbar that's already pretty inexpensive.
Amazon Zvox might be a lesser-known brand, but it's earned its slot in our favorite soundbars for its unique AccuVoice feature. This tech isolates voices to make them sound clearer, better than any other soundbar we've tested. This is particularly helpful if someone in your home is hard of hearing—or if you're watching a Christopher Nolan movie.
Amazon If you're the type to set up smart speakers and gadgets throughout your home, this soundbar from Yamaha lets you cut down on some of that work. It comes with Amazon Alexa built in, and can control a host of other smart home gadgets. We've actually seen this soundbar's price fluctuate a fair amount recently, sometimes as low as $180, but this is still nearly the cheapest we've ever seen it, so it's a good time to grab one.
Sennheiser Ambeo Soundbar.
Photograph: Amazon Amazon For the luxury-minded, this extravagant soundbar from Sennheiser is our top pick.
It has massive speakers with some of the best audio quality we've seen (or heard, I suppose) of any soundbar we've tested. It's also one of the most expensive we recommend, but its price very rarely dips this low, so if you've been waiting for the perfect sale to grab one, now's the time.
Amazon WIRED reviewer Jaina Grey has spent a few years with this very large dual-subwoofer soundbar system from Japan. The two huge subwoofers deliver earth-shattering bass, while the two side speakers and rear speakers provide more lifelike reproduction than soundbars that bounce sound off the walls for side and rear noises. It also comes with support for all major object-based surround formats (like DTS:X and Dolby Atmos). It's great for large spaces, where the extra bass response helps things feel more cinematic. This is also the lowest price we've tracked, so far.
Amazon This is our favorite soundbar-subwoofer combo in our guide to Best Soundbars.
With a basic, no-frills remote and an HDMI ARC connection to plug into a modern TV, it's easy to set up. You'll also have the choice between different modes, all of which work well. There's Cinema mode which works in a stimulated 3.1.2 Atmos surround, making it fairly room-filling; Music mode, which gives you a more normal stereo image; and Night mode which limits the subwoofer action.
Amazon Best Buy Walmart REI B&H Moment The Home Depot Lowe's Wayfair Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Read next Read next The Best Prime Day Deals on Apple Devices More WIRED Prime Big Deal Days Coverage Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Amazon Kindle Deals Mattress Deals Lego Deals Laptop Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Prime Day Shopping Tips Get a 1-Year Subscription to WIRED for $5 ($25 off) Subscriptions help fund our work.
Writer and Reviewer X Topics Amazon Prime Day Shopping Deals Amazon Prime Day Deals Nena Farrell Louryn Strampe Nena Farrell Matt Jancer Matt Jancer Scott Gilbertson Louryn Strampe Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,084 | 2,023 |
"21 Best October Prime Day Mattress Deals (2023) | WIRED"
|
"https://www.wired.com/story/best-amazon-prime-day-mattress-deals-october-2023-1"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Laptop Deals Lego Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Medea Giordano Gear Team Gear 21 Best October Prime Day Mattress Deals (2023) ILLUSTRATION: DANIEL JURMAN Amazon Prime Day October 2023 Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Now Reading Laptop Deals Lego Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Save this story Save Save this story Save If you need a new mattress, any sales event is a good time to look for one.
Most mattresses are marketed with "discounts" most of the year, but Amazon Prime Day mattress deals are usually significantly better than the discounts on an average Tuesday. We track prices to highlight when a deal is actually a deal. This Amazon Prime Day 2023 —technically called Prime Big Deal Days—offers some solid prices, whether you're buying a bed from Amazon or not. There are also some deals on sheets and other sleep accessories, like weighted blankets.
The prices below are for queen sizes.
We test products year-round and handpicked these deals.
Products that are sold out or no longer discounted as of publishing will be crossed out.
We'll update this guide periodically throughout the sale event.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Updated October 11: We've added a new mattress deal from Brooklyn Bedding, and updated deal pricing in this story.
Mattress Deals Read our Best Mattresses and Best Organic Mattresses guides for more.
Helix Midnight Luxe Hybrid Mattress Photograph: Helix Sleep Helix Enter code DEALDAY25 at checkout to get this deal, which includes two pillows. This matches the best price we've seen our favorite mattress reach. The Midnight Luxe has six layers of foam and individually wrapped inner springs. It's medium-firm and comfortable for almost all sleeping positions. There are other firmness levels within the Luxe collection that we haven't tested yet.
Helix Enter code DEALDAY25 at checkout to get this deal. It also includes two pillows. We've been fans of the above Helix for years, but this one is a new addition to our guide. This isn't the cheapest we've tracked—it dropped to $2,577 during Prime Day in July. As with the Luxe, the Elite collection includes six mattresses, so you can choose your perfect firmness. WIRED reviews editor Martin Cizmar slept on the soft Sunset model. These are a thick 16 inches, and they come in two heavy boxes. One box holds the bottom layer, and the other determines the softness level. They zip into a larger support system to form one, hopefully perfect, bed.
Amazon The Leesa Sapira is our runner-up and while it does reach full price, it's steadily $1,699 on Amazon. This isn't the absolute cheapest we've ever seen, but it's still a solid deal on a mattress that's cool, cozy, and soft, yet firm enough to relieve pressure.
Tuft and Needle Mint Mattress Photograph: Tuft and Needle Tuft & Needle We've seen this mattress for less, dropping to $1,117 during the summer's Prime Day sale. Still, if you need pressure relief, this one delivers. The foam top layer offers support while still being super soft, so you can sink in a little bit without getting stuck.
Amazon Casper ($1,271) Casper's hybrid bed reaches its $1,495 price but is often $1,196 on Amazon. Still, this price is among the best deals we've tracked on a bed from the brand that put bed-in-a-box mattresses on the map. This hybrid is a great neutral option. It strikes a good balance between soft and supportive, with just enough bounce.
Awara This mattress is made from latex foam, organic wool, and individually wrapped springs. It's more affordable than our other organic options, and while it is supportive and bouncy, it's not quite as comfy as some. You may feel the springs a bit more than you're used to. But it's not too hot or too cold, and we didn't feel much motion transfer.
My Green Mattress Kiwi Organic Hybrid Mattress Photograph: My Green Mattress My Green Mattress Enter code DISCOVER at checkout to see this discount. We have seen this get even lower in the past, but the base price has risen since then, and this price is lower than in recent sales. This isn't our top organic mattress pick, but we like the twin size for kids. It's made from certified organic cotton, wool, and latex.
Amazon Despite the price of this mattress rising to over $1,000 on Amazon in September, it's been $999 or less every other month since last year. That makes this one of the best prices we've tracked on the best firm mattress—it was $865 during July's Prime Day.
My Green Mattress Enter code DISCOVER at checkout to apply this discount. If you aren't ready for a whole new mattress, spruce up your existing one with a mattress topper. This organic latex choice from My Green Mattress is our favorite firm topper —it's 2 inches high, has a zipper if you need to remove the organic cotton cover from the pad, and stays in place without needing any straps.
Saatva Zenhaven Natural Latex Mattress Photograph: Saatva Saatva The retail price is technically a whopping $3,295, but it's been steady at $2,945 since we started tracking it. This is one of our favorites, and we think it will last for years, thanks to its quality construction—it's extremely heavy, though, so be prepared. It's made from organic latex protected by an organic wool liner and an organic cotton cover. If you aren't sure whether you want a soft or firm bed, this one is double-sided so you can figure it out once you get it or switch as needed. It has great edge support and sleeps neither hot nor cool.
Bed Sheet and Pillow Deals Read our Best Bed Sheets guide for more options and material information.
Brooklinen Washed Linen Core Sheet Set Photograph: Brooklinen Brooklinen Linen sheets are divisive—people tend to love them or hate them. I thought I would be in the latter camp up until the moment I fell asleep on these. They might feel itchy at first, but they get softer with every wash and I don't sweat even a drop during hot Texas summers. These were cheaper during Labor Day, at $191 for a queen set, so if you can wait you may find them for less.
Brooklinen We like several Brooklinen sheets, and this is our favorite organic set.
They're soft but not overly silky, and you won't sleep too hot in them. They are made from Global Organic Textile Standard (GOTS)-certified organic cotton and are Oeko-Tex certified , which means they're tested for and do not contain any known toxic chemicals. Like the linen set above, we saw the organic cotton sheets dip lower to $183 during Labor Day's sale.
Amazon We already love Bedsure's bamboo rayon sheets for how affordable they are. These sheets are consistently available for $60, so snagging them for a little cheaper is even better. They're silky and cool, especially for the price point.
The Company Store Legends Hotel Velvet Flannel Sheet Set Photograph: The Company Store The Company Store The discount is applied automatically in your cart. matches the price we saw during the Labor Day sale on our favorite flannel sheets, and if you like the two colors currently marked as final sale, you can save even more (though stock on those is more limited).
Buffy Buffy's sheets are made from Tencel Lyocell, which comes from sustainable wood sources, in this case, eucalyptus. My husband and I agree that these are light and airy but still feel warm and cozy—not so much that you wake up sweaty, but enough to feel properly snuggled. On my 13-inch mattress, though, they tend to ride up during the night and need to be readjusted. The brand's Wiggle Pillow , which is basically a supersized body pillow, is also discounted on the Buffy site.
Amazon Big Blanket Co.
This amazing and gigantic blanket will be the focus of its own story in a few weeks' time. WIRED reviewer Louryn Strampe loves it. True to its name, it's massive, measuring 10 feet by 10 feet, so it's really easy to share—even if you're a blanket hog like she is. The price matches what we've seen during other shopping holidays.
Photograph: JCPenney JCPenney Be sure to enter code GIGANTOR at checkout to get the additional $21 off. Even at their typical price of $90, these are among the cheapest sheets we tried, and they're the best sateen ones. They're soft, cool, and silky and almost identically match the feel of Brooklinen's sateen set.
Amazon Spoiler alert: This is our top overall pick in our upcoming guide to the Best Pillows. The Casper Hybrid Pillow uses a design that sandwiches a foam core between layers of memory fiber that make this pillow squishy and foldable while still holding its shape. And best of all, it stays cool all night long. This price matches what we saw during Prime Day in July.
Amazon This is WIRED reviewer Louryn Strampe's absolute favorite pillow. It stays cool all night, the case is washable, and you can customize how much squishable material is inside. Quote from her: “15/10, Louryn recommends.” Weighted Blanket Deals Photograph: Brooklinen Amazon This price is for the terracotta color only. Brooklinen's weighted blanket is 12 pounds but feels sufficiently weighty while I snuggle up at night. It has held up well through many trips to the wash. It's also prettier than some other options, and one side has a nice pattern.
Amazon Gravity ($60) Gravity makes great weighted blankets, including this 15-pound budget version. It's cheaper than most options out there but doesn't lack in quality. You can add a cover too (also discounted) if you don't want to wash the entire thing. If you aren't sure whether weighted blankets are for you, this is a good way to try them without spending too much.
Amazon This price is for the queen-sized 20-pound blanket, but there are several others to choose from. Most weighted blankets have two or three weight options, but Luna has several weights and sizes—from 5, 7, or 10 pounds aimed towards kids all the way up to 20 pounds. If you're buying for a child or just aren't sure you want to go as heavy as other brands offer, consider Luna's crispy cotton blanket. If you don't see the exact one you want on Amazon, you may find it directly from Luna's website.
Amazon Best Buy Walmart REI B&H Moment The Home Depot Lowe's Wayfair Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Read next Read next 26 Best Prime Day Laptop Deals (2023) to Upgrade Your Work Station More WIRED Prime Big Deal Days Coverage Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Amazon Kindle Deals Mattress Deals Lego Deals Laptop Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Prime Day Shopping Tips Get a 1-Year Subscription to WIRED for $5 ($25 off) Subscriptions help fund our work.
Writer and Reviewer X Topics Shopping Deals Amazon Prime Day Amazon Prime Day Deals Jaina Grey Adrienne So Julian Chokkattu Adrienne So Simon Hill Julian Chokkattu Eric Ravenscraft Brenda Stolyar WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,085 | 2,023 |
"27 Best Prime Day Laptop Deals (2023) and Other WFH Gear | WIRED"
|
"https://www.wired.com/story/best-amazon-prime-day-laptop-deals-october-2023-1"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Laptop Deals Lego Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Matt Jancer Gear 27 Best Prime Day Laptop Deals (2023) to Upgrade Your Work Station ILLUSTRATION: DANIEL JURMAN Amazon Prime Day October 2023 Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals (and More Amazon Devices) Mattress Deals Laptop Deals Now Reading Lego Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Save this story Save Save this story Save Past your Prime? Your laptop, that is. Well, it's a good day to upgrade! Today is Amazon's second Prime Day of the year, called Prime Big Deal Days. Here, we've rounded up all the top Prime Day laptop deals we could find, from discounted MacBooks and Windows laptops to PC accessories and peripherals.
Laptop and Monitor Deals Computer Accessory Deals We test products year-round and handpicked these deals.
Products that are sold out or no longer discounted as of publishing will be crossed out.
We'll update this guide periodically throughout the sale event.
The Best MacBook Air is On Sale: Apple MacBook Air 15-Inch Laptop for $1,049 ($250 off) The Thinnest, Lightest Laptop You Can Buy: LG Gram 16 (2022) Laptop for $1,119 ($127 off) One of the Most Powerful Gaming Rigs You Can Buy Is On Sale: Razer Blade 17 Gaming Windows Laptop for $2,300 ($800 off) The Adjustable Desk Everyone Needs: Flexispot Adjustable Table With Wheels for $90 ($30 off) The Gaming Laptop With a Beautiful Screen: Razer Blade 14-Inch Gaming Laptop for $1950 ($350 off) Portable Power to Keep You Going All Day: UGreen 25,000-mAh, 145-Watt Power Bank for $90 ($60 off) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Laptop and Monitor Prime Day Deals If you find your current machine chugging with lots of browser tabs open or just want a new gaming machine, then check out our Best Gaming Laptops , Best Laptops , Best Cheap Laptops , and Best MacBooks guides.
MacBook Air Photograph: Apple Amazon Best Buy The 2023 MacBook Air ( 8/10, WIRED Recommends ) is one of our favorite laptops this year. It has an excellent six-speaker sound system, a 1080p front-facing webcam, and a 10-core variant of the M2 processor the previous year's model came with. It's blazingly fast for most normal work and can even handle some light video editing and other heavier tasks. If you need more RAM, the 16-GB model is on sale for $1,300 ($200 off).
Amazon Our review of the 2022 MacBook Pro M2 ( 7/10, WIRED Review ) notes that we expected more improvements to Apple’s mid-tier laptop. Still, this model has a fan alongside the M2 chipset, meaning it can eke out a little more power. It's also the only MacBook with Apple's Touch Bar now, if that's something you care about.
Amazon The 2020 MacBook Air ( 9/10, WIRED Recommends ) is more than capable for most work tasks. Its M1 chip can handle dozens of browser tabs without issue, and even light image editing doesn’t phase it. The battery life still impresses at a full workday of life, and it’s nearly silent while running. A beautiful display and 256 GB of storage round out an impressive feature list.
2022 LG Gram 16 Photograph: Amazon Amazon This was a favorite deal that went dead on Prime Day in July but is now back (well, it's $3 more now). Weighing in at a tick less than 3 pounds, this is a very light 16-inch laptop. We tested the similar LG Gram SuperSlim ( 7/10, WIRED Recommends ) with the 2.2-GHz Intel Core i7-1360P processor, a step up from the 1260P processor on this model, and found its performance middling. So don't expect a heavy-lifting speed demon from the Gram 16, but do give it a look if you prize portability for lighter tasks, such as browsing and word processing.
Amazon We were fans of the Swift 14 ( 7/10, WIRED Recommends ) when it was released earlier this year, and we’re even bigger fans of the Swift X version. It's the same MacBook competitor, but with a dedicated graphics card that can handle heavier tasks, like gaming and video editing. Acer mucks up the gorgeous, all-metal chassis with too much obnoxious branding, plus the battery life isn’t too good, but at this price, it strikes an impressive balance of beauty and brawn.
Photograph: Microsoft Best Buy The Microsoft Surface Laptop 4 ( 7/10, WIRED Recommends ) is our top Surface pick for most people.
It has an AMD Ryzen 7 processor, 8 GB of RAM, and a 256-GB SSD. It doesn't have any of the flashy hinges or tablet hybrid features of its siblings, but it's a solid all-around laptop, and even comes with a magnetic charger, so you don't fling it across the room if you trip on the power cord.
Best Buy For power users looking for a Microsoft laptop, our pick is the Surface Laptop Studio ( 7/10, WIRED Recommends ). It has a 2-in-1 hinge that lets it function as either a laptop or a tablet. It's got a 14-inch touchscreen, an 11th-generation Intel Core i5 processor, and 16 GB of RAM. Yes, there's a new Laptop Studio, but we ran into some thermal issues , among other things. If you spring for the Surface Slim Pen, there's a spot to magnetically attach it to the front of the laptop.
Amazon Powerful, wafer-thin, and sleek, the Blade 17 is one of the most capable gaming laptops on the market. This Windows machine is the 17-inch-screen bigger brother of the Blade 15 for $1,960 ($240 off).
Its 4K-resolution touchscreen display packs 100 frames per second and a 144-Hz refresh rate (and looks gorgeous doing it), while the 12th-gen Intel 14-Core i9 CPU wields enough power to play virtually any AAA video game.
Monoprice 4k Photograph: Monoprice Monoprice Monoprice's 28-inch CystralPro is a great 4K monitor.
It supports HDR and its colors are suitably vibrant. WIRED reviews editor Julian Chokkattu used it in both a Mac and Windows setup and says it worked great in both. He VESA-mounted it, but do note that the mounting holes are recessed—you can use longer M3 screws to make it work. If you want the highest possible resolution on a monitor without spending a boatload of cash, then this is the best we've tested.
Amazon This matches the good deal we saw on Prime Day for our favorite portable display. It sticks to the back of a laptop screen via magnets, which means you do need to be comfortable with sticking and leaving adhesive magnets on the back of your machine, but you get a second screen that doesn't take up any desk space. Slide it out! Computer Accessory Prime Day Deals For more context, take a look through our guides to the Best Mechanical Keyboards , Best MacBook Accessories , Best Portable Storage Drives , and Best Computer Mice.
Photograph: Amazon Amazon This deal on a great keyboard was better yesterday, but it's still a bargain at this price. Logitech makes some of our favorite keyboards, and the MX board is a great portable option. Its understated design fits in perfectly in an office, and it's low-profile enough to be comfortable typing on all day.
Amazon You may have to click “See All Buying Options” to see this deal. As both a mechanical keyboard enthusiast and a longtime Windows hold out who converted to a Mac, it always burned me up that nearly every keyboard was geared toward Windows users. Well, if you’re a Mac user with a taste for Cherry MX Red switches and could use a two-port USB-C hub, you’re in luck. The veteran keyboard brand offers this all-metal keyboard in a Mac-specific layout.
Amazon There was a slightly better deal on Prime Day, but not by a lot. We love Cherry switches on our mechanical keyboards , but the company also makes keyboards themselves. This low-profile, detachable, and rechargeable keyboard gives you that Cherry typing experience while letting you move around your house.
Razer Kiyo X Photograph: Razer Amazon This is our favorite webcam for most people, and the sale is a match for what we saw on Prime Day in July. Its automatic white balance and color saturation are excellent right out of the box, and the image quality is sharp. It focuses quickly too. You can affix it on top of your laptop or monitor with the included mount. Too bad it doesn't come with a privacy cover.
Amazon We named this compact, two-port charger as our second-favorite charging adapter in our Best MacBook Accessories guide.
Outlets are precious commodities in our electronics-choked homes and never mind about fighting for two outlets in an airport or café. Whether you're packing a laptop, tablet, or smartphone, with this power adapter you can charge any two of them at the same time.
Amazon Working from home offers a lot of freedom, among them the freedom to never make up your mind where you want to settle down and work. Flexispot’s adjustable table with wheels can make breezing between the living room and the kitchen easier than picking up all your accessories and carrying them from place to place. WIRED reviews editor Julian Chokkattu has been wheeling this rollable desk around different spots in his apartment and appreciates its adjustable height, as well as the fact that because the leg isn't centered, you can use it while sitting in bed or on the couch.
Photograph: Amazon Amazon We love this laptop stand for those who prefer working from your bed or couch. The stand's height isn't adjustable, but you have the option to raise the base to position it at the best angle for typing, watching a movie on a tablet, or sketching. There's also extra space for your coffee mug and a small drawer for storing knickknacks.
Amazon Plugable's USB-C Triple Display Docking Station is a great choice, especially for anyone using more than one monitor. It supports up to three displays at once (either HDMI or DisplayPort for each). The dock also packs six USB 3.0 ports (two on the front, four in the back) and a gigabit Ethernet port. Whenever you come back to your workstation with your MacBook, all you have to do is plug it in and you instantly have a multi-monitor setup. With an output of up to 60 watts, you can use the dock to charge your laptop too.
Amazon Samsung's T7 external solid state drives are among the WIRED Gear Team's favorites. Lightning fast and reliable, solid state drives take less babying than hard drives. The T7 Shield comes with a rubberized exterior to protect it from drops and impacts, and it's also IP65 water- and dust-resistant. It comes with a USB-C cable, fits in the palm of your hand, and doesn't require an external power source. Product reviewer Matt Jancer has been using several T7s and T7 Shields for three years and has never had even a hiccup.
Photograph: Satechi Amazon We recommend Satechi's 108-watt wall charger if you own a MacBook Pro. It comes with three USB-C ports, each with the ability to charge at 100 watts if only one device is connected (making it perfect for the 16-inch MacBook Pro). But if you want to charge three gadgets simultaneously, it'll charge them at 45, 30, and 30 watts, respectively, 58, 30, and 20 watts, or 65, 20, and 20 watts, depending on what you're charging. It's also on the larger side, but it's not as big as the one from Apple, and the plug folds up too.
Amazon This Baseus power bank is on the heavy side (it weighs around 1 pound), but it has been a reliable charger in my testing. I like it for laptops, but it'll juice up smaller devices as well. The 20,000-mAh battery is enough to keep your laptop going all day. There is one USB-C PD port rated at 65 watts, and two USB-A QC ports at 30 watts apiece. The LED shows the remaining battery life as a percentage and displays the current and voltage.
Photograph: Ugreen Amazon If you need more power than the brick above, we recommend this UGreen model, which not only packs a little more juice but is much better at fast-charging compatible devices. It's surprisingly compact for the power it provides, although, at 1.1 pounds, it's definitely not ultralight. There are two USB-C ports and one USB-A port. What sets the Ugreen apart is that you can actually draw 145 watts while charging. That works out to one USB-C port at 100W and the other at 45W. Very few other batteries we've tested are capable of that feat.
Amazon We've used this hub with iPads , but it's also great for MacBooks. Plug it in via the USB-C port on your laptop and you'll have access to another USB-C port for passthrough charging, a USB-A port, an HDMI output, and a headphone jack. It's also fairly compact and thin, so it won't add to much bulk to your laptop.
Amazon The humble cable may not be very exciting, but let's face it, you gotta have them. Anker makes some of our favorite cables , and while this one is not in our guide, it's been serving me well for years, which is more than I can say for any other cable I've owned.
SanDisk Extreme Pro Photograph: SanDisk Amazon Claiming the top spot in our Best USB Flash Drives guide , the SanDisk Extreme Pro balances speed, reliability, and price. The sleek aluminum case has a loop for attaching it to a keyring and a slider to push out the USB-A plug. It is fast, performs reliably (we've been using one regularly for two years), and comes with a lifetime warranty.
Amazon This PNY drive appears in our Best USB Flash Drives guide as it combines a compact form, with a sliding USB-A connector, fast read and write speeds, and a loop for a lanyard or keyring. It's a quick and easy way to move or backup files, and we have never seen it this low before.
Amazon This handy charger has enough power to juice up two MacBook Pro models simultaneously. But it's also great if you have a lot of devices around your desk that constantly need to be charged. It has a little stand to prop it up, a short cord that goes out to an outlet, and four USB-C ports that output 100 watts each. It dipped lower to $90 back in July, but this is still a great deal.
All of the Very Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Kindle Deals Lego Deals Mattress Deals Laptops Deals TV Deals Apple Deals Espresso Machine Deals Prime Day Shopping Tips Get a 1-Year Subscription to WIRED for $5 ($25 off) Subscriptions help fund our work.
Amazon Best Buy Walmart REI B&H Moment The Home Depot Lowe's Wayfair Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Read next Read next The Best October Prime Day Lego Deals More WIRED Prime Big Deal Days Coverage Absolute Best Deals Deals Under $50 Best Buy Flash Sale All-Clad Deals Amazon Kindle Deals Mattress Deals Lego Deals Laptop Deals TV Deals Apple Deals Espresso Machine Deals Sex Toy Deals Prime Day Shopping Tips Get a 1-Year Subscription to WIRED for $5 ($25 off) Subscriptions help fund our work.
Writer and Reviewer Topics Deals Shopping Amazon Prime Day Amazon Prime Day Deals Julian Chokkattu Jaina Grey Matt Jancer Adrienne So Michael Calore Matt Jancer Eric Ravenscraft Adrienne So WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,086 | 2,023 |
"The Top New Features in Apple's WatchOS 10: Device Compatibility, Release Date | WIRED"
|
"https://www.wired.com/story/apple-watchos-10-new-features"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear The Top New Features in Apple’s WatchOS 10 Photograph: Apple Save this story Save Save this story Save Last year, Apple introduced the Apple Watch Ultra , a fitness wearable meant to compete with Garmin in the premium outdoor watch category. The Ultra didn’t quite meet the mark —for starters, battery life that barely lasts three days is not enough for the shortest backpacking trip—but Apple’s quest continues. The company announced the next version of WatchOS at WWDC , WatchOS 10, and many of the new features are determinedly creeping into Garmin territory.
That’s in addition to the usual roundup of new and improved software, like easier navigation on the watch face, newly redesigned apps, and new watch faces. We break down the top new features below. Read our guides on iOS 17 and MacOS Sonoma to learn what's new on those platforms, and don’t forget to check out our Best Apple Watch and Best Apple Watch Accessories guides.
Apple's WatchOS 10 update will be available for the Apple Watch Series 4 and newer. However, you'll need to have an iPhone XS or iPhone XR or later running iOS 17 (find out which iPhones support iOS 17 here ). To find what model you have, look at the back of your Apple Watch.
WatchOS 10 is currently in developer beta, but a public beta is expected to land in July. You'll be able to test it out then but expect to run into a few bugs. The betas will continue through to the fall, and the final version will likely launch in September.
Top WatchOS 10 Features We've parsed out some of the top new features arriving in the next version of WatchOS. To read the full list, you can check out Apple's preview page here.
Photograph: Apple We first saw Apple begin to focus on outdoor activities with 2021’s Apple Watch Series 7 , which was more dustproof than ever, and offered improved fall detection and the ability to differentiate between ebiking and regular biking when auto-sensing workouts. Last year, WatchOS 9 introduced running-specific features, like measuring vertical oscillation and stride length.
Now, the watch and the iPhone together are becoming a specialized cycling tool that looks a lot like a dedicated bike computer.
When you download WatchOS 10 and start a cycling workout on the watch, it immediately shows up as a Live Activity on your phone. Tap it, and the Live Activity immediately switches to a full-screen Workout View that displays important information like your heart rate zone and your route. This allows you to mount your phone on your handlebars, make sure you’re in the correct heart rate zone, and not get lost.
The Apple Watch can also automatically connect to Bluetooth-enabled sensors in WatchOS 10, like power meters and cadence sensors, which lets you see metrics like your rotations per minute (RPM) on your watch or Workout View. It can use all this new data to calculate your Functional Threshold Power (FTP), which is a measure of your highest cycling output over the course of an hour. The watch uses this data to calculate your personalized Power Zones as you work out.
Zone training is complicated. Essentially, low-intensity zones let you up your endurance, high-intensity zones up your power, and switching between the two helps you fine-tune your performance.
It’s worth noting that whether you’re running, swimming, or cycling, an FTP assessment has historically been done with a specific format at specific times in your training to prepare for a peak performance event. This is a niche metric. But you will also be able to use all your personalized data to create your own custom workout plan in Apple Fitness+.
Photograph: Apple Last year, the Apple Watch Ultra introduced new navigational features to assist with outdoor adventures, but it had one big flaw—there were no offline maps nor any topographic maps.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft WatchOS 10 includes new topographic maps in the US (iOS 17 also offers offline maps on iPhones, with access to turn-by-turn directions on the watch). The compass app includes a new Elevation view with a 3D view of saved waypoints. Those waypoints also include two automatically generated waypoints: the Last Cellular Connection waypoint for checking messages or making a call, and the Last Emergency Call waypoint from which you can call for emergency assistance.
Photograph: Apple Spending lots of time outside—between 80 to 120 minutes, to be precise—has been linked to a number of positive mental and physical health outcomes for both adults and children. As such, Apple has a new feature called Time in Daylight in WatchOS 10 that uses the ambient light sensor on the Apple Watch to measure how much time you spend outside.
Not only can you view your own data on your iPhone or iPad, but you can also keep track of how much time your children spend outside. If your children have Apple Watches , you can use Health Sharing in Family Setup to make sure they’re spending enough time outside as well.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Finally, the Mindfulness app on the Apple Watch offers different shapes that let you record how you feel in the moment while offering the chance to identify factors that may be contributing to it. Apple says there's access to clinical-grade depression and anxiety assessments to help determine your risk level and if you should see a health care professional.
Video: Apple The Apple Watch is one of the most popular and easily-navigable smartwatches ; however, that isn’t saying much. Flipping through data on a tiny screen is still hard and irritating. In WatchOS 10, things are getting a little better as you can flip through all your widgets on the Smart Stack. Simply turn the digital crown to scroll. If you still can’t find what you’re looking for, Apple's machine learning can help you identify which widget is most relevant at certain times. For example, if you’re traveling, your boarding passes will shuffle to the top.
Apps have also been redesigned to take better advantage of the screen. For example, you can scroll through the World Clock app to find the best time to call your friend overseas. You can also activate the Control Center just by pushing the side button.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Apple There is a whole host of smaller updates to go along with iOS 17 , including NameDrop, to share contact information by bringing your watch close to someone else’s iPhone or Apple Watch; follow-up medication reminders ; and the ability to watch FaceTime messages on your watch.
Finally—and this is the most hotly anticipated feature of every year’s WatchOS update—the new watch faces are Palette, whose colors shift as time moves, plus a Snoopy and Woodstock face. Snoopy and Woodstock will interact with the hands, play with each other, get rained on when you get rained on, and do your workout along with you. Just don’t ask the watch to display Snoopy’s FTP.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Senior Associate Reviews Editor X Topics Fitness Trackers Apple Watch apple how-to Wearables WWDC software fitness Adrienne So Eric Ravenscraft Jaina Grey Brenda Stolyar Simon Hill Reece Rogers Jaina Grey Julian Chokkattu WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,087 | 2,023 |
"Withings Body Comp Scale and Health+ Review: Not Enough for Too Much | WIRED"
|
"https://www.wired.com/review/withings-body-comp-health-plus"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Simon Hill Gear Review: Withings Body Comp Scale and Health+ Subscription Facebook X Email Save Story Photograph: Withings Facebook X Email Save Story $210 at Withings £200 at Withings If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 5/10 Open rating explainer Smart scale pioneer Withings has been making Wi-Fi-connected scales for more than a decade.
As the Body Comp name suggests, Withings’ latest scales provide a breakdown of your body composition, adding vascular age, visceral fat, and nerve health to the usual list of measurements. The Body Comp ($210) scales come with a year’s subscription to Withings’ new Health+ fitness service, adding practical advice to all that data, with programs that include workouts and meal suggestions to cajole you toward healthier habits.
Upgrading from the excellent Withings Body+ ($100), I was eager to see whether the Body Comp and Health+ subscription would justify the extra expense. After spending several weeks with these scales, I’m not convinced the new measurements are essential, and I was underwhelmed by the fledgling subscription fitness service.
Photograph: Withings The Withings Body Comp scales come in black or white and feature a familiar durable design with a glass top, circular metal centerpiece, and a little display to show your stats. Setup is simple, with four AAA batteries included (enough for 15 months of battery life if you weigh yourself once daily).
One of the things I like about the Body Comp is that the scales connect directly to Wi-Fi, so your phone doesn’t have to be nearby to upload your latest measurements. The Health Mate app is good, particularly if you use other Withings devices, like the ScanWatch ( 8/10, WIRED Recommends ) or the Sleep Mat. But you can also export your measurements to Apple Health, Google Fit, Fitbit, Strava, and a few other apps.
1 / 3 The Health Mate app displays charts of your weight over time, enables you to set goals, and offers bits and pieces of advice. We’ll get into what Health+ adds in a moment. While you need to dig into the app to see longer-term trends and get the most value from your Body Comp scales, you can customize the scale display to show you the stats you want.
Hop onto the scales in bare feet (ideally naked) to get accurate measurements. The scales support up to eight users and usually identify you correctly by weight (this works fine for my family, but two people at a similar weight may have to attribute measurements specifically). The sensors in the Body Comp scales can be a little temperamental. Place your feet in the center, standing completely still, to trigger a set of measurements. You have to stay there for several seconds, which can be annoying on a cold morning.
By default, Body Comp shows your weight, weight trend (up or down since the last measurement), fat mass, muscle mass, visceral fat, heart rate, pulse wave velocity, vascular age, and a nerve health score, plus the weather and air quality. It also measures BMI (body mass index), body water percentage, and bone mass, and it can display your steps (if you have a linked tracker). You can customize the display for each user.
Withings Body Comp Smart Scales Rating: 5/10 $210 at Withings £200 at Withings If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Upgrading from the Body+ scales, Body Comp adds vascular age, visceral fat, and nerve health. The Pulse Wave Velocity metric measures the speed at which heartbeat-generated waves move along your arteries, with lower results indicating better heart health. The Body Comp gives you a vascular age range (mine was 44 to 48). Your number should be within that range or higher. If it’s significantly lower, you could be at risk for vascular diseases in later life.
Photograph: Withings Visceral fat is deep inside your body, cushioning your organs, and too much of it is associated with various chronic health conditions. The Body Comp measures this using multi-frequency bioelectrical impedance analysis (BIA), essentially the rate an electrical current travels through your body. Most smart scales use this technique, but few break out your visceral fat. The index is on a scale of 1 to 20, and you want a result between 1 and 5.
The nerve health measurement is taken by stimulating the sweat glands in your feet, and it provides a score out of 100. It can warn of peripheral neuropathy, where conditions like diabetes lead to nerve damage in your extremities. You don’t get a confirmed score here until the Body Comp has 25 days of measurements, but it does offer a predicted score, and anything above 50 is considered normal.
These additional metrics can flag things to ask your doctor about, but they are finicky to measure. When I stepped off the Body Comp scale too quickly or shifted my weight even slightly, the vascular and nerve measurements failed. Mine were all within normal range and have stayed consistent over the past few weeks. These measurements are likely superfluous for most folks.
You get 12 months of Health+ with your Body Comp scale, a subscription that automatically renews and currently costs $9.95 per month. Weirdly, you can only get Health+ with a Body Comp or Body Scan scale at the time of writing.
Body Scan (£400) is Withings premium smart scale, which adds six-lead ECG. It is not currently available in the US, but based on UK pricing, will likely cost around $400 when it does land stateside.
Don’t worry about losing any of the functionality of your smart scale when your Health+ subscription ends. I actually had some trouble activating my Health+ subscription, so I initially tried the scales without it and can confirm that all measurements are independent of the subscription service.
Withings Body Comp Smart Scales Rating: 5/10 $210 at Withings £200 at Withings If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED 1 / 3 What Health+ adds is a new Programs tab in the app where you can choose from a handful of six-week programs. A couple are focused on activity, a couple on nutrition, and one on sleep. The programs aim to help you build healthier habits through daily missions that mix workouts, articles with advice, and meal suggestions. But you can only do one program at a time, and if you quit one to start another, you lose your progress.
Halfway through the High Energy, Big Results program, I am aching and disappointed. All of the workouts, and some of the articles and meal suggestions, come from 8fit , a German subscription workout and meal service that Withings acquired in February 2022.
My first mission was a HIIT (high-intensity interval training) workout. Frustratingly, the Health Mate app does not have a HIIT category, so I had to record it as Other and manually track the session on my ScanWatch. The instructor offered minimal direction and very little in the way of modifications for folks at different levels, and there was no music. This one-size-fits-all approach doesn’t seem to take into account of your age, fitness level, or the measurements from your scales.
Although I’m far from an athlete, I work out regularly (mostly HIIT and yoga), but this session was grueling, leaving me sore for days afterward. Although most of the subsequent workouts haven’t been as tough, they are not suitable for beginners. Your experience will depend on your fitness level, but I found it a jarring switch from the slick production values of Apple Fitness+, with its enormous library of categorized workouts with motivational music, a range of modifications, and integration with the Apple Watch.
Health+ also includes meal suggestions. On some days, you get shopping lists of ingredients and recipes, such as a goat cheese and plum sandwich for lunch, but it’s not a complete eating plan. If you already eat healthy, there isn’t much value here, but some recipes might introduce you to tasty and nutritious foods. The articles offer solid advice, but there’s nothing you couldn’t find using Google.
While you can save your favorite workouts, articles, and recipes, there doesn’t seem to be any way of accessing a library of content to browse. Considering you could pay $80 a year for access to all the 8fit workouts and recipes, I’m struggling to see the value in Health+. It will improve as Withings adds more content, but it feels hastily cobbled together. I can’t help wondering if that’s why Withings has limited its availability; I certainly wouldn’t pay $10 per month for it.
Ultimately, the Body Comp scales themselves are a pleasure to use, but compared to more affordable options the extras are not worth the price. Spend more than $100 on smart scales and you get diminishing returns. The Body+ ($100) is still the sweet spot in Withings’ lineup. As for Health+, it needs a lot more work to compete with the best fitness apps and services.
Withings Body Comp Smart Scales Rating: 5/10 $210 at Withings £200 at Withings If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $210 at Withings Contributor X Topics fitness Exercise health Reviews review Fitness Trackers smart home Shopping Parker Hall Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,088 | 2,022 |
"Shark AI Ultra Review: A Multifunctional Robot Vacuum and Mop | WIRED"
|
"https://www.wired.com/review/shark-ai-ultra-robot-vacuum-and-mop"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear Review: Shark AI Ultra 2-in-1 Robot Vacuum and Mop Facebook X Email Save Story Photograph: Shark Facebook X Email Save Story $450 at Amazon $450 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 8/10 Open rating explainer I’ll admit it: I have residual trepidation from the last time I reviewed a Shark smart vacuum.
The company’s other home appliances may be reasonable dupes for pricier options, but when I received its first-ever smart robot vacuum, I ran it 35 times and it never developed a map. I lived in a 1,000-square-foot house where I could walk from my bed to my daughter’s room in 12 steps.
So my expectations for Shark’s new AI Ultra robot vacuum were very low—especially since I hate most robot mops. I’ve tested many over the years, and few have seemed faster or more effective than simply dragging out my manual Swiffer. But time has passed, both for me and for Shark. Now that I live in a larger house with different types of flooring, the Shark AI Ultra has become one of my most reliable cleaning companions. It may not scrub as hard as Ecovacs’ enormous and expensive Deebot X1 Omni , but it's surprisingly effective at half the price.
If you’re familiar with robot vacuums , you know that they tend to be pretty finicky about placement. That goes double for a robot vacuum that doubles as a mop. If you want to be able to start the vacuum from your phone, without carrying it into the kitchen, you have to … well, find a place to put it in the kitchen. That way, the robot doesn’t have to travel, dripping, across your carpet.
Most robot vacuums I’ve tried can be safely stowed in discreet locations (I’ve even parked a few under the couch), but oftentimes mopping vacs take up more space. Chances are you'll have to move the garbage bin and the dog food bin in the kitchen, as I did, to make room for the Shark AI Ultra. Accessories are also an issue. Some vacuums, like the iRobot Roomba j7+ , have storage bins inside the docking station, but others like the Shark require you to empty out a shelf in your closet.
When you switch between mopping and vacuuming, you also have to swap out the dustbin, so I needed to find a convenient place where I wouldn’t forget about that too. It comes with an effective and pretty innocuous-smelling cleaning solution. (If you don’t like it, you can use plain water.) The Shark dock itself is fairly unobtrusive. I measured it at 14 inches high and 19 inches deep, which isn't too big compared to other auto-empty docking stations. After I plugged it in and it charged, it mapped my (now larger) house accurately after one 20-minute mapping run—a huge improvement over my first Shark robot vacuum.
Everyone uses their robot vacuum and mop differently. Some people want to pick up their whole house after the kids are in bed, set up a routine, and wake up to a sparkling new house, like a bunch of elves came through in the night.
I used to clean like that. But now that my husband is traveling for work and I am single-parenting two grade schoolers, a dog, and a grouchy hamster during the week, I take my bits and pieces of cleanliness when I can get it. Shark’s SharkClean app ( iOS , Android ) is remarkably simple and easy to use. Once I mapped my house, I designated separate rooms and added a no-go zone around the fireplace, where vacuums tend to fall in.
When my kids are in school, I pick up the kitchen, fill the mopping bin, and lock it into the bottom of the robot vacuum. I particularly appreciate that the app offers a time estimate (that is reasonably accurate) for how long the cleaning will take. I was also surprised by how effective the mopping was. It’s very hard for a robot vacuum to calibrate mopping correctly. If it releases too little fluid, it’s not effective. Too much and it leaves your floor a dripping, soggy mess.
The Shark’s bin releases just enough cleaning fluid, and most importantly, it wiggles as it mops to scrub the floor. If you select UltraMop in the app to spot-clean, you can see the squiggly pattern in the floor as it mops. The microfiber cleaning pad, which was easy to slide on and off the bin, showed a lot of that dirt.
Shark AI Ultra 2-in-1 Robot Vacuum and Mop Rating: 8/10 $450 at Amazon $450 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Speaking of the cleaning pad, this is one of my major pain points with robot mops. It’s certainly more sustainable to use a reusable cleaning pad than it is to throw out multiple wipes with each Swiffering. Shark includes two you can swap out. When I wasn’t able to throw them into the washing machine, they did clean remarkably well when I washed them by hand in the sink with some dish soap. However, washing mops by hand is gross. I found myself thinking fondly back on the Ecovac Deebot X1 Omni's little swishy pool with self-cleaning mops.
That said, the 35-minute mopping time was accurate, and it picks up a lot of dirt. The mapping was incredibly precise—after each mopping, I checked the edge of the carpet, and it was dry.
After my kids are in bed, I swap out the bin and set the Shark to vacuum their playroom. It navigates an additional several hundred feet, for a total of 800 square feet of cleaning per day. In two months of runs through a veritable Indiana Jones-type booby-trapped temple of robot doom, it only got stuck once, on … well, some unidentifiable plastic figurine that got stuck in the roller.
Otherwise, it adeptly navigated the space and picked up all the loose dog hair tumbleweeds. I also deliberately left millions of minute pieces of cut paper under the counter after a craft project, and it picked those up as well while mopping (the mopping bin also has a rudimentary dust bin).
Just about the only quibble I have is that the self-emptying function doesn’t always work reliably—I do end up checking it after every run, just to make sure it hasn’t gotten clogged. Also, unlike the iRobot vacuums, the Shark doesn't have a self-empty automatic bin sensor. That means that it doesn't know when its bin is full and will just keep going. This may be a dealbreaker for some. However, it does place itself back on the dock accurately, you don't need replacement bin bags, and the self-emptying does work, unlike some other robot vacuums I could mention (I’m looking at you, Yeedi).
The Shark’s most attractive feature is its price. My favorite robot vacuum is still the insanely reliable and accurate Roborock Q5+ ( 9/10, WIRED Recommends ), but with a self-emptying bin, it costs $600. The Shark AI Ultra has two functions, not one, and is roughly the same price.
You can also buy this robot vacuum without the self-emptying bin for $430.
If you clean your house as I do, room by room, and don’t find using your hands to empty bins to be completely disgusting (as I do too, sadly), then it's a fine way to save some cash. For several months, I found the Shark AI Ultra to be a reliable cleaning companion. You can’t ask for much more than that.
Shark AI Ultra 2-in-1 Robot Vacuum and Mop Rating: 8/10 $450 at Amazon $450 at Target If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $450 at Amazon $450 at Target Senior Associate Reviews Editor X Topics Shopping review robot vacuum household smart home cleaning Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,089 | 2,023 |
"Samsung Bespoke Jet AI Review: Stylish Smarts, Off the Mark | WIRED"
|
"https://www.wired.com/review/samsung-bespoke-jet-ai"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear Review: Samsung Bespoke Jet AI Facebook X Email Save Story Photograph: Samsung Facebook X Email Save Story $1,000 at Amazon $1,000 at Samsung If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 7/10 Open rating explainer Samsung launched its Bespoke series, a home appliance line for the Wi-Fi-enabled mid-century modern home , a few years ago. Everything has a bunch of “AI-optimized” smarts and looks like it belongs on the set of A Single Man.
As of today, Bespoke includes a smart slide-in induction range, dishwasher, fridge, clothes washer and dryer, and the Jet vacuums—a robot vacuum and this beautiful cordless stick vac.
When I tried the Jet Bot AI+ robot vacuum , it was clear that the appliance had been designed by someone who had never seen a robot vacuum before. Most robot vacuums look similar for very practical reasons, but the JetBot was much taller and bigger, and it boasted remarkable navigation capabilities while leaving a dirty 4-inch border around everything in my house.
The stick vacuum has been designed by someone born on planet Earth. It has a lot of useful accessories, a beautiful and easy-to-use docking station, plenty of “AI-calibrated” suction, and even a connection to the Samsung SmartThings app. I’m just not sure you need AI to do these things.
If you’re considering whether to get a Bespoke Jet or a Dyson V15 , the first questions you need to ask are whether floor space is scarce and whether you have a conveniently placed outlet. My family’s first house had a hall closet where we could discreetly hang the V15. Later, we moved to a much bigger house where floor space is no longer a premium.
I love the Bespoke Jet’s stylish, free-standing, and self-emptying docking station, which has a circular footprint that’s about a foot across. The vacuum and station come in a chic satin black. The set has a place of pride in my living room and is basically the Sword in the Stone.
As Samsung’s marketing materials say, it’s designed to be seen.
The vacuum also comes with three attachments and seven additional docking station bags, although the accessory I really wanted was the spray spinning sweeper ($150) , which is sold separately. The marketing materials note that the vacuum comes with an accessory cradle, but this wasn’t in the box with my tester unit.
You can connect it to the Samsung SmartThings app ( Android , iOS ) by scanning the QR code, but although pairing is quick and painless, there isn’t much of a reason to use the app. It lets you check the charge level, when the dustbin was last emptied, and the suction power, but you can also do this by checking the display on the vacuum itself.
It has an impressive 280 air watts of suction, which is more than even the Dyson Gen5detect ($950) ; my current Dyson V15 has only 230. At a little more than 6 pounds, it’s almost 3 pounds lighter than the Gen5detect. However, its build quality doesn’t hold up to the Dyson V15. It’s more plasticky, and the pieces aren’t engineered to fit together as precisely and solidly as a Dyson. It’s a letdown on a premium vacuum marketed as being as slick and beautiful as a tube of Chanel lipstick.
Photograph: Samsung Newer Dyson vacuums, like the Gen5detect , have HEPA-grade filtration and use light to illuminate dust particles and feed information back to the vacuum’s computer. Samsung notes that the Bespoke Jet AI uses a combination of pressure and air sensors to calibrate the level of suction; but you can also see a little light illuminating all the schmutz as you push the vacuum around.
Samsung Bespoke Jet Rating: 7/10 $1,000 at Amazon $1,000 at Samsung If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The company claims that the vacuum has a battery life of up to 100 minutes, but I’ve seen nowhere near that. When the vacuum is on our medium-pile (half-inch long) carpets and on the AI setting, I normally get about 29 minutes. Transferring to hardwood or tile floors extends the battery life to about 60 minutes, but even on minimum suction, I only get a maximum of about an hour and 14 minutes.
Despite this, the Jet is extremely effective. I have a 6-year-old and an 8-year-old. They leave a trail of grime behind them like cute, tremendously active snails. When they eat muffins, there are tons of crumbs and sugar sprinkles under the kitchen table. When they get home from camp, they shed piles of dirt off their legs; shake sand out of their shoes; and sprinkle who knows what out of their backpacks. The Bespoke Jet handled it all quite nicely, even sucking up palm-sized hairballs from my dog in the laundry room. My 6-year-old spilled an entire salt shaker at the dinner table, and the Bespoke Jet picked it all up.
I also appreciate the automatic emptying feature. With a Dyson, you have to click off the bottom handle and empty the bin into the garbage bag. The Bespoke Jet does it automatically when you click it back into the docking station. This process is around 75 decibels and continues for several cycles, which is more annoying than you might think, but it empties the bin much more effectively than I or gravity do with the Dyson. The bin is also removable and washable.
The crevice tools are usable and function well. The vacuum’s lighter weight makes it great for sucking up all the spiderwebs in the far corner of my house and vacuuming hard-to-reach sections, like the stairs. The side effect of having so much suction is that it’s hard to push on carpets, and I usually end up doing a two-handed push-pull.
There are a few compelling reasons to pick the Bespoke Jet over a Dyson.
If storage space isn’t an issue, the freestanding dock, accessories, and extra battery are all beautiful and convenient. If you bought the mopping attachment, it would be even more useful. Automatic emptying is a big bonus, and the LED display is easy to see and use. If you have other appliances from the Bespoke line, you can line them all up neatly in your home and in the app and gaze at them fondly.
The major reason the Bespoke Jet is not a practical purchase is purely philosophical—you don’t really need AI to detect so-called invisible dirt particles. Companies like iRobot and Dyson have been doing this level of cleaning for years—and just as effectively. The Dyson is also a more practical size, with a slightly bigger dust bin (at 0.75 liters to the Bespoke Jet’s 0.5), HEPA-grade filtration, and noticeably better build quality. If you’re spending this much on a vacuum, it should be pretty darn close to perfect, and the Bespoke Jet isn’t quite there.
Updated August 21, 2023: A previous version of this story noted that the Bespoke Jet AI comes in three colors and that it comes with an extra battery. It only comes in satin black and does not have an extra battery. The story has been updated to reflect these changes.
Samsung Bespoke Jet Rating: 7/10 $1,000 at Amazon $1,000 at Samsung If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $1,000 at Amazon $1,000 at Samsung Senior Associate Reviews Editor X Topics Shopping review vacuum smart home Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,090 | 2,023 |
"Sony WF-1000XM5 Review: Smaller, Lighter, but Not Better | WIRED"
|
"https://www.wired.com/review/review-sony-wf-1000xm5-true-wireless-earbuds"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Simon Lucas Gear Review: Sony WF-1000XM5 Facebook X Email Save Story Photograph: Sony Facebook X Email Save Story $298 at Amazon $300 at Best Buy $298 at Walmart £259 at Sony (UK) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 7/10 Open rating explainer “It is not best that we should all think alike,” according to Mark Twain—and far be it from me to contradict him. But while he obviously had his mind on higher things when he said it, there’s something to be said for unanimity of opinion when it comes to, for instance, true wireless in-ear headphones.
Take Sony’s WF-1000XM4 from 2021. Critical opinion was unanimous: They were high on the list of the best true wireless earbuds you could buy, period. And when critical opinion aligns like that, it takes an awful lot of sweat out of the decisionmaking process for consumers.
It’s that unanimity of opinion that makes the launch of Sony’s WF-1000XM5 so much more interesting than that of any other true wireless in-ear headphones. A new pair of true wireless earbuds is launched every day (or, at least, it very much seems like it), but the chance to find out whether the replacement for the GOAT continues the dynasty doesn’t come around that often. About once every two years, in fact.
Initial impressions are very good indeed. There’s not much in life that people are prepared to pay more for in order to get less of, but the WF-1000XM5 are much smaller and lighter than the earbuds they replace. The WF-1000XM4, for all their many virtues, were on the chunky side. But the WF-1000XM5 tip the scales at just 5.5 grams per earbud and 37 grams or so for their charging case. So already we’re ahead, at least where discretion and comfort are concerned—and the fact that Sony has been good enough to include four sizes of eartip in the packaging (which is, incidentally, made from a combination of bamboo, sugarcane fibers, and post-consumer recycled paper that Sony calls “original blended material”) only increases your chances of finding the WF-1000XM5 comfortable in situ.
Photograph: Sony The eco-credentials of the WF-1000XM5 extend beyond their packaging. The charging case and earbuds themselves are mostly made from a material composed almost entirely of recycled plastic. For the charging case it’s very slightly textured, while for the earbuds it’s so smooth it makes getting them out of the case trickier than it should be.
Despite a form factor that’s around 25 percent smaller and 20 percent lighter than the model they replace, the WF-1000XM5 manage to hold almost exactly the same amount of battery power. With active noise cancellation on, the earbuds are good for around eight hours; turn ANC off and that figure rises to around 12 hours. There are two additional full charges in the case, too, so anywhere between 24 and 36 hours of listening is available before you’ll need to visit the mains.
Adequate , then, is the word best applied to battery life.
Despite the reduction in physical size, though, Sony has found space to squeeze in some of its newest technologies. The bulk of the business is taken care of by the new “integrated processor v2.” Along with amplification and 24-bit audio processing, it also works in conjunction with the “HD noise canceling processor QN2e” to deliver what Sony is boldly claiming to be “the best noise-canceling performance on the market.” Sony WF-1000XM5 Rating: 7/10 $298 at Amazon $300 at Best Buy $298 at Walmart £259 at Sony (UK) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Wireless connectivity is via Bluetooth 5.3, with SBC, AAC, and high-resolution LDAC codec compatibility and multi-point connectivity. Lower-resolution content can be breathed on by Sony’s DSEE Extreme algorithm, which claims to be able to upscale lossy audio files in real time.
The WF-1000XM5 are compatible with Sony’s Dolby Atmos—bothering “360 reality audio,” and features head-tracking technology that adjusts the sound-field to follow your head movement. Augmented reality games can benefit from this same technology, too.
Three mics per earbud, including a pair of feed-forward mics, take care of telephony, voice-assistant interaction, and noise cancellation.
Call quality is augmented by bone-conduction sensors, a specific wind-noise reduction structure, and some neural-network-based AI algorithms also trying to keep wind-noise suppressed.
No matter if you’re listening to music or podcasts, playing games, or making or receiving calls, though, sound is delivered by a pair of newly designed drive units. At 8.4 mm each, these new drivers are a fair bit bigger than the 6-mm items the WF-1000XM4 had to make do with—and the name Dynamic Driver X also makes them seem pretty mysterious.
As far as getting all that hardware to do what you want, Sony has—as is the company’s standard operating practice—gone to town. The WF-1000XM5 have more features, more opportunity for customization, and more functionality than any of us have the patience to discuss in full. So by way of a taster, here are some of the highlights: Control is available via a large, responsive capacitive touch-surface on each earbud. All the most common operations can be performed this way, and the exemplary Sony Headphones control app allows a degree of customization of their functions, too. (And though the app itself was in beta during the course of this test, it was an absolute paradigm of stability and functionality.) It allows finessing of the “ambient sound” side of active noise cancellation, including the ability to concentrate fully on voices using the “voice passthrough” setting. There’s also “speak to chat,” which pauses playback when your voice is detected by the earbuds. It allows you to prioritize either Bluetooth wireless connection stability or sound quality.
It features a five-band EQ with nine presets and the ability to save a couple of your own. It has an on/off setting for the aforementioned DSEE Extreme (frankly, the difference between the two settings is nothing as pronounced as Sony would have you believe), and it is keen to receive a photograph of each of your ears in order to optimize its 360 Reality Audio function.
It allows you to answer calls with a nod of your head (or, even more importantly, reject them with a shake). And there’s activation for Spotify Tap and for Endel (the latter plays a series of sounds intended to help you relax or drift off to sleep). It lets you switch low latency on or off—having it on is very handy when watching videos or gaming.
There’s more, and will be more still when the app is finalized, but the broad point is already made: The Sony WF-1000XM5 have functionality the like of which no nominal rival can compete with. Oh, and there’s utterly reliable compatibility with your source player’s native voice assistant, too.
Photograph: Sony And where the most important aspect of performance—the reproduction of music—is concerned, the WF-1000XM5 need no apologies made for them. They may not have the sort of sound that will satisfy the most committed bass-heads, but listeners who value momentum, accuracy, and straightforward fidelity will find very little to take issue with here.
Sony WF-1000XM5 Rating: 7/10 $298 at Amazon $300 at Best Buy $298 at Walmart £259 at Sony (UK) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Play a big, high-resolution file of “What Was I Made For?” by Billie Eilish from the Barbie soundtrack, and the Sony almost immediately reveal themselves as a balanced, insightful listen with outstanding soundstaging ability and excellent frequency integration. Tonal consistency is unquestionable, and timing is deeply impressive, too.
Treble sounds on the open, organized soundstage stay the right side of “edgy,” with plenty of substance to balance their brightness. In the midrange, sky-high detail levels mean Eilish’s vocal is absolutely loaded with character as well as information regarding her tone, timbre, and technique.
The WF-1000XM5 do great work with low-level dynamics, making the tonal and harmonic variations (especially apparent in a voice or an instrument when a recording is as spare and quiet as this one) completely obvious—and giving them proper context at the same time.
Switch to the more forthright charms of De La Soul’s “Eye Know” and the bottom of the frequency range does its thing with admirable pace and momentum. Rhythm expression is very good, low-end extension is considerable, and the same sort of harmonic variation apparent higher up the frequency range is evident, too.
There’s not a huge amount of punch or substance to bass sounds, but their rapidity and sky-high detail levels make up for that somewhat. The EQ settings in the control app allow you to ramp up the bass, of course, but that doesn’t make it any more substantial or significantly punchier—it just makes it louder, which spoils the overall tonal balance of the presentation.
The WF-1000XM5 are similarly circumspect where the broader dynamics of volume and “quiet/LOUD” potency are concerned, too. The Sony don’t seem able to breathe deeply enough to give these variations their fullest expression, and consequently recordings can lack a little intensity.
It’s the more peripheral aspects of performance that are of greater concern, though. For instance, the idea that the WF-1000XM5 represent “the best noise-canceling performance on the market” is fanciful at best.
The Sony do a decent job at reducing external interference while maintaining their sonic stance at the same time, but there are any number of alternative designs that do it better. The Bose QuietComfort Earbuds II spring immediately to mind—their noise cancellation is of an entirely different order.
And for all the talk about the lengths Sony has gone to in order to maximize call quality here, the WF-1000XM5 are nothing special where telephony is concerned. No matter if you’re using them to make or receive a call, it’s possible to hear the noise-reduction hardware sticking its oar in. It alters the sound of voices arbitrarily, and intelligibility is not all it might be. And it’s not as if the reduction in wind noise is spectacular as it’s doing so, either.
So I go out with more questions than when I came in. Is the Sony WF-1000XM5 a poor product? Not on your life, no: Sound quality is good at worst, and great at best, while extended functionality is class-leading and comfort is improved over the product it replaces.
Is the Sony WF-1000XM5 the same kind of no-brainer recommendation as the outgoing WF-1000XM4? No, it isn’t: It’s more expensive, the level of competition it faces has improved, and it’s not the sort of consummate all-rounder the older product was.
Will the WF-1000XM5 appear near the top of our Best Wireless Earbuds list? Well, that’s going to be the subject of quite a lot of debate, I imagine—because it wouldn’t do for us all to think alike around here, would it? Sony WF-1000XM5 Rating: 7/10 $298 at Amazon $300 at Best Buy $298 at Walmart £259 at Sony (UK) If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $298 at Amazon $300 at Best Buy $298 at Walmart Contributor Topics Sony Headphones audio Wireless noise-canceling Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,091 | 2,023 |
"10 Best Travel Coffee Mugs (2023): Insulated, Steel, Thermal | WIRED"
|
"https://www.wired.com/gallery/best-travel-mugs"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Matt Jancer Adrienne So Gear The Best Travel Mugs to Keep Drinks Hot or Cold Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Best Overall $35 at Miir Runner-Up $33 at Amazon A Close Third $28 at Amazon Space Saver $30 at Yeti If it isn't whiskey, you shouldn't be drinking it at room temperature. Even river water on a warm day of hiking is refreshingly cooler than the ambient air temperature. Lukewarm coffee is a great way to get your whole day off to rough start, and nobody daydreams about relaxing by the pool with a tepid glass of 70-degree water by their side.
Lucky for you, everybody seems to be selling a vacuum-insulated bottle, mug, or tumbler these days. Most of them are perfectly capable, too. It's rare to run across one that's a total failure at its one job, but it's also rare to find one that truly stands out. Here are the best travel mugs that impressed us, and some of the rest.
Updated August 2023: We've added the Hydro Flask Cooler Can, Miir Camp Cup, Toaks Double-Wall Titanium Cup, and Hydro Flask Mug. We've also updated pricing and availability throughout.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com. Subscriptions help fund the work we do every day.
Photograph: Miir Best Overall Miir Flip Traveler (16 Ounce) Miir makes one of my favorite stainless-steel water bottles , and its insulated travel tumbler doesn’t disappoint. It has a tough powder coating with a flip-top lid that is absolutely leak-proof. I couldn’t get one drop of liquid to escape, no matter what I did to this tumbler. It’s narrow enough to fit any cupholder or backpack bottle holder, and it feels tough enough to survive years of abuse.
$35 at Miir $39 at Amazon Photograph: Backcountry Runner-Up Hydro Flask Coffee Mug With Flex Sip Lid (16 Ounce) Hydro Flask’s powder coating is one of the toughest I have come across on a beverage container. Whenever I can foresee some serious abuse happening to a coffee mug on a trip, I take a Hydro Flask. I’ve yet to dent or scratch one through routine carelessness. Without a cupholder in my car, my Hydro Flask lived on the floorboards, rolling and crashing around with every maneuver, and it still held up. The pebbled texture is grippy, so you won’t fumble it like a stick of hot butter if your hands get wet or greasy.
$33 at Amazon $33 at REI $33 at Dick's Sporting Goods Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Amazon A Close Third Klean Kanteen TKWide Insulated Mug (16 Ounce) Narrow openings are fine for water, in my opinion, but for hot beverages, I like having a wider gap so I can take a big gulp. You’re less likely to burn your mouth on hot drinks when you can slurp, too. The TKWide’s Cafe Cap is like drinking from a regular to-go coffee cup, rather than a water bottle.
All the colors have matte powder-coated finishes, which are more scratch-resistant than the brand’s smooth powder-coated finishes. That said, I haven’t found them to be as tough as Hydro Flask’s powder coating, and the uncoated stainless-steel ring on the bottom of the mug is pretty easy to scuff up.
$28 at Amazon $33 at Target Photograph: Yeti Space Saver Yeti Rambler Stackable Pints (16 Ounce) These are my new favorite everyday vacuum pints. They come in a set of two, and they stack for easy storage in your cupboard. The matte exterior is pleasant to hold, and the clear, sealed lid lets you see how much fluid is in the cup before you pour it all down the front of your shirt. (You can also swap it out for a straw lid or Yeti’s lid with a sliding magnetic closure.) It keeps coffee hot for the several hours I need to drink it before re-upping. Most importantly, it’s dishwasher-friendly, so you’re not constantly soaping up at the sink.
$30 at Yeti $30 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: KeepCup A Classy Paper Cup Replacement KeepCup Brew Cork (12 Ounce) The Brew Cork is greater than the sum of its parts. Its double-walled, insulated version is meant to replicate and replace paper coffee shop cups. It’s fun to drink out of. Many other tumblers’ lid openings are blocky or mash your nose, but the KeepCup is ergonomically on point. It’s not the best for road trips, nor the best for keeping a ton of coffee hot for hours, but I highly recommend the LongPlay if all you want is a reusable cup to cut down on single-use waste and keep your drink warm long enough for you to actually drink it. That said, the lid is a bit dribbly. While the interior and lip are glass—no metallic off-tastes here—the exterior shell below the rubber grip is plastic.
$32 at Amazon $32 at KeepCup Photograph: Miir An Eco-Friendly Option Miir Climate+ It doesn't fit a typical car’s cupholder, but if you like an insulated mug that resembles an actual cup more than a pack of Lifesavers standing on end, the Climate+ is for you. It has the solid build quality and tough powder-coated finish we’ve come to expect from Miir, in a package that has less of an impact on the environment. Miir says that the Climate+ uses no new plastic (the lid is 100 percent recycled and recyclable), and its insulation uses 25 percent less stainless steel than traditional insulated mugs. It’s also completely BPA-free.
$25 at Amazon $25 at Miir Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Ello Camp Classic Ello Campy Travel Mug (16 Ounce) The blue enameled steel camp cup is a piece of Americana that hearkens back to black-and-red flannel shirts and war-surplus Army tents. Like all the tumblers on this list, it’s vacuum-insulated to keep hot drinks hot and cold ones cold. Its screw-on plastic lid, with a sliding lever for sipping, is leak-proof enough. If you leave it upside down for more than a few seconds or shake it, it’ll drip, but we couldn’t get it to leak by knocking it onto its side.
The handle is plastic to avoid conducting heat from hot contents, and the inner part of the handle is lined in cork. The Campy isn’t enameled—it’s just painted to look like it—but it pulls off the effect well.
$18 at Amazon $18 at Macy's Photograph: Amazon For Coffee Purists Fellow Carter (16 Ounce) Instead of a tiny sippy hole, the Carter’s screw-on cap reveals a wide tumbler that lets you breathe in your coffee’s aromas as you drink. The opening is 69 millimeters wide, so you can use most manual coffee brewers, such as an AeroPress or Hario pour-over , directly on it. That’s too wide for many cars’ cupholders, but it’s plenty stable, and you won’t have to worry about tipping it over on a desk. My average-size hands had no issues, but some buyers with smaller hands might find it difficult or uncomfortable to hold.
The interior is ceramic-coated, so you don’t get any metallic flavors, and the thin metal lip is curved like a cabernet glass. Its textured matte exterior coating is tough and held up as well as the mighty Hydro Flask’s coating. It's been completely leak-proof too. You’ll have no concerns throwing it into your laptop bag completely full.
$35 at Amazon $30 at Fellow Products Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Backcountry For Camping Snow Peak Double Wall Insulated Cup (450 ml) When traveling, I want to pack light. Snow Peak’s gorgeous insulated titanium camp mug is less than 4 inches tall, weighs only 4.2 ounces, and has foldaway handles to make it even smaller. Its 450-ml capacity equates to slightly more than 15 fluid ounces. As someone who finds washing mugs to be an interminable hassle, this is the easiest one to travel with—just refill, rinse, and carabiner it to the outside of your bag. You can also buy a lid separately.
$63 at Amazon $53 at Snow Peak Photograph: REI For Cans Hydro Flask Cooler Cup Tumblers and travel mugs are generally designed for you to pour your chosen beverage into, but what if you just want to slam a can in there? These kinds of insulated drink holders are particularly useful when I'm out and about, drinking a canned soda or beer, and there's no nearby recycling bin immediately nearby to toss the empty can into.
The Hydro Flask displaced the Yeti Rambler Colster because, yes, it's designed to keep an entire beverage can cool, but if you feel like pouring one out and drinking directly from the tumbler, you can do that too. Just remove the collar, and now you've got a handsome, stainless steel rim to sip from. The collar fits over the bottom of the can to stabilize it too, so you won't lose it. This is the 12-fluid-ounce version that fits a standard beer, soda, juice, or wine can. There's also a 16-fluid-ounce Tallboy Cooler Cup for $28 if you're feeling particularly thirsty.
$25 at Amazon $25 at REI $25 at Backcountry Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Amazon Honorable Mentions We run through so many travel mugs, and not all of them are winners. These are a few we like, just not as much as the ones above.
Contigo Luxe Autoseal for $36 : What makes the Contigo “automatic” is a button on the side of the lid that opens the sippin’ hole. There’s a lock to prevent the button from opening the hole too. With or without the lock activated, the Contigo never leaked a single drop. Of all the tumblers and bottles I’ve tested, this is the easiest to reach down and quickly use one-handed. You don’t want to mess with latches while you’re piloting a wheeled missile down the road. Some buyers have complained that the metal lid gets too hot, but I filled up the Luxe Autoseal with scorching, molten coffee, and the lid barely even got lukewarm, so consider that myth busted.
Yeti Rambler Colster for $25 : The Colster did a fine job keeping a can of beer or soda cool for hours, and I liked the way the insulator's lip sat below the can's rim so that it didn't interfere with drinking. It just lost out the top spot to the Hydro Flask because, unlike that one, it's designed to only be used with a 12-fluid-ounce beverage can inserted into it, although there is a 16-fluid-ounce Colester Tall for $30 if you want to use it with pint-sized cans.
Hydro Flask Trail Series Wide-Mouth Water Bottle for $45 : Hydro Flask's regular line of wide-mouth water bottles isn't exactly heavy at about 14 ounces for a 24-fluid-ounce version. Still, if you want to trim every ounce you can without resorting to a plastic bottle (which is quite a bit lighter), then the new Trail Series exists for you. It's purportedly 25 percent lighter than Hydro Flask's typical bottles, though you lose the extraordinarily tough powder coating.
Zojirushi Stainless Steel Mug for $29 : Zojirushi's classic 16-ounce travel mug is a favorite around these parts. The stainless-steel interior is BPA-free and has a wide-mouth opening to accommodate ice cubes. The lid locks to avoid accidental spillage, and I accidentally left hot tea in it for 18 hours and found it still hot when I cautiously opened it again. It’s also small enough to fit in my jacket pocket on chilly morning walks. It’s not my preferred mug for daily use, simply because the lid has three separate parts—a mouthpiece, a gasket, and a lid—that are deeply ridged and hard to clean. I also need a bottle brush to wash the interior.
Hydro Flask Mug for $28: This style of mug has become increasingly common. The Hydro Flask Mug merges a durable powder-coated, vacuum-insulated construction with the traditional, handle-sporting shape of a diner or camp mug. Hydro Flask does it better than most. The stainless steel rim makes it nicer to sip from than competitors' mugs, and it comes with Hydro Flask's usual drip-proof lid and bomber-tough powder coating that is nearly impossible to scratch. But it is more at home on a desk than at a campsite or in a car's cupholder, which it can't fit into.
Miir Camp Cup for $28: Miir's insulated coffee mug doesn't fumble any crucial details. It doesn't leak, it insulates hot and cold drinks just fine, and the coating is as tough as any Miir. But it's up against tough competition, and for the same money the Hydro Flask Mug is a bit nicer. The Miir lacks the stainless steel rim, and the transparent plastic lid feels a little cheaper.
Owala FreeSip for $28 : Drinking from the FreeSip while wearing a full-face motorcycle helmet (by tilting the helmet up slightly and sipping from under the chin bar) was surprisingly easy, thanks to the built-in straw on this mug. If you've got mobility or pain issues that make tilting your head a hassle, this mug is a solid performer. It's easy to grip too, with its flattened sides, which can come in handy for those with reduced hand dexterity.
OtterBox Elevation for $30 : At 8.5 inches tall, the Elevation 20 looks a lot bigger than it is. It has a copper lining to maintain your beverage’s perfect temperature, and the clear press-on lid has a locking mechanism. You can also switch it out for a straw lid or a French press lid if you’re in a hurry. It comes in a variety of stunning ombre hues.
Purist Mover for $48 : Ever empty a stainless-steel bottle of one beverage and fill it up with a different one, only to notice that the taste of the first drink lingers? The Purist has applied a thin layer of glass over the interior of the Mover, which keeps this taste transfer from happening. You can down a mug full of coffee and then fill it with herbal tea without risking a coffee aftertaste. I didn’t experience leaks from the Element top, but a high number of customers have reported their Purist lids leaking over time. I’ll keep using the Purist and update this page with information on how it performs over the course of the year.
S'well Traveler Tumbler for $30 : S’well boasts that its tumblers are triple-walled, but we’re not convinced that has much real-world benefit over a normal double-walled tumbler. What really sets the S’well apart are its designs. There are 12 finishes, from plain colors and bare stainless steel to elaborate patterns, such as blue marble and faux wood, and a slide-open lid so you don’t have to pop it off every time you want a swig of coffee.
Stanley Classic Vacuum Pint for $26 : Stanley’s vacuum pint includes a press-on lid with a deeply pebbled exterior that’s reminiscent of classic flasks, and also hard hats and construction sites. Although it’s billed as a 16-ounce pint, Stanley has added a few extra ounces to accommodate foam (or splashing hot coffee), and the lid comes with a slide-in metal bottle opener if you like to go immediately from work to happy hour.
Photograph: Amazon Avoid These Travel Mugs You Can Do Better We’ve tested a great many tumblers, and not all are winners. These aren't anywhere near as good as our picks above.
Greens Steel Beast 20-Ounce Insulated Tumbler : Greens Steel’s Beast tumbler has nearly 14,000 positive reviews on Amazon and is, at least for me, one of the top hits when I search Amazon for an insulated tumbler. But the rubber seal around the lid is thin and easily comes out of place. I was ready to write the Beast off when it was leaking like a sieve, but after I adjusted the seal, it was reasonably leak-proof. Sometimes it dribbles, sometimes it doesn’t, depending on whether the seal stays put when you’re attaching the lid. The exterior color coating is not as durable as the Klean, Hydro Flask, Yeti, or Fellow. It did come with a regular metal straw, a thick metal milkshake straw, and a cleaner brush.
Stanley Adventure Vacuum Quencher : It's not that it's a bad tumbler, but rather that I don't see the point. Yes, it has the typical Stanley bombproof powder coating and build, and it does a fine job of keeping hot drinks hot and cold drinks cold, but the chief feature is just … a straw. It pokes out of a hole in the lid without sealing to the opening's sides, so it's not spill-proof if you're using the straw, even though there's a lid on it. You can close the lid, but you have to remove the straw and put it somewhere. It doesn't flip down conveniently or anything. “Insulated tumbler with a reusable straw thrown in” seems like an afterthought of a product.
Snow Peak Kanpai 500-ml Bottle : Unlike most of Snow Peak’s line of camping and backpacking gear, the Kanpai is stainless steel, not titanium, and it’s not made in Japan. It’s a double-walled, insulated stainless-steel tumbler with a glossy finish, and it comes with three lids, for some unnecessary reason. There’s a white screw-on lid that needs to be removed every time you want a drink, and a black version of the same lid. The third lid—one with a sipping hole that can be closed with a sliding latch—leaks if the Kanpai tips over. It took damage in a mere 3-foot drop when it was empty, landing on its rim, which flattened. A steel bottle, especially one with no liquid in it, should be able to survive that without battle scars.
Toaks Titanium Double Wall 450ML Cup for $40: More often than not, I champion Chinese-made Toaks gear as an affordable source of titanium camp cookware compared to Japanese-made Snow Peak and Evernew and Thai-made MSR, which tend to be more expensive. But this mug is only $10 less than the Snow Peak mug we recommend above, and it's finishing is rougher.
Writer and Reviewer Senior Associate Reviews Editor X Topics Shopping buying guides Travel kitchen outdoors Medea Giordano Pia Ceres Louryn Strampe Matt Jancer Nena Farrell Jaina Grey Eric Ravenscraft Brenda Stolyar WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,092 | 2,023 |
"Best Running Gear (2023): Shoes, Clothes, Accessories | WIRED"
|
"https://www.wired.com/gallery/best-running-gear"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adrienne So Gear The Best Running Gear for Your Long and Chilly Winter Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The Best Running Shoes $170 at REI (Men's) The Best Fitness Tracker $350 at Amazon Best Headphones $100 at JLab Audio Best Tights $90 at REI (Women's) I have given up on persuading people to take up running outside in winter. Gyms are fine! And if pulling on multiple layers of clothing and lights to run outside in the grim, freezing dark isn't something that calls to you, a few well-meaning words probably won't do the trick.
But running in these long, dreary months is a chance to give cabin fever the finger and get some much-needed fresh air and vitamin D. Do you need some tips on how to prevent hypothermia while you trot along? I pulled together some of the gear that gets me out every day, along with a few starter tips. Be sure to also check out our Best Fitness Trackers and Best Running Shoe guides—and all the gear that helped WIRED's former editor in chief run faster marathons in his forties.
Updated February 2023: We added our favorite cold-weather running picks, like Patagonia Pack Out Tights.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Photograph: On The Best Running Shoes On Running Cloudvista Waterproof When the temperature is hovering around freezing, the last thing you want are squishy, squelchy feet. I am deeply skeptical of On Running's claim that their signature sole bubbles cushion your joints in any significant way against hundreds of pounds of your body weight repeatedly hitting frozen asphalt. However, I do very much like these shoes, which are waterproof (the membrane is recycled). They feel stiff and supportive in mud and have a protective rubber rand around the outside of the shoe. The big lug soles offer lots of traction, but the shoes themselves are insanely light—only 17.6 ounces for the pair. Also, the laces never come undone! My other longtime favorites are the Altra Lone Peaks ($170).
However, if you don't want to go straight to a trail shoe just yet, you can always try Yaktrax ($35) and waterproof socks ($37) with your regular running running shoes first.
$170 at REI (Men's) $170 at REI (Women's) Photograph: Garmin The Best Fitness Tracker Garmin Forerunner 255 We regularly recommend Garmin's Forerunner series to runners. If you're a multisport athlete who also wants advanced sleep features, try the midrange Forerunner 255 ( 8/10, WIRED Recommends ). (Do you want fewer features, or more? There's also the Forerunner 55 and the Forerunner 945 , and Garmin updates the line pretty regularly.) The standout feature with Garmins is the company’s comprehensive (and free!) sports training program with Garmin Connect, which includes a Morning Report when you wake up. Morning Report gives you your Body Battery, a measurement of how ready you are to take the day's activities, as well as the weather and a daily greeting. It includes multiband GPS support for greater accuracy with location tracking, a barometric altimeter and compass for when you hit the trails, and support for other sports, like cycling.
$350 at Amazon $400 at Best Buy $350 at Target $350 at Garmin Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: JLab Best Headphones JLab Audio Epic Air Sport ANC (2nd Gen) As an iPhone owner, I am still pretty devoted to my Beats Fit Pro ( 9/10, WIRED Recommends ), but even I admit that it's hard to spend more than $100 on a pair of headphones whose only purpose is to stick to your head and get crusty with sweat. Right now, my favorite out of the crop that I'm currently testing is the JLab Epic Air Sport ANC. JLab has consistently made some of our favorite affordable headphones.
I have spent several weeks trying to run the battery out on these things with multiple walks and runs per day, but every day they continue to say “battery full” when I put them on. They come with around 70 hours of playtime, and the case can charge wirelessly (JLab's signature charging cable is included).
They're rated IP66 against streams of water and are significantly thinner than some of the other earbuds I'm currently testing. For someone whose left ear is determined to spit out almost every earbud on the planet, JLab's Cloud Foam ear tips fit securely and well. I hate, hate, hate fidgeting with an earbud midrun. Everything you wear should help you, not irritate you.
$100 at JLab Audio Photograph: Patagonia Best Tights Patagonia Pack Out Tights The rule of thumb is to dress for running as if it's 20 degrees warmer than it is. For example, if it's 40 Fahrenheit degrees, you want to dress like it's 60. On those days, I like any leggings that are high-waisted or have a drawstring, so they don't fall down, and are made from compressive and durable fabric, like Lululemon's Fast and Frees ($98) , which have reflective details and come in a few inseam lengths for short-legged folk.
Once the temperature drops, however, the leggings slowly get thicker. Right now, I'm reaching for the Patagonia Pack Out tights. They're technically a hiking legging, which means there's a crotch gusset for additional mobility (I can't be the only one who loves a good crotch gusset). They're thick and insulated and have a wide waistband so they don't roll over. For below-freezing days, I have a pair of these Smartwool sport fleece tights ($140) , which have a wind-resistant panel on the thigh.
$90 at REI (Women's) $60 at Backcountry (Women's) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Smartwool A Good Base Layer Smartwool Merino Classic Long Sleeve Layering in the winter is a complex puzzle. What I wear depends on how long I'll be out and what I'm doing. A long, slow run with friends? I'll probably put on a breathable puffer jacket or a fleece for a glorified walkie-talkie. Short, fast intervals? Probably a wicking top under a water-resistant shell.
But no matter what midlayers or shells I'm wearing (or not), I'm probably wearing a base layer. I've had one of these Smartwool shirts for years, and it still holds up.
Here I will offer you my second layering cheat code for free: Are you stymied over which jacket to wear? Save yourself some trouble and get a vest. A shell doesn't seem quite warm enough? Does it seem just a little too warm to put on that full-sleeved fleece? Enter vest, stage right. I particularly like this light, sleek, and stretchy one ($235) from Ibex, which is PFC-free and packs down small enough to stuff into my running pack. It also looks good enough to fit under my wool coat on days when it's just a little too cold $87 at REI (Men's) $90 at REI (Women's) Photograph: BlackStrap Best Face Covering BlackStrap The Hood Balaclava If it's around the 30s or 40s, any hat or headband will do. But when the temperature sinks lower—if you're still going out, which I might not be—you have a few options. Even an hour or two in sub-20 temps might be enough to give you painful frostnip or frostbite on your nose or ears. I'm also prone to cold-induced asthma , and I appreciate having something to cover the lower part of my face and help warm the air before it reaches my lungs.
I prefer natural fibers, but I make an exception for this balaclava. The fabric is very soft, so you can wipe your runny nose and drool all over it as needed and it won't scratch your sniffly, snotty face. A hinge makes it very easy to pull it on or off your face as needed. It's also UPF 50, so it will protect you from the sun.
$38 at Amazon $38 at REI Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Tifosi Optics Best Sunglasses Tifosi Vogel SL This is the year we stop caring about “looking good” or even “looking normal” and embrace wearing horrible sunglasses not only while running but while picking up our kids and while walking to happy hour at the bar.
Tifosi consistently makes some of the most durable and affordable specialized sports sunglasses. The Vogel SL are Tifosi’s running pair, and they have everything you want in sport sunglasses—hydrophilic grips on the nose, light and flexible arms, and big lenses that cover most of your face. They're not polarized, which could be an issue if you run in places near water or on snow with a lot of reflective glare. But if you're just going out for a couple of hours on the weekend and tossing these in your car's console when you get home, these are fine.
$40 at Amazon $40 at REI Photograph: Showers Pass Best Gloves Showers Pass Crosspoint Waterproof Knit Gloves These knit gloves have a bit of a cult following in Portland, Oregon, where I live. They have three layers—a rubbery nylon exterior, a waterproof membrane, and a warm merino wool lining—and they're expensive enough that I cried when I lost one (then immediately bought another pair). They fend off ice and rain and keep your hands warm when you walk out the door and your hands feel like they might turn into icy appendages bolted onto your body.
Once you're a couple miles in, they vent heat when you've started sweating and are ready to strip everything off. They're also light and have little grippy pads on the palms that make them suitable for biking and hiking as well.
$49 at REI $50 at Evo Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Nathan Sports Best Storage Solution Nathan Crossover 5 Liter Hydration Pack I really like Nathan packs. They're small, simple, versatile, and last forever—I had my previous Nathan pack for years without noticing any wear on it (it did get a little smelly). Since I run (very slowly) and for long distances, mostly alone, I very rarely go without a bag of some kind. As the name implies, this one is small enough for short solo hikes and mountain biking excursions while large enough for a tiny hydration reservoir, some snacks, my phone, hat, and gloves. I also like the color! $95 at Backcountry $80 at Dick's Sporting Goods Photograph: Zensah The Most Fun Running Socks Zensah Limited Edition Mini Crew If you're just running a few miles every other day, you probably don't need fancy socks with a lot of features. (If you do, we have a great running sock roundup here ). These are the printed versions of Zensah's compression socks, which are our favorites. They have a seamless toe, added heel protection, and silver-infused fabric to combat stink. I also like crew-height socks when trail running, because the higher sock keeps me from kicking pebbles or dirt into them. The cool tan lines are just a bonus.
$20 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Knog Best Lights Knog Plus Twinpack Black Maybe you don't really need a headlamp so that you can see. Maybe you need lights so that car drivers can see you.
A safety vest ($9) works great, but I also have a drawer with a box filled with an assortment of miscellaneous lights for when dusk starts to fall. They're waterproof, have a 40-hour run time, and recharge just by sticking directly into a USB port. Most important, they're light and have a clip, so I can stick them anywhere on my clothing—pockets, lapels—and not have to worry about fitting them on top of my hat, earbuds, or whatever else I'm wearing on the other parts of my body.
$24 at Amazon Photograph: Sun and Swell Foods Best Snack Sun & Swell Oatmeal Cacao Chip Bites You'll have to experiment to find which snacks keep you fueled without upsetting your stomach. Highly processed goos and jellies tend to give me diarrhea (sorry). These cookie bites are pocketable and come in separate bites so that you don't leave half-eaten bars in your pockets when you throw your jacket into the wash. They're sweetened with dates and cacao and are tasty enough that even my 5- and 8-year-old will eat them.
$14 at Sun & Swell Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Champion Best Therapy Treatment Champion Lacrosse Ball The worst problem with winter running is stiffness and getting injured. If you don't start slowly and give yourself enough time to cool down and stretch, your muscles can really suffer in cold climates. A few common ailments include shin splints or plantar fasciitis, which you can usually avoid by starting slow, warming up and cooling down, stretching, and upping your mileage gradually.
If you get unlucky enough to acquire some kind of chronic ailment, I recommend seeing a physical therapist who specializes in running. But I would also recommend stretching and getting a small, cheap, hard, rubbery lacrosse ball. Just spend a few minutes each day rolling out the muscles in your calves, thighs, and feet. It's like using a foam roller but smaller, easier to transport, and better for targeting small muscles.
$6 at Amazon Senior Associate Reviews Editor X Topics running shoes marathon Shopping buying guides Adrienne So Brenda Stolyar Pia Ceres Medea Giordano Medea Giordano Brenda Stolyar Boone Ashworth Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,093 | 2,023 |
"25 Best Cat Toys and Supplies (2023): Scratchers, Window Perches, Modern Furniture, and More | WIRED"
|
"https://www.wired.com/gallery/best-cat-toys-and-supplies"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Medea Giordano Louryn Strampe Gear The Best Cat Toys and Supplies Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Basic Cat Rules Read more Find a Litter Box They Like $85 at Amazon (Plant Litter Box) If You Want an Automatic Box $650 at Smarty Pear (Leo's Loo Too) A Cheaper Way to Monitor Bathroom Habits $200 at Petivity Cats are beautiful, interesting, weird creatures. If you're lucky enough to be loved by one, it's your God-given responsibility to give them a comfortable and fun home. We wrote about the supplies you should get if you recently adopted a pet , but once you have that pet situated at home, you'll want to create a healthy, welcoming space for them. Cats require a specific type of environment to play, scratch, and relax.
Here are our favorite products based on months of testing with our own cats. Even if our pets rejected a particular product, we still examined overall construction, design, and value to determine whether it may be of use to other kitties. Felines can be finicky, so you may have to go through a few options to find the right fit.
Check out our related guides, like the Best Veterinary Telemedicine Services and Our Favorite Fancy Cat Furniture.
More of a dog person? We've got you covered! See our Best Accessories and Tech Essentials for Your Dog guide.
Updated March 2023: We've added a bunch more cat stuff we like, including Purina's Petivitiy bathroom tracker and the Cat Amazing treat puzzles, as well as the Fur Zapper and Sprinkle & Sweep cleaning accessories. We've also updated prices and links throughout.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Photograph: Martin Poole/Getty Images Basic Cat Rules Dos and Don'ts Don't listen to the cat haters: Cats do form a connection to their human owners. And while they may be more low-maintenance than dogs, they still require thoughtful care. Here are some basic dos and don'ts when it comes to owning a cat.
DO: Separate food and water. Use multiple litter boxes for multiple cats. Give them ways to hunt their food. Ensure they get exercise. Give them places to hide and feel safe. Regularly trim their nails. Give them love and affection! DON'T: Leave them unattended around these toxic plants.
Accidentally harm them with common essential oils like eucalyptus.
Feed them a vegan diet , milk (yes, really), or these other toxic foods.
Declaw them.
Photograph: Tuft and Paw Find a Litter Box They Like Litter Box A litter box is essential. What kind you get depends on your cat—not every cat likes enclosed boxes, and others need high sides to shield your walls from urine (sometimes they aim high!). You should have one box per cat, and one on each floor if you live in a multilevel home.
You'll find cheap, standard litter boxes everywhere they sell pet items, but if those don't work, consider these: Rubbermaid storage bins (without the lid) are cheap and work well.
Tuft and Paw's Cove Box is simple but modern with detachable sides and a place to hold its scoop and small dustpan. (All Tuft and Paw products are aesthetically pleasing and pricey.) The Good Pet Stuff Hidden Litter Planter nicely blends into small spaces, but it needs to be replaced more than other boxes as it gets weirdly grimey.
Want to try an automatic litter box ? We have thoughts below.
Can't decide on a box? Kitty Poo Club delivers disposable, recyclable boxes to your door every month. The cardboard has a thin plastic coating inside, so it shouldn't leak, as long as you're actually replacing them.
★ You should also use a litter mat underneath the box to minimize the litter tracked through your house. Just vacuum and shake it out regularly.
$85 at Amazon (Plant Litter Box) $199 at Tuft and Paw (Cove Box with Shelter) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Smarty Pear If You Want an Automatic Box Self-Cleaning Litter Boxes We Like I (Medea) was unsure about robotic litter boxes—they're big and expensive, and experts warn that not cleaning out a box every day could mean missing potential signs of sickness. But then I tried two that changed my mind: Leo's Loo Too and Whisker's Litter-Robot 4.
Both are still large and expensive, but they connect to apps that keep track of your cat's bathroom habits, alerting you when they use the box and what their weight is. You'll know something is off if their bathroom trips suddenly change, and you can scoop a little less too. Both have sensors and other safety features so it won't spin if a cat is inside. Leo's Loo is the most sensitive, so if you have a particularly curious cat, this might be the one to get. Bigger cats will probably prefer the larger drum of the Litter-Robot.
$650 at Smarty Pear (Leo's Loo Too) $699 at Whisker (Litter Robot 4) Photograph: Purina A Cheaper Way to Monitor Bathroom Habits Petivity Smart Litterbox Monitor System You don't have to spend $700 to know exactly what's happening when Fluffy visits the commode. Purina's Petivity ( 8/10, WIRED Recommends ) sits underneath a standard litter box and, once connected to the app, tells you which cat visited the box at what time, how much they weigh, and if they went one or two.
This has made my life much less stressful, because now I know exactly how much Huxley, who has lower urinary tract disease, is urinating. If something is off, I know immediately and can get him to the vet.
$200 at Petivity Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Amazon Keep Litter Odor Undercover Litter Genie For years, I didn't understand the allure of the Litter Genie. Then I moved into an apartment complex where taking out the garbage meant a trip across the parking lot, and I started making excuses to not clean out the box—it was raining or dark, or I had my hair up in a towel and didn’t want to go outside. Finally, I bought one.
As with a Diaper Genie, you scoop clumps into the top compartment and open a hatch that drops it to a bottom compartment, where it holds in the odors for up to two weeks. You can clean every day without daily trips to the trash and without wasting a ton of plastic bags. When you’re ready to empty it, there’s a handy attachment that safely cuts the bag to tie it off and start a new one. You'll have to commit to buying refills , though. There's also an XL version if you have multiple cats.
$20 at Target $21 at Chewy Photograph: Wayfair … Or Out of Sight Entirely Archie & Oscar Rena Litter Box Enclosure Litter box placement is hard. You need a low-foot-traffic area, away from your cat's food and water, and preferably a space where a stray odor won't ruin the mood. Most people don't want to relinquish closet space or a bedroom to a litter box. I (Louryn) tested and loved this litter box enclosure. It conceals my cat's litter boxes from both eyes and noses, and it gives my kitties privacy. The neutral colors work well in most rooms, and you can also paint it. My cats took to it right away and seem to be as relieved as I am that we can't see one another while they do their business.
The enclosure looks like a small credenza or freestanding cupboard. I don't think you could guess it housed litter if you didn't know. I sprinkle this deodorizer on the litter, but the enclosure does a good job at trapping odors on its own. This is my favorite piece of cat gear I've ever tried, and it's often on sale.
$110 at Wayfair Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Cat Person Get Better Bowls … Glass and Stainless Steel Food and Water Bowls When it comes to materials, most vets and cat experts will tell you to use stainless steel or glass bowls for your pet's food and water. Plastic can get dingy and dirty fast, and it holds onto bacteria. This can result in what's called cat acne.
Cat Person's Mesa Bowl gives a modern take to perfect-posture eating. It's made of polycarbonate, and every part is dishwasher safe (and Cat Person packaging turns into cardboard cat houses).
Owala's stainless steel pet bowl is cute and doesn't slide around, but basic stainless steel bowls are simple and inexpensive.
Elevated feeders are a good option, as they can help your cat's neck.
WIRED editor Adrienne So likes the (expensive!) Yeti Boomer Dog Bowl for her pooch. It's great if you have an animal that likes tipping bowls over.
$10 at Amazon (Stainless) $40 at Cat Person (Mesa Bowl) Photograph: Amazon … Or Slow Their Rolls Caflower Slow Feeder Lick Mat My neighborhood has an affectionate real-life squishmallow of an outdoor cat named Stokely. We call him a walking black hole due to his gravitational force (he weighs over 20 pounds). He’s the sweetest, biggest gravy boat imaginable, but it's tough not to feel like an enabler when he comes around asking for dinner. This slow feeder has helped curb his habits—maybe not his appetite, which is a runaway train with no conductor—but the mat definitely slows him down. The included spatula means you don’t have to get mystery gravy on your human utensils, and the suction cups keep it stuck firmly to the floor. The mats are easy to clean. The suction cups might stick to your kitchen counter if you load the mat there, so I find it best to place the mat in the cats’ feeding area before mashing the food in. I fully believe that if this worked for Stokely, it'll work for any cat.
Some reviews mention that particularly toothsome cats might chew on the mats to the point of degrading them. While I have not experienced this, it's always smart to supervise your pet while they're eating.
$15 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Catit Try a Water Fountain Catit Water Fountain Cats don't feel the need to drink water the way humans do. So if they're unhappy with their water situation, it could lead to dehydration and other serious issues like bladder stones and urethral blockages—some cats don't like their water right next to their food, which is why it's recommended to keep them separate. Male cats are especially prone to these issues. Feeding them wet food helps with their water intake, but we wanted a more enticing way for our cats to drink water. Some cats prefer drinking from fountains (or, as many cat owners have experienced, from the bathroom faucet ).
If you get a fountain, you'll need to have an outlet nearby, and you'll need to change the filter about every month, but it's worth it if your cat uses it. We tried Catit's plastic flower fountain and its stainless-steel-topped fountain.
While stainless steel bowls are preferred, the plastic should be OK as long as you keep it clean. See below for a smart option.
$37 at Amazon (Steel Top) $28 at Amazon (Flower top) Photograph: Catit Or a Smart Fountain and Feeder Catit Pixi Smart Fountain and Feeder Catit’s Pixi series offers a smart fountain and feeder controlled via the Pixi app (available on iOS and Android ). The fountain's pump has a small LED that shines through the clear cat nose on the front, turning red when the water is low and blue if UV-C sterilization is on. It blinks blue when the filter needs to be changed, and the app will also alert you.
You can use the app to either pour food remotely or on a daily schedule. You can also press the cat nose to pour, or disable it if your pets figure it out. The app will tell you when the reservoir is ready for a refill. Plus, it includes a spot for backup batteries in case the power goes out while you're away.
★ Another Smart Water Bowl: Sure Petcare Felaqua Connect ( 7/10, WIRED Recommends ) is another great water bowl that tells you when, and how much, each cat drinks that's to its microchip sensor.
$135 at Catit (Feeder) $130 at Amazon (Fountain) $135 at Catit (Fountain) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Chewy Let Them Scratch Scratching Posts Cats need to scratch, and if you want to prevent them from ripping up furniture, you must provide them with ample scratching posts. Declawing is not the answer—it's like removing your fingers at the last knuckles and can lead to a ton of problems.
There's a wide spectrum to choose from, and these are some of our favorites: A simple cardboard slat costs just a few bucks or level up to the Boots and Barkley tunnel.
My cats really like the Wave Scratcher from the same brand, made of sisal and carpet.
PetFusion lounges are a long-lasting, but pricey favorite. They're sturdy, look nice, and once the top has been thoroughly destroyed, you turn it over for a brand-new surface.
Target's adorable house cat scratchers are loved by both of our cats—you can get one for every season, holiday, or theme.
This cat scratcher (also from Target) has refills available online and in-store, and works as a toy too with its attached ping pong ball. There’s nothing cuter than a cat playing soccer with a ball they’ll never be able to free.
★ Don't forget to trim their nails: You should also regularly trim your cat's nails.
(It's easier than it sounds, but it might be a two-person job.) Ask your vet to show you where to trim to so you don't cut their quick (the part of the nail that holds the nerves and blood vessels). There are also helpful guides online.
$51 at Amazon (Lounge) $15 at Target (Wave) $20 at Target (Tunnel) Photograph: Catit Give Them a Place to Climb Cat Trees Cats like to jump and climb whatever they can, so a nice cat tree should help keep them occupied and off your mantle or breakable glassware. Cat trees are made from materials that can be scratched up, and some include separate scratching posts. If you aren't worried about aesthetics, you'll find plenty of good cat trees at pet stores, as well as places like Home Goods or the like.
Catit's Vesper line has a nice modern feel that's hard to find in moderately priced cat furniture. The Small Vesper Box doesn't take up too much space, but it's the perfect height to get my cats right at window level. They can nap in the covered bottom level, scratch and play on the second level, and sit on the soft fluffy pillow on top for bird watching. It was really easy to put together, and the cloth pillows and pads are machine washable.
The Vesper High Base is a taller option, great for multi-cat homes or for pets that don't necessarily like to lounge together.
The Vesper line includes many other sizes and colors.
$70 at Catit $170 at Catit Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Whisker And a Stylish Place to Rest More Modern Cat Furniture When you live in a small apartment, everything you decorate with matters because it's all on display—nothing really gets hidden when you only have one to three rooms. So some of us want our cat's furniture to match too.
We have a full guide on the fanciest cat furniture we've tried , but be prepared to shell out some serious cash. These are two of our favorites: Whisker's Cat Silo (this is the brand that makes the Litter-Robot) looks nice enough to be an end table, but it has sisal mats for them to stick their claws into and a thick pad so they can relax inside. The gold legs are a nice touch too.
Tuft and Paw's Happy Camper Cat Bed is extremely cute, and I get happy every time I see my cat peacefully asleep on its furry interior bed. You can put it together with the felt on the outside or inside, whatever your decor and cats prefer. This brand is more expensive, but everything we've seen so far is nicely crafted.
$199 at Whisker (Cat Silo) $249 at Tuft and Paw (Happy Camper Bed) Photograph: Amazon Keep an Eye on Them Petcube Play 2 Camera The ability to sneak a peek at your cat when you're out offers nervous pet owners (most of us) some peace of mind. We have a whole pet camera guide , but Petcube's Play 2 Camera is designed specifically for cats, with an app-controlled laser. The wide-angle camera records in 1080p and has two-way audio. It's also compatible with Alexa, so you could ask Amazon's voice assistant to play with your pet if you're busy.
★ Another pet camera we like: We've been using Eufy's dog camera.
Despite the name, it works just as well for cats. It doesn't have a laser, but it does launch treats, and it can pan around the room.
★ Standard cameras work too: A simple security camera works just as well and they're usually cheaper.
Cync's indoor camera is a favorite and you can slide it up to cover the lens when you don't want it watching, and Nooie's Cam 360 can pan to follow your cats throughout the room.
$199 at Amazon $199 at Chewy $199 at Petcube Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Enabot Give Them a Robot Bestie Ebo Pro I (Medea) tried two robot cat pals, the Ebo Pro and Rocki.
My cat Huxley loved them both, while Eely-Rue couldn't be bothered with either. The Ebo Pro was expensive but took the win. If I even bump Ebo and it makes a noise, Huxley will come running from wherever he is in the house. (The brand has newer models too, the Ebo Air and SE.
) Both are equipped with cameras and microphones and are designed to be controlled by you from home or away. That way you can play with your cats if you can't be home cuddling. The Rocki is larger and has a treat dispenser, but it can't run on its own and had a bit more glitches in its app.
$299 at Enabot Photograph: Basepaws Get Their DNA and Health Info Basepaws Breed + Health Cat DNA Test Basepaws is thorough.
After swabbing our cats' cheeks and sending the samples back in the included envelope, we received PDFs of nearly 70 pages detailing their breed percentages—as well as several pages about all the cat breeds, and how our babies stacked up against around 115 feline health markers.
The test tells you if your cat is clear, a carrier, at risk, or at high risk of numerous metabolic, cardiovascular, eye, blood, endocrine, renal, autoimmune, skin, musculoskeletal, and connective tissue disorders, as well as blood type, transfusion risk, and other traits. Then there's also all the dental info—I found out my cat Eely was at risk of periodontal disease and the vet confirmed her gums were inflamed, so we scheduled a cleaning.
Any cat can develop a sickness or dental problems, but having a baseline can alleviate anxieties and also empower you to work with your vet to make the best life choices for your cat.
$159 at Basepaws $159 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Amazon Keep Calm and Kitty On Scientia Pet Bserene Pheromone + Catnip Calming Solution Cat anxiety can manifest as fighting, obsessive grooming, overeating, or our least favorite: peeing in places they shouldn't. When cats are happy and calm, they rub their cheeks on things, depositing pheromones that mark something as safe and familiar. Pheromone sprays imitate those cheeky chemicals, convincing your cat that an area or situation is A-OK.
I (Louryn) have tried other pheromone diffusers and sprays; sometimes they work, but they often reek.
I don't recommend Feliway nor Scientia Pet's smelly diffuser, but this spray smells better and works faster than others that I've tried. It's infused with catnip, making it smell more herbal and vegetal than the artificial hairspray vibes I got from similar products. You spritz the problem area, like a pet carrier before a vet visit, and wait 15 minutes before reintroducing your animals to that location. I could tell it was working almost immediately. Instead of terrorizing both one another and myself, my cats sniffed around and took a nap. Calmer days are possible! $35 at Amazon $35 at Scientia Pet Photograph: Medea Giordano A Perch for Window Gazing K&H Kitty Sill Cat Window Perch These window seats are a great way for cats to bask in the sun and keep a watchful eye on the neighborhood while safely indoors. They're easy to install too, with sticky strips that attach to your window sill and can hold up to 40 pounds. You can also nail the base into the window frame, and there are even heated seats for super-spoiled kitties. The covers are removable and can be machine washed.
You'll need a window sill at least 2 inches deep to properly support it. If you don't have that, see the next blurb on suction-cup seats.
$30 at Chewy $30 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Amazon A Suction-Cup Seat Kitty Cot Cat Perch With Suction Cups I (Medea) was scared to try perches that attach with suction cups, out of fear they may just suddenly fall, but after some searching, I found the Kitty Cot perches. They stick extremely well—Huxley's 13-pound belly didn't budge it.
The seat part is made of tough nylon that should outlast even the sharpest claws. Kitty Cots come in a few sizes, as well as a deluxe version that can be maneuvered to sit flush against the window. That way, you can close your blinds without removing the bed. The company also has mats for the perches, but they've been unavailable lately, and your cat may prefer a blanket or bed that they already like on top anyway.
$45 at Chewy $45 at Amazon Photograph: Meowbox Consider a Subscription Box for Toys Meowbox Cats need toys to keep them stimulated and entertained. Unfortunately, there isn't one toy that every cat will love. Some will play with any toy you bring home, others will prefer strings that fall off your clothes and the box that the expensive toy came in. You can go to a pet store and pick up a bunch of things to see what they like—most will probably find some enjoyment out of ball they can push around or crinkly catnip toys—or you can try a subscription box. I've used a few, and Meowbox is my favorite.
You can choose to get deliveries every one or two months, and they'll include incredibly cute toys following an equally cute theme, plus treats. Getting a few different toys will show you which your cat prefers, and then you can continue getting boxes or cancel without hassle once you're sufficiently stocked up.
Plus, for every box sold, the company gives food to a shelter. You can see exactly where on its website.
$24 at Meowbox Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Cat Amazing A Toy to Hone Their Hunting Skills Cat Amazing Sliders Puzzle Feeder If you have a cat, you know they typically want whatever piece of trash they find rather than a nice toy you've actually spent money on. I have to say, though, these Cat Amazing puzzle toys have been well received by my cats, and the toys keep them sharp by activating their hunting skills and making them use their brains.
The brand has a few sizes, but they're all made of cardboard and easy to put together. Just add their favorite treats.
$26 at Amazon $26 at Chewy Photograph: Amazon Extra Window Protection Extra Window Screens Because my cats like to be up at the window sleeping or chirping at birds, I always use extra screens as a reinforcement. If they roll over and lean all their weight against the open window, or jump at a squirrel, they won't push the screen out of its track and go flying out the window. Check your local Home Depot or Lowe's, as they tend to be quite cheap there.
$12 at Amazon $5 at Home Depot Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Amazon Keep Your Carpets Clean Bissell Pet Stain Eraser PowerBrush Cats puke and cough up hairballs, usually on whatever carpeted surface they can find. They'll also occasionally get a little piece of poop stuck to their fluffy butt hair and drag it across the room in a desperate attempt to flee its grips (or maybe that's just my cat). A good carpet cleaner will be a lifesaver. We have a guide with several options , but I particularly like the Bissell Pet Stain Erase PowerBrush.
I used to use a Hoover cleaner , but this specific Bissell is so much easier to use and clean when you're done. It's small and light but powerful, cleaning even day-old stains, and there are no long hoses or tiny little parts for debris to get stuck in—any part that's going to get grimy from what you're cleaning can be rinsed out easily. It's portable too, so as long as it's charged you can walk around cleaning every surface imaginable without being tethered to an outlet. I don't audibly groan when I spot a pile of puke anymore, and that's a big deal.
We also like Bissell's Little Green Cleaner.
$134 at Amazon $134 at Target Photograph: Amazon And Clean Your Hardwood Floors Ecovacs Deebot Ozmo T5 Despite my best efforts, my kitties track litter everywhere their toe beans travel. Like magic, they also dust up fluffy fur tumbleweeds that drift across my hardwood floors. I have to sweep or vacuum at least once a day. This robot vacuum/mop combo has been a time saver. It's easy to use, and when the dust bin gets full, it's easy to empty and clean as well. I lovingly named it Bonk, and my cats have accepted it as their new sibling. Bonk is smart enough to use more suction over the litter mat, use his weird little arms to get into every corner, and alert me in an almost uncanny human voice when his brush is tangled. The companion app is pretty user-friendly and allows me to schedule cleanings or check on Bonk's whereabouts with just a tap or two.
The T5 is expensive, and it isn't on our list of the best robovacs (though we like a few products from Ecovacs). However, what makes it cool aren't really its individual features. Any good robot vacuum will offer users a similar sense of satisfaction. Having a helper corral random whiskers, litter dust, and fluffs has made a big difference in my daily to-do list.
$179 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Roverlund Hit the Road Roverlund Pet Carrier [INT: LOURYN'S LIVING ROOM, PRE-ROVERLUND CARRIER] LOURYN: Come on, kitty. You sit in every other container. Why won't you get in this one? HER CAT, PROBABLY: Your motives are suspicious. You want me to do the thing, therefore I cannot possibly do the thing.
LOURYN: It's got your blanket! And treats! And pheromone spray! And toys! And my love! HER CAT, PROBABLY: I hate blankets. I hate treats. I hate your love. Please understand that this is a personal attack. Call the vet and inform them we will be running 12 to 24 years late.
[END SCENE] Roverlund's carrier is the only one I've used that my cats will (sort of) tolerate. I feel better not cramming them against hard plastic or squinting through tiny holes in order to see them. They feel better with all-encompassing ventilation and a fully unzipping top instead of a claustrophobic cage opening. It's a win-win situation that has drastically shortened the standoffs between me, my cats, and a looming vet appointment. (We also recommend this carrier in our dog gear buying guide ; it's a WIRED Gear team fave.) ★ Another Carrier We Like: Medea just started using the Diggs Passenger Carrier and is impressed by its craftsmanship and safety features, including seat belt clips and a buckle strap. There's also a million pockets and the interior bed easily fits a pee pad over it if your pal is prone to accidents (it comes with one pad for you to try).
$159 at Amazon $159 at Roverlund Photograph: Lucky Pet (Safely!) LuckyPet Break-Away Cat Collar Unfortunately, I (Louryn) can speak firsthand to the devastation that comes with having a pet go missing. There are a few things you can do to prevent it.
Step one is to get your pets microchipped.
Step two is to make sure they’re wearing a collar with identification. ID tags are widely available, but ideally the one you go with will be reflective and legible. Whether to list your cat’s name is a personal choice, but the ID should definitely include your phone number.
I ordered this collar for my cat after her brother went on an extended vacation without my permission. The clasp breaks away so the collar won’t cause injury if it gets snagged. It has held up well over time, and it doesn't bother my easily ruffled fur baby. If it bothers yours, there are plenty of others, some of them high-tech (which I've yet to try). No matter which option you choose, make sure that it's from a trusted brand. The collar should be durable, highly visible, and lightweight, with a breakaway clasp.
$9 at LuckyPet Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Chewy You May Want to Try Chewy Chewy Chewy is a big retailer now, but we're still fans. The company offers nearly any pet brand you're used to, with easy-to-manage auto-ship orders (usually at a slight discount), so you don't have to worry about running out of food and litter. Plus, it's nice to have that heavy stuff delivered right to your door.
Shipping is fast, and the customer service is good, in our experience. They answer questions quickly and efficiently and will replace any damaged items, no questions asked. I (Medea) received a busted litter package once, and Chewy sent a new box the next day. Every order since then has been more sufficiently packaged to avoid spills. Plus, if you include information on your pets in your account you'll get birthday cards and potentially even hand-painted portraits.
Chewy has also rolled out a televet service.
Buy at Chewy Photograph: Sabina Torres/Getty Images More Cat Supplies We Like More Cat Products Steps for $35 : These cardboard steps were easy to put together and are surprisingly sturdy. Plus, there's a little opening on the sides so they can play underneath.
Air Purifier for $152 : Air purifiers help tremendously if you're dealing with a stuffed-up nose from cat dander and fur, especially if you have carpets. We have a full air purifier guide , too, with many more options.
Chom Chom Hair Remover for $30 : My cats are arguably too fluffy. This tool makes it easy to de-fur my sofa, ottoman, shoes, and any other surface that gets covered in their hair. I use it every single day. It doesn't fill up too quickly, and emptying it out takes all of three seconds. It works efficiently and doesn't take too many passes to de-fur my entire couch.
Litter Attractant for $12 : If your kitties are having litterbox issues, sprinkle a bit of this after cleaning out the cat box. It'll help them do their business in the designated spot. It's also helpful for after a move.
Find a good brush: We use the Pet Neat Grooming Brush that is no longer available. It's a good duper for the pricier Furminator.
But there are plenty of brush options anywhere they sell pet items.
Catnip Spray for $10 : Most cats love catnip. Ours have responded well to Pet Craft Supply Co's ($12) and Yeowww ($6) , but I really like this spray for days when I don't want to get flakes all over.
Cat Person toys: In addition to the Mesa Bowl we mention earlier, Cat Person makes other good products, like these cute catnip toys ($7).
Louryn's cats loved the wet food ($10) , and even though they're not wholly necessary, we're fana of these tiny spoons for scooping out gravy ($12).
Bonus: The packaging turns into cardboard cat houses.
Sprinkle & Sweep Messy Pet Accident Cleanup Aid ($25) : This powder makes cleanups slightly less disgusting (as long as they're puking on hard surfaces). You need a bit more than the package suggests, but once the mess is covered, you can sweep it up. The fragrance can be a little overwhelming, but it doesn't last, and it's certainly better than the smell of feline bodily fluids.
Fur Zapper ($12) : Unless your pet is hairless, their fur is likely everywhere all the time. The silicone Fur Zapper is naturally sticky, so hair clings to it in the laundry. Throw these in the washer and dryer, then just rinse 'em off and use them again.
Writer and Reviewer X Writer and Reviewer X Topics Shopping cats pets buying guides Adrienne So Adrienne So Brenda Stolyar Simon Hill Julian Chokkattu Eric Ravenscraft Jaina Grey Julian Chokkattu WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,094 | 2,023 |
"9 Best Carpet Cleaners (2023): Budget, Spot Cleaners, Hard Floors | WIRED"
|
"https://www.wired.com/gallery/best-carpet-cleaners"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Simon Hill Medea Giordano Gear The Best Carpet Cleaners to Resurrect Your Rugs Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Best Overall $279 at Amazon An Expensive Upgrade $499 at Amazon Best for Stubborn Stains $492 at Amazon Best Spot Cleaner $134 at Amazon Over time, tramping feet, molting pets, and spilled drinks can take a heavy toll on our hard-working carpets. That pristine pile loses its shine and bounce, fibers get tangled with hair, and stains settle in for the long haul. Surface crumbs and dust might get sucked up regularly by your vacuum, but there’s only so much it can do. For a deep clean that will wet-wash your rugs to lift ingrained dirt and lingering odors, you need a carpet cleaner.
We tested a range of carpet cleaners in busy households with aging carpets that have seen some serious action. These are our picks of the best carpet cleaners in different categories. You'll also find recommended mops and vacs for hard floors. And there's advice on what to consider when buying a carpet cleaner, and how to get the most out of it. For more cleaning recommendations, check out our other guides, like the Best Robot Vacuums , Best Cordless Vacuums , Best Handheld Vacuums , Best Dyson Vacuums , and Best Eco-Friendly Cleaning Products.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Updated August 2023: We added the Tineco Carpet One Pro, the Bissell Little Green Cleaner, and the Bissell Revolution HydroSteam. We also updated prices and links throughout.
Photograph: Bissell Best Overall Bissell ProHeat 2X Revolution Pet Pro This Bissell looks like a normal upright vacuum cleaner, but it packs plenty of carpet cleaning power. I was pleased with the results; my whole house felt renewed. It removed plenty of cat hair and eliminated lingering odors. It's easy to use, with the two removable tanks—fill the top tank to the marked lines with warm water and detergent, pull a trigger on the handle to wet wash, and then run over the area slowly and watch the bottom tank fill with dirty water. A special spray jet, triggered by a pedal, can target stains. There are three modes (Max, Deep, and Express) and lots of attachments. The upholstery attachment was very effective on an old armchair, and the stair-cleaning tool works well too. There’s even a handy tool for cleaning the cleaner when you’re done, though this is a fiddly job.
On the downside, the ProHeat 2X Revolution Pet Pro is very loud (like a jet taking off). Some older stains remained, even after multiple runs. A toothpaste stain on the upstairs landing initially disappeared but gradually returned, and an old red wine stain in the living room refused to budge. Also, it's maneuverable for a carpet cleaner, but it's still heavy to lift, and don't expect it to slide under low furniture. It needs storage space similar to an upright vacuum, and you only get a drawstring bag to store all the attachments.
A Steam Cleaner From Bissell: I never used a steam cleaner before, but was impressed by how well the Bissell Revolution HydroSteam Pet cleaned up forgotten stains on my rugs. It's big, about the size of the ProHeat, so you need somewhere to store it. It's priced at $400, but is often much cheaper.
$279 at Amazon $259 at Walmart Photograph: Tineco An Expensive Upgrade Tineco Carpet One Pro If a carpet cleaner can be said to be fun , the Tineco Carpet One Pro is. It's almost 30 pounds, but the clever design leaves the dirty water tank on the ground while the handle hinges back, so I (a small woman) found it fairly lightweight and easy to maneuver. Both the clean and dirty water tanks are easy to pop in and out and have carrying handles, so they're easy to rinse out.
A big LED screen (and voice) tells you whether you're toggling in between Auto, Max, or Drying modes. A few passes with Max lifted several years' worth of grime out of a white carpet that I had left criminally unattended. Drying mode blows 167-degree hot air at the carpet and shows you the percentage of dryness. It's not perfect, but I was able to clean my carpets before I left to pick my children up from camp, and the carpets were fluffy and fully playable when we came back three hours later. It also comes with a cleaning accessory for upholstery, extra cleaning solution, and tools to clean the tools. It also takes up the same amount of space as our Dyson Animal Ball vacuum. Overall it did an amazing job for the weight, but my husband did point out a stubborn small stain or two that it left behind. If you need a heavier-duty washer, read on.
—Adrienne So $499 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Rug Doctor Best for Stubborn Stains Rug Doctor Mighty Pro X3 When you absolutely, positively must clean every carpet in the house, accept no substitutes: The Rug Doctor Mighty Pro X3 is as good a clean as you’ll get without hiring professionals. I've rented this beast a few times, and it has never failed to impress, leaving carpets clean, fluffed up, and relatively dry. It has a huge water tank, so there’s less emptying and filling required. It’s also straightforward to use—you roll it forward and then pull back very slowly, pressing the red button to wet-wash and then going over the same line to suck up the dirty water. If you take your time and do overlapping lines, the results are the best we’ve seen, and the suction is strong enough to pick up clumps and leave the carpet relatively dry.
Spending $600 on a carpet cleaner won’t make sense for most people, but Rug Doctor offers rentals starting at $35 for 24 hours with this machine. The cons are similar to our top pick and true of most carpet cleaners. First, this heavy machine can be awkward to maneuver and tough to lift. It is very loud, so protect your ears. It has a relatively narrow cleaning line and is only effective if you go very slowly, so it can take a while to clean a whole room. This model doesn’t offer quick-clean modes or have any attachments in the box, though you can buy a Hand Tool ($100) separately. You will also need considerable storage space if you're not renting it.
$492 at Amazon $597 at Walmart Buy at Rug Doctor (Rent) Buy at Rug Doctor (Hire) Photograph: Amazon Best Spot Cleaner Bissell Pet Stain Eraser PowerBrush I don't always want to lug around a big carpet cleaner when my cats inevitably puke on the rug. Bissell's compact Pet Stain Eraser PowerBrush has been a lifesaver for this. It takes stains out of the carpet without much effort on your part, even ones that have been marinating for a day or two. It's cordless, so you can clean every spot in the house without being tethered to an outlet. (I've only had to charge it twice in four months.) I also really like that it's easy to clean; many of the pieces can be taken off and rinsed under a faucet. There's no pukey grime clogging up hoses like with other spot cleaners I've tried. It comes with two brushes—the Rotating DirtLifter is the standout for carpets, while the Stationary Pet Tool may work better on furniture.
$134 at Amazon $134 at Target Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Hoover A Budget Cleaner Hoover PowerDash Pet Compact Carpet Cleaner This Hoover PowerDash reminded me of a toy vacuum in the best way. It's light and easily maneuverable, which is a relief compared to a lot of bulky cleaners out there. You can usually find it for around $90 too. (Even at its full price of $120, it's cheaper than others we tried.) Like the others on this list, this one has a dirty-water tank at the bottom and a clean-water and solution tank at the top. Both are easy to remove and clean. The handle has a solution trigger, which was oddly satisfying to use, for accurately spraying stains first. You probably don't want to deep-clean an old, neglected house with this one, but for bedrooms, area rugs, or cleaning up pet messes or food spills, this should get stains out quickly. One thing I don't love about Hoovers is that the actual nozzle openings tend to be quite thin—I found this to be the case with the larger vacuum-style models and the spot cleaners I've tried. With any cleaner, you shouldn't expect it to pick up large chunks of … blown chunks (sorry), but I find even little pieces of hair or food got clogged in there.
$120 at Target $120 at Amazon Photograph: Bissell A Viral Favorite Bissell Little Green Portable Carpet Cleaner If you've landed on the cleaning side of TikTok , you've probably seen people cleaning their carpets and furniture with this Little Green machine.
This and the Pet Stain Eraser (also from Bissell) that we like opens up the world of upholstery cleaning too, not just carpets. It worked well and it's easier to store and tote around your house than our top pick. But use the included hose-cleaning tool frequently. These hoses can get nasty.
$123 at Amazon $99 at Walmart Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Shark Best for Hard Floors Shark S5003D Genius Steam Mop Some carpet cleaners, such as our top pick, can be used on certain hard floors, but I recommend going for a steam mop like this one instead. This Shark Steam Mop is great for cleaning hardwood, tiles, or laminate flooring (not carpets). Simply fill the water tank, plug it in, and attach one of the mop pads. It has three heat levels, and you press down to release a jet of steam for stubborn stains. There’s no need for any detergent, it’s light and maneuverable, and it doesn’t require much space. The clever pad design enables you to flip it over when one side is soiled, and the mechanism makes it easy to attach, with a button to detach the dirty pad, which is machine washable. (You get two pads in the box.) I regularly use this mop to clean laminate, composite, and tile floors, but you must be careful using steam, especially on wood or vinyl flooring. Test it on the lowest heat setting before going over the whole floor. There are no special attachments or extras here, and it’s only suitable for use on hard floors. You also need to empty any remaining water if you don’t plan on using it for a while, or the tank can go nasty.
★ An alternative : The Shark is great because it's affordable, but if your budget can stretch, the Karcher SC 3 ($230) is better if you want attachments and the option to steam-clean harder-to-reach surfaces and your hard floors. It’s good for complete kitchen or bathroom cleaning without the need for any detergent or other products. It's effective for cleaning glass and mirrors too. It only comes with one microfiber cover, and it’s not recommended for use on fabrics or carpets.
$130 at Home Depot $100 at Kohls Photograph: Proscenic Upgrade for Hard Floors Proscenic WashVac F20 If you don’t mind spending big to bring the gleam back to your hard floors, this cordless wet vacuum and mop makes light work of the job. Fill the rear container with water and Proscenic’s cleaning solution (you get a bottle that’s enough for 50 washes), and go to work on laminate, wood, tiles, or any other hard floor surface. (It does not do rugs.) The Proscenic F20 is light, easy to maneuver, and kinda pulls you along as the roller spins. A full charge proved enough to do all my hard floors twice over, and the result was shiny.
What I love about this vac is that it effectively cleans up dry or wet spills, so whether you are cleaning cat litter or a dropped bowl of cereal, it performs. It’s best for cleaning recent spills, but it can also shift stubborn stains with the Max mode and repeated passes. Even better, when you finish, you can stick it on the charging cradle and trigger the self-cleaning program, which sterilizes the soft roller and dries it (though it takes a long time). No one really wants to install an app or create an account just to use a vacuum, but it does make it easier to choose modes, and it displays a wealth of useless cleaning stats.
$399 at Proscenic Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Hoover Another Cleaner We Like Hoover SmartWash Automatic Carpet Cleaner Hoover's SmartWash Pet Carpet Cleaner is a bit more capable than the PowerDash for bigger messes. It's bulkier, but it has automatic cleaning and drying cycles—pushing it forward releases the solution and pulling it back starts the drying process. After you've gone over the whole area, you can turn just the drying mode on for an extra pass if the carpet needs it.
It also has some extras. The handle comes out with the click of a button, and you can use its separate tank with a cleaning solution to spot-treat before vacuuming. A hose and separate antimicrobial pet tool can clean stairs or any other hard-to-reach areas that need extra elbow grease. Some customer reviews say it worked well for a few months but then shorted out. We'll keep trying it to see if we run into that issue.
$250 at Amazon $199 at Walmart Photograph: BanksPhotos/Getty Images Things to Consider How to Choose and Use a Carpet Cleaner There is a lot to think about when shopping for or using a carpet cleaner, such as how much space you'll need for storage and whether you should rent or buy. Here are some tips to keep in mind.
Carpet cleaners are heavy and bulky , especially when filled with water. They can be harder to maneuver than regular upright vacuums. They will also need quite a bit of storage space.
Tackle stain-causing spills immediately.
Most households only need to wash carpets once every six months to a year, but spot cleaners are ideal for treating immediate spills, plus they're easier to store and use.
You likely won't use a carpet cleaner often , so it's OK to consider hiring professionals to do your whole home, especially if you have limited storage space. (It also can depend on how dirty and stained your carpets are.) Look at options for renting a machine from local businesses or retail stores like Home Depot. You'll be able to get the benefits of a commercial-grade cleaner without paying a fortune.
Clean your carpet before you use a carpet cleaner.
This may seem counterintuitive, but you don’t want dirt and hair to form wet clumps that block the cleaner. And if you haven’t washed your carpets in a while (or ever), be prepared for an embarrassing amount of hairy clogs to fill the dirty water tank.
The carpet shampoo or detergent you use is important.
Manufacturers often insist you use their brand, and while other types may work fine, you might void your warranty (although I have no idea how they'd know). Most carpet cleaners come with some detergent, but I had a good experience with Rug Doctor's Commercial Carpet Cleaner ($20).
It works well and does not have a strong scent, and you can buy a large jug for cheap.
Try, try, and try again.
It can be disappointing to fire up a carpet cleaner and find that it’s incapable of removing that old red wine stain or ground-in toothpaste. Don’t lose heart. Multiple cleaning sessions can sometimes chip away at established stains, and at least reduce, if not remove, them.
Drying your carpets can take a long time.
Most carpet cleaners have different settings, and they will suck up some of the water, but they all leave carpets a bit damp. The deeper cleans tend to leave carpets wet, so think about how you might speed drying time. Use fans, fire up the heating, or do your carpet cleaning in the spring and summer months when you can leave windows open.
Protect your hearing.
Of all the ways you can damage your hearing, a carpet cleaner is perhaps the least fun, so protect your ears. Some of these get very loud, so wear earplugs while you work.
Contributor X Writer and Reviewer X Topics Shopping buying guides cleaning How We Clean Scott Gilbertson Scott Gilbertson Boone Ashworth Carlton Reid Reece Rogers Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,095 | 2,013 |
"Review: Razer Blade 14-Inch | WIRED"
|
"https://www.wired.com/2013/07/rader-blade-14"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Christopher Null Gear Review: Razer Blade 14-Inch Facebook X Email Save Story Photo: Ariel Zambelich/Wired Facebook X Email Save Story $2,000 at Razer If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 9/10 Open rating explainer Why, why, why must gaming laptops be behemoths that can't even fit in a typical messenger bag, let alone under an airplane seat? All those fans, you say? Dual video cards? Triple hard drives? Ground effects? OK, fine, I get it. Gaming notebooks are typically enormous because they're really desktops writ small.
Balderdash! Razer's had enough of the excuses. Following on the qualified success of the 17.3-inch Razer Blade R2 comes this pint-sized powerhouse – a near-ultrabook version of the same concept, a true gaming PC in a case that measures just 20mm thick.
Naturally, some accommodations have had to be made to squeeze 6.7 pounds of computer into the 4.2-pound Razer Blade 14-inch package. The screen is not just smaller but lower in resolution (1600 x 900 pixels), and the old hybrid hard drive has been jettisoned for a straight (and faster) 256GB SSD. The most visible change is driven by necessity: The programmable keypad and secondary Switchblade LCD/touchpad/thingy are of course gone, too.
On the other hand, other components have been upgraded. The third-generation Core i7 is now a fourth-generation "Haswell" version, running at 2.2GHz. And the graphics card has been upgraded one generation, too, to an Nvidia GeForce GTX 765M model. 8GB of RAM is still standard, and ports are kept to the basics: three USB 3.0 ports and an HDMI connector.
So, what's not to like? I mean that literally. The machine is faster all around – about 30 percent faster than the R2 on most benchmarks and close to double the framerate on some graphics tests and gaming runs. The screen is fantastically bright – one of the brightest in its class and far better-looking than the R2's. Even the battery life is fantastic. For any ultrabook to top five hours of running time on full-tilt video playback is impressive. For a gaming version of same to do so is almost unthinkable. On the whole, it's difficult to find much in the way of fault here unless you want to lay into the nitpicks (the screen resolution could be better, after all).
I don't need to heap on the praise for this machine. It does everything it's designed to do and more. No hiccups or driver issues (a popular complaint with past Razer machines), no weird fit and finish problems. Yeah, it's a $1,999 laptop, but that's a dollar cheaper than Toshiba's far less interesting KIRABook, which didn't even have fancy green keyboard backlights. Come on! WIRED Record-setting performance on all fronts – including battery life. Impressive portability, particularly for a gaming rig. Looks good, especially if you like snake symbology.
TIRED A bit slow to boot. Pricey. No touchscreen. Still no SD card reader.
Razer Blade 14-Inch Rating: 9/10 $2,000 at Razer If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $2,000 at Razer Topics laptops Razer video games Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,096 | 2,022 |
"Emotional AI Is No Substitute for Empathy | WIRED"
|
"https://www.wired.com/story/artificial-intelligence-empathy"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Pragya Agarwal Ideas Emotional AI Is No Substitute for Empathy Illustration: Scott Balmer Save this story Save Save this story Save In 2023, emotional AI —technology that can sense and interact with human emotions—will become one of the dominant applications of machine learning. For instance, Hume AI, founded by Alan Cowen, a former Google researcher, is developing tools to measure emotions from verbal, facial, and vocal expressions. Swedish company Smart Eyes recently acquired Affectiva, the MIT Media Lab spinoff that developed the SoundNet neural network, an algorithm that classifies emotions such as anger from audio samples in less than 1.2 seconds. Even the video platform Zoom is introducing Zoom IQ, a feature that will soon provide users with real-time analysis of emotions and engagement during a virtual meeting.
This story is from the WIRED World in 2023 , our annual trends briefing. Read more stories from the series here —or download or order a copy of the magazine.
In 2023, tech companies will be releasing advanced chatbots that can closely mimic human emotions to create more empathetic connections with users across banking, education, and health care. Microsoft’s chatbot Xiaoice is already successful in China, with average users reported to have conversed with “her” more than 60 times in a month. It also passed the Turing test, with the users failing to recognize it as a bot for 10 minutes. Analysis from Juniper Research Consultancy shows that chatbot interactions in health care will rise by almost 167 percent from 2018, to reach 2.8 billion annual interactions in 2023. This will free up medical staff time and potentially save around $3.7 billion for health care systems around the world.
In 2023, emotional AI will also become common in schools. In Hong Kong, some secondary schools already use an artificial intelligence program, developed by Find Solutions AI, that measures micro-movements of muscles on the students’ faces and identifies a range of negative and positive emotions. Teachers are using this system to track emotional changes in students, as well as their motivation and focus, enabling them to make early interventions if a pupil is losing interest.
The problem is that the majority of emotional AI is based on flawed science. Emotional AI algorithms, even when trained on large and diverse data sets, reduce facial and tonal expressions to an emotion without considering the social and cultural context of the person and the situation. While, for instance, algorithms can recognize and report that a person is crying, it is not always possible to accurately deduce the reason and meaning behind the tears. Similarly, a scowling face doesn’t necessarily imply an angry person, but that’s the conclusion an algorithm will likely reach. Why? We all adapt our emotional displays according to our social and cultural norms, so that our expressions are not always a true reflection of our inner states. Often people do “emotion work” to disguise their real emotions, and how they express their emotions is likely to be a learned response, rather than a spontaneous expression. For example, women often modify their emotions more than men, especially the ones that have negative values ascribed to them such as anger, because they are expected to.
As such, AI technologies that make assumptions about emotional states will likely exacerbate gender and racial inequalities in our society. For example, a 2019 UNESCO report showed the harmful impact of the gendering of AI technologies, with “feminine” voice-assistant systems designed according to stereotypes of emotional passiveness and servitude.
Facial recognition AI can also perpetuate racial inequalities. Analysis from 400 NBA games with two popular emotion-recognition software programs, Face and Microsoft’s Face API, were shown to assign more negative emotions on average to Black players, even when they were smiling. These results reaffirm other research showing that Black men have to project more positive emotions in the workplace, because they are stereotyped as aggressive and threatening.
Emotional AI technologies will become more pervasive in 2023, but if left unchallenged and unexamined, they will reinforce systemic racial and gender biases, replicate and strengthen the inequalities in the world, and further disadvantage those who are already marginalized.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Topics artificial intelligence algorithms The WIRED World in 2023 Meghan O'Gieblyn Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,097 | 2,023 |
"How AI Can Make Gaming Better for All Players | WIRED"
|
"https://www.wired.com/story/ai-make-gaming-better-accessibility"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter By Geoffrey Bunting Business How AI Can Make Gaming Better for All Players Video: Lauryn Hill; Getty Images Save this story Save Save this story Save Application Games Technology Machine learning Natural language processing When Google revealed Project Gameface, the company was proud to show off a hands-free, AI-powered gaming mouse that, according to its announcement , “enables people to control a computer’s cursor using their head movement and facial gestures.” While this may not be the first AI-based gaming tool, it was certainly one of the first to put AI in the hands of players, rather than developers.
The project was inspired by Lance Carr , a quadriplegic video game streamer who utilizes a head-tracking mouse as part of his gaming setup. After his existing hardware was lost in a fire, Google stepped in to create an open source, highly configurable, low-cost alternative to expensive replacement hardware, powered by machine learning. While AI’s broader existence is proving divisive, we set out to discover whether AI, when used for good, could be the future of gaming accessibility.
It’s important to define AI, and machine learning , to understand clearly how they work in Gameface. When we use the terms “AI” and “machine learning,” we’re referring to both the same and different things.
“AI is a concept,” Laurence Moroney, AI advocacy lead at Google and one of the minds behind Gameface, tells WIRED. “Machine learning is a technique you use to implement that concept.” Machine learning, then, fits under the umbrella of AI, along with implementations like large language models. But where familiar applications like OpenAI’s ChatGPT and StabilityAI’s Stable Diffusion are iterative, machine learning is characterized by learning and adapting without instruction, drawing inferences from readable patterns.
Moroney explains how this is applied to Gameface in a series of machine learning models. “The first was to be able to detect where a face is in an image,” he says. “The second was, once you had an image of a face, to be able to understand where obvious points (eyes, nose, ears, etc.) are.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg After this, another model can map and decipher gestures from those points, assigning them to mouse inputs.
It’s an explicitly assistive implementation of AI, as opposed to those often touted as making human input redundant. Indeed, this is how Moroney suggests AI is best applied, to broaden “our capacity to do things that weren’t previously feasible.” This sentiment extends beyond Gameface’s potential to make gaming more accessible. AI, Moroney suggests, can have a major impact on accessibility for players, but also on the way developers create accessibility solutions.
“Anything that lets developers be orders of magnitude more effective at solving classes of problems that were previously infeasible,” he says, “can only be beneficial in the accessibility, or any other, space.” This is something developers are already beginning to understand. Artem Koblov, creative director of Perelesoq , tells WIRED that he wants to see “more resources directed toward solving routine tasks, rather than creative invention.” Doing so allows AI to aid in time-consuming technical processes. With the right applications, AI could create a leaner, more permissive, development cycle in which it both helps in the mechanical implementation of accessibility solutions and leaves developers more time to consider them.
“As a developer, you want to have as many tools that can help you make your job easier,” says Conor Bradley, creative director of Soft Leaf Studios.
He points to gains in current implementations of AI in accessibility, including “real-time text-to-speech and speech-to-text generation, and speech and image recognition.” And he sees potential for future developments. “In time, I can see more and more games making use of these powerful AI tools to make our games more accessible.” Koblov believes it can go even further. He’d like to see AI training on specific patterns to create a basic, adaptable accessibility framework that could be injected into games. “Such framework would adapt the visual, audio, and interactive aspects of games,” he says. “In other words, smaller developers like us wouldn’t have to conduct expensive research, develop unique solutions, and go through numerous iterations of testing on their own.” Bradley urges caution when pulling primacy away from human input. Asked whether AI could prove an aid or a distraction to existing accessibility efforts, he said he was optimistic about its potential, but stressed that AI is not a shortcut.
“You cannot say, ‘AI, make my game accessible!’ and hey presto, you now have the most accessible game of the year,” he says. “We need players, including those from disabled and neurodiverse communities, to test our games. At the end of the day, a human will be playing your game, not a machine.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg While Koblov believes AI could be valuable for implementing and testing accessibility features, he acknowledges that thinking about AI requires “an ‘addition’ mindset,” rather than a “replacement” approach.
But conflating the generative, content-driven tools that spark fears of human redundancy with the kind of AI implementations that help accessibility is, according to Moroney, “Really dangerous.” He continues, “If we’re going to be the adults in the room when it comes to AI, we have to recognize hype and bandwagons.” This makes clarity and transparency about AI’s capabilities all the more important, especially in its relation to accessibility. It’s not a magic wand. “AI and machine learning were doing well until the recent releases,” Moroney says. “Now they’ve fallen back in the hype cycle.” AI can be an excellent tool for developers, but they must remain dedicated to accessibility throughout the process, whether AI is present or not. After all, as Bradley says, “At the end of the day, it still is up to the developers to want to make their games accessible by design.” AI’s gradual progress is evident in Gameface. But another project demonstrates how AI-assisted accessibility can be implemented on a wider level.
Minecraft Access is a mod that seeks to make Minecraft accessible to blind and visually impaired players. Logic, part of the team behind the mod, tells WIRED how a suite of AI tools, including ChatGPT and Google’s own Tensor Flow, are helping with the project.
“We are hoping AI can fill in … visual context for blind and low-vision players by providing information about the world as it is needed or upon request,” Logic says.
Particularly exciting is the potential for AI to not just bolster accessibility, but actively learn what a player needs. This will prove especially useful for broader applications in accessibility, given the layers of spectrums that make up disability and how personalized each player’s needs are.
We do need to rein in our expectations, however. As promising as these recent implementations have proven, and as instructive as they may be for the future, there remain significant barriers to entry. In its current stage of development, Minecraft Access requires multiple programs to function, something Logic acknowledges makes it less accessible than it could be.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “The average user is not going to want to collect a bunch of programs from different parts of the web,” Logic says.
Similarly, Ben Green, a disabled gamer, finds Gameface’s potential exciting but worries about diversity in the data. It may be able to “recognize lots of faces,” he says. “But some people with facial differences, like a ventilator in my case, or asymmetrical facial features, might be barely represented, or not at all.” When asked about this, Miguel de Andrés-Clavera, who leads the team that developed Project Gameface, says, “We decided to create a functionality for people to customize which expressions they used to control the mouse.” This includes the ability to customize the intensity of gestures for different needs. He goes on, “With that being said, we are always looking for ways to increase the accessibility of our technology for more people. Our hope is that over time, Project Gameface will continue to improve and become even more helpful.” Even with these caveats, it’s interesting to see how hopeful people are about AI’s role in accessibility. Once we can distinguish between unethical applications of content-driven generative AI and meaningful AI tools and implementations that can help people solve problems and benefit others, there’s plenty of cause for optimism—with the understanding that AI’s true value is tied to our ability to make it work for us.
The future of AI is ambiguous, but it holds the potential to benefit individual gamers and the industry at large. Its use requires caution, and we can expect pitfalls, but there’s every reason to believe that careful implementation of AI can contribute to a gaming landscape that encompasses a wider spectrum of players.
That’s the world Moroney wants to live in: “a world where people like Lance aren’t confined because solutions are technically infeasible, but rather one where developers have such superpowers that building solutions to allow him to connect to the world is easy.” You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Contributor X Topics artificial intelligence video games gaming culture accessibility developers WIRED30 Nelson C.J.
Peter Guest Andy Greenberg Steven Levy Will Knight Joel Khalili Kari McMahon David Gilbert Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,098 | 2,023 |
"15 Best Laptop Totes and Purses (2023): Sustainable, Weather-Proof, Durable | WIRED"
|
"https://www.wired.com/gallery/best-laptop-totes-and-purses"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Medea Giordano Gear The Best Laptop Totes for Work and Weekends Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED The Best Traditional Tote $110 at B&H Photo A Runner-Up Tote $129 at Bellroy The Best Purse $348 at Cuyana (16-inch) A Runner-Up Purse $198 at Cuyana Now more than ever, people work hybrid jobs that take them from home to the office to the corner coffee shop. Even if you work from home permanently, you'll occasionally need to go out into the world and bring your junk with you. A backpack will do the trick, but some of us want bags that look as nice as our outfits. That's where a good work tote or purse comes in.
Whatever your needs or style, we have an option you should like. These totes aren't the thin, pocketless bags we all seem to accumulate. We tried bags that make organization easy and can stand up to the elements and the normal amount of wear and tear that life brings.
If you prefer a backpack or a messenger bag , we have guides for those too, as well as a roundup of all our favorite types of bags made from recycled materials.
Updated August 2023: We've added Baggu's Duck Bag and Verloop's Scrapped Stuffed Tote as picks. We've also added the Lojel Niru Tote to the honorable mentions.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Photograph: Moment The Best Traditional Tote Moment MTW Tote Moment's Tote is WIRED writer Jaina Grey's favorite.
She says it distributes weight like magic, no matter how much junk is shoved inside, so it won't give you shoulder pain as you go about your day.
This bag has pockets within pockets, next to pockets. Your 16-inch laptop, Kindle, water bottles (yes, plural), and cables all have a place. And because it comes from a photography brand, it's made to protect all your expensive gear with padding, weatherproof recycled nylon, and a full-zip closure. It also holds Moment's camera insert for even more organization and protection.
$110 at B&H Photo $120 at Moment Photograph: Bellroy A Runner-Up Tote Bellroy Tokyo Tote The Bellroy Tokyo Tote is a solid runner-up to Moment's. There are pockets all the way around the perimeter of the inside to help you stay as organized as can be. On one side, a soft sleeve cradles a 13-inch laptop, on the other, two 5-inch pockets can hold a phone, wallet, cables, or a small notebook. Larger “pop” pockets on either end can extend to hold a water bottle, umbrella, or shoes and then push back against the bag when you don't need them. I was even able to fit a tall water bottle with a straw, though I needed to do a little finagling to get the zipper over it.
The water-resistant Tokyo Tote is made of recycled plastic bottles , and its straps have a nice rubbery grip to keep it on your shoulders.
$129 at Bellroy Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Cuyana The Best Purse Cuyana System Tote A nice bag is an investment you can make, instead of accumulating a bunch of cheapies. The Cuyana System Tote is beautiful, with a design that should outlast trends. It gets its name for the add-ons that work as an efficient system for your needs, taking you from work to dinner to weekends away. But you have to pay a premium for those, even the laptop sleeve ($98).
The organizational insert ($98) has a pocket for your laptop and water bottle. However, the bag itself isn't padded. It also snaps closed in the middle, but there isn't a zipper.
Purses sometimes suffer at the point where the strap meets the rest of the bag—the more you stuff into it, the more weight those straps hold, and flimsy threads can unravel. With this bag, the straps are integrated into the leather. There is, of course, stitching elsewhere, but I threw this bag around while it was filled to the brim and it held up.
★ More accessories: You can add a flap bag ($128) that works as a clutch when that's all you need, or as an inner compartment to hold essentials. An adjustable strap ($58) makes the clutch or the entire purse a cross-body bag. We recommend getting the laptop sleeve first and the others later if you need them.
$348 at Cuyana (16-inch) $98 at Cuyana (Laptop Sleeve) Photograph: Cuyana A Runner-Up Purse Cuyana Oversized Recycled Sling Bag I loved Cuyana's System Tote so much, I tried its Oversized Sling made from recycled plastic. It zips fully closed and is a little more casual, but it fits a ton —I brought it on a plane and shoved in everything I couldn't fit in my suitcase, including a deflated pool floaty and a high heel (the other was shoved in a different bag). For more organization, you can add Cuyana's tote insert if you want to, but it carried a laptop just fine without it.
You can get the medium or small size, but we think the oversized is probably best for work and commuting comfortably. It's machine washable too, as long as you use a mesh bag.
$198 at Cuyana Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Baggu A Cute and Capable Tote Baggu Duck Bag WIRED reviewer Brenda Stolyar loves her Baggu duck bag. She had been looking for a lightweight bag that was comfortable to wear with a coat (tote straps tend to annoyingly slide off jacket sleeves). Her boyfriend gifted her the embroidered floral version and it's been the only bag she's worn since.
An adjustable strap makes it easy to switch between carrying it as a crossbody or a traditional tote. Both ways are comfortable, whether you're bundled up in a coat or not, plus you can hold it from the top handles too and leave your shoulder free. She regularly loads it with a 15-inch MacBook Air, a change of clothes, and a book. The smaller, inner pocket holds her wallet, chapstick, and keys. It's roomy, comfortable, and effortlessly cute, plus the recycled cotton canvas is machine-washable.
$38 at Amazon $38 at Baggu $46 at Baggu (Zip bag) Photograph: FJÄLLRÄVEN A Tote Backpack Combo Fjallraven Kånken Totepack We love the Kanken backpack.
The Totepack is essentially the same bag, but with extra straps so you can wear it on your shoulder or your back. It's nice to be able to effortlessly switch back and forth, like when you get on a crowded subway and don't want to knock people over, or when you've packed it full of groceries on the way home and one shoulder holding the weight won't cut it anymore.
Like on the backpack, there's a pocket for a 13-inch laptop, a smaller one to fit a tablet, notebook, or Kindle, plus a large main compartment for everything else. There are two side pockets on the outside for water bottles or a small umbrella—but they're tight, so don't expect to fit a large bottle in there. The rigid fabric should repel water if you get caught in a rain shower, and the company offers limited lifetime repairs.
It comes with a thin foam seat pad that adds protection to the laptop pocket but also works as a cushion in a pinch if you need to sit on an uncomfortable surface.
$100 at Fjallraven $100 at REI Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Newhey The Best Budget Laptop Purse Newhey Laptop Tote Bag If you're in school or newly entering the workforce, spending over $100 on a bag is hard to stomach—it's still hard for me. We tried three inexpensive, highly rated bags from Amazon, and this Newhey was the best. The inside is well organized, with two pen slots and side pouches for a phone or wallet. A large zipper pocket runs down the middle of the bag, and a padded laptop sleeve is secured with a Velcro strap.
There's a lot of room inside, but it's thin when it isn't stuffed full, so it feels nice and comfortable under your arm. The outside is a soft faux leather, made of polyurethane, with adjustable handles and a removable strap for slinging it across your body if you need to. However, I could see a clear difference in quality when it came to the stitching and materials. I don't see this bag lasting forever, but if you treat it well, it should be OK for a while.
★ Another budget bag: We also tried and liked the Lovevook Laptop Tote ($37).
The interior is nearly identical to the Newhey, and it has a pretty V-shaped pocket on the outside, like the Lux and Nyx bag below. The faux leather is stiffer, but it's hard to say if that makes it more durable long-term or if its structure is more prone to cracks.
$28 at Amazon Photograph: L.L. Bean A Budget Tote L.L. Bean Hunter's Tote Bag Cheap purses have flimsy faux leather and fragile straps, but an affordable tote is much easier to find. Gear editor Michael Calore loves this bag and says he uses it for everything. Really! He takes it on quick grocery runs or farmer's market trips, camping, and beach days, as well as on flights. We think it could be useful for work too, though it doesn't have a laptop sleeve, so you might consider getting a case to put your computer inside.
Like most of L.L. Bean's merchandise, its rugged construction is designed for long, wet mornings spent trudging through the New England muck. All of the seams are double-stitched, the thick polyester shell is reinforced with a second layer of material along the bottom, and the handles are beefier than an Aberdeen Angus, as Calore says. The lining is a rubbery plastic. While it isn't leakproof, the tote can haul frozen foods or snowy boots, and it wipes clean with a paper towel. It has a removable strap and comes in medium, large, or extra-large—Calore uses the extra-large. He says it holds a week's worth of veggies, plus a couple of half-gallon cartons of oat milk and a 12-pack of hard kombucha. It's also available as an open-top tote, but get the zip-top version.
$60 at L.L. Bean (XL) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: United By Blue A Recycled Convertible Bag United by Blue Convertible Carryall Like the Kanken, this bag can be used as a tote or a backpack, but it's not as compact. It has more padding and protection, plus it's made of recycled polyester and nylon and has a limited lifetime guarantee.
The padded laptop sleeve is big enough that you can keep your laptop in a case if you want, but you don't need one. It has organizational pouches inside the front zippered pocket for a phone, wallet, or pens that you need to access quickly. Two side pockets hold water bottles in place, and expandable elastic straps can hold bigger bottles or keep smaller bottles tightly secured. Unzip the back compartment to reveal the hidden backpack straps. Just take them out and clip them onto the sturdy D-rings. When you're ready to switch back, unclip and hide them away.
$118 at United By Blue Photograph: Longchamp A Sustainable Cult Tote Longchamp Le Pliage Green Shoulder Bag When I first got to college in 2012, every cool girl in a sleek outfit had a black and brown bag under her arm. (Even Meghan Markle and Kate Middleton have them!) It was the original Longchamp Le Pliage.
I've finally tried a Le Pliage of my own, but this one is made of recycled polyamide canvas , which is constructed from old fishing nets and carpets.
What makes the bag so popular among students and professionals alike is its durable, weatherproof fabric. Rain, snow, or spilled coffee won't ruin your belongings, and you'll look nice too. It also zips fully closed. If you're traveling and want to take this as your backup purse, not only is it incredibly thin as it is, but you can fold it up and snap it closed to about 10 inches by 6 inches, plus the straps. On the minus side, it doesn't have a dedicated laptop sleeve, so you'll have to buy your own.
$155 at Nordstrom $155 at Longchamp Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Verloop Recycled Yarn-Stuffed Bag Verloop Scrap Stuffed Tote Verloop's mini tote is one of my favorites when I don't need to carry much. This is a slightly bigger option from the brand, and it's made from paper-thin nylon stuffed with scrap yarn. The result is a cool, colorful explosion reminiscent of the ’90s. I haven't seen anything like it. There is a matching pouch too that you can use in whatever other bag you prefer.
It won't fit your laptop but you could put a tablet or a Kindle in here. The biggest issue is just how loud the nylon is when you touch it. It's like walking with a chip bag.
$68 at Verloop Photograph: Chrome Industries Durable AF Chrome Industries Barrage Tote Chrome bags are known for their durability, which is why we already like the company's backpacks and messenger bags. The Barrage tote is just as strong, “built twice” with a welded, waterproof liner and a tough nylon shell. There are two internal sleeves that fit a 13-inch laptop. They aren't padded, but you can squeeze a case over your laptop if its paper-thin. There's a key clip inside, too, and two external water bottle pockets.
A cargo netting front can expand and contract to fit whatever you need in there—a bike helmet, a small bag of groceries, shoes. Hidden behind the netting is a zip pocket, and there's also a zip pocket on the back that runs the entire length of the bag. If the bag is packed full and heavy, you can sling it on your back while a removable stabilizer strap goes across your chest.
$100 at Chrome Industries $85 at Backcountry Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Mission Workshop If You Need a Pocket for Everything Mission Workshop The Drift Laptop Tote Try to count the pockets on this bag. I'll wait.
This is another of editor Michael Calore's favorites. He says it feels designed especially for people who always carry an army of gadgets with them. There are two zippers along the top of the Drift; one for the 28-liter main compartment, the other for a padded laptop pocket that fits a 16-inch PC. The front of the bag has a smaller zip-up slot for a Kindle or iPad, plus an exterior compartment with several pockets for cables, pens, chargers, notebooks, and other smaller stashables. A dedicated phone pocket on the side of the tote is lined with a fuzzy non-abrasive fabric that won't scratch your screen. The other side has a slot for a water bottle. (It fits a slim Klean Kanteen, but not a chubbier Nalgene.) But it's kind of a beast, Calore notes. If you're traveling with it, it won't fit under your airplane seat if it's fully loaded, though you can stash it in the overhead compartment. When traveling by car, train, or bus, you'll be good, and a grippy coating on the bottom keeps it from sliding around. Also, Mission Workshop's bags are made in the US and come with a lifetime warranty, which makes their higher prices easier to swallow.
$345 at Mission Workshop Photograph: Lux and Nyx A Gorgeous Weekender Lux and Nyx Origami Large This bag is stunning, with a design that can go from work and the gym to dinner or the airport. It's one of my favorite bags that I tested, but it has a downside: It's made of neoprene. While the fabric stands up to water, it's made from petroleum and doesn't biodegrade.
The company makes up for some of that by adding straps made of upcycled leather coming from shoes and bags, but it's still something to keep in mind.
There's a padded laptop sleeve, two interior side pockets that can hold mini-umbrellas or even a flat shoe, a small zip pocket hidden inside the exterior V-shape sleeve that holds a phone, and a luggage passthrough on the other side. You can pack this full of a weekend's worth of stuff, thanks to its expandable edges, and it comes with a removable crossbody strap.
$288 at Lux and Nyx Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Stuart and Lau If You Prefer Briefcases Stuart & Lau Cary Briefcase I think a tote or backpack is a more modern choice. However, Stuart and Lau's Cary is very versatile. It's made from twill but has leather accents, so it looks nice but not pretentious. The organizational details are also thoughtful—the internal laptop case pops in and out, which is genius. The bag also has two small additional pockets. On the opposite side is a sleeve, plus four pockets and two pen slots. The exterior hosts five additional open slots, a small zippered one, and loops to hold an umbrella.
Plus, it's waterproof to protect your electronics while commuting. It even comes with a reusable shopping bag.
★ Alternative: Stuart and Lau's Campaign Briefpack ($385) converts from a super organized briefcase to a backpack. With both options, you can tell the brand put thought into the construction of its hardware and leather accents. Unfortunately, they're both expensive.
$375 at Stuart and Lau Photograph: Madewell Even More Totes We Like Honorable Mentions Lojel Niru 3-Way Tote for $55 : Lojel has a few nice bags made of recycled nylon. This tote has become my go-to pool bag, with its big open space and a zipper compartment for holding my card. Lojel's three modes of carry include holding it by the handles or the strap. Technically, the third is that you can roll it up when you aren't using it. I like the convenience, but I wouldn't call it a method of carrying it.
Troubadour Featherweight Tote for $195 : The Troubadour Tote looks nice but isn't trendy–which means it will last you a while and go with whatever you're wearing. It's not overly feminine if that's a concern for you. It snaps closed like a traditional tote bag, so your stuff is not completely protected from the outside world, whether that's rain or sneaky hands on the subway. There's a laptop sleeve secured with a snap, zippered and elastic internal pockets, plus side snaps to slim it down when you can. There's also a small clip to hook onto a wallet or keys.
Incase ARC Tech Tote for $90 : I like how compact this bag is, without losing its ability to keep your life together. It's made of weather-proof, recycled polyester. A faux-fur-lined pocket secures a 13-inch laptop, and there are organizational slots for a pen or two, a phone, a wallet or small headphones, plus a water bottle. The front zipper pocket is big enough to fit a Kindle or tablet, plus it has organizational slots of its own. It has small handles, though, so you'll probably get more use out of the adjustable (and removable) strap.
We liked the backpack version of this bag, and like that one, it has a separate zipper pocket inside that blocks radio frequency identification. It's a nice addition, but not necessary.
Writer and Reviewer X Topics Shopping Bags laptops buying guides Nena Farrell Julian Chokkattu Adrienne So Scott Gilbertson Scott Gilbertson Brenda Stolyar Nena Farrell Scott Gilbertson WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,099 | 2,020 |
"13 YouTube Channels We Geek Out Over in Quarantine | WIRED"
|
"https://www.wired.com/story/our-favorite-youtube-channels"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Matt Jancer Gear 13 YouTube Channels We Geek Out Over Save this story Save Save this story Save Sheltering in place for several months has led me to explore the vast caverns of YouTube to find entertaining videos to watch—after all, it feels like I've exhausted all my movie and TV options on Netflix, Hulu, and all the other streaming platforms. In my YouTube searches, I've come across a few real gems.
Some of these YouTube channels revolve around hobbies that I love, where I can put their tips and knowledge into practice. Others not so much, but they still make some riveting content. These are my favorite YouTube channels that hone in on one particular area of expertise. Happy streaming! Gardening is a deep rabbit hole and it's easy to, well, get lost in the weeds when you're trying to figure out how to keep alive a bunch of complicated organic machines that need exacting levels of sunlight, soil nutrients, watering, and space. Mohit Kumar Singh Rajput has two decades of experience in gardening, and he explains all the nitty-gritty details in videos that usually run under 10 minutes.
Unlike a lot of YouTube gardening hosts, most of his advice doesn't revolve around having an enormous backyard and a wheelbarrow full of power tools. You can put all his advice into practice whether you live in an apartment or a detached house, like how to grow plants in kitchen waste , how to grow new plants from cuttings of other ones , and how to grow vegetables in pots indoors. My favorite is a primer on growing a corn plant in a container.
Photograph: Simone Giertz Remember when she built the Truckla , a production-looking custom Tesla pickup? Giertz has made a lot of whimsical inventions, like a drone that carries babies and a lipstick-applying robot that made Stephen Colbert pretty when she was a guest on The Late Show.
WIRED's interview wizard Lauren Goode hung out with Giertz throughout the summer of 2019, which is how we learned that Truckla became a turning point for Giertz as an inventor. Look for her creations to become more grand and ambitious as she's committed to pushing her limits.
Car boots. Home safes. Bike locks. Padlocks. Nothing seems to stop this guy. He won't reveal his identity, but he claims to be a lawyer from the Washington, DC, area who picked up lockpicking as a hobby. In his videos, he picks open both common and strange locks, from modern ones to the antique kind, and explains how different locks attempt to foil lockpickers (and why almost all of them can be beaten). Sometimes he uses a prop, such as a magnet, a pair of open-ended wrenches, or a Red Bull can. Once he used a Lego astronaut.
He doesn't water down his words with niceties when the locks are trash, such as in an AmazonBasics bike lock review titled " As Bad As You'd Think " and a Brinks cable lock review titled " A Security Joke ". The takeaway here is that basically all locks are bad if a knowledgeable lockpicker wants your stuff. Some are just crappier than others.
Right now is the best time in history for a guitar player who's into effects pedals. Everyone's making a million varieties and doing some really out-there stuff with them that wasn't possible when we were all kids. For all the juicy tones and valuable guitar gear information, this YouTube channel from Dan Steinhardt, head honcho of pedalboard component maker The GigRig, and Mick Taylor, former editor in chief of Guitarist magazine, really clicks as the duo play off each other so well. I've been an off-and-on guitar player for 18 years, and I learn new things about pedal effects on this channel all the time. Not just how they sound but why they sound like they do.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So So why does a fuzz box sound so different from an overdrive pedal and a distortion pedal (ignoring the vague distinction between the latter two, for the moment)? That Pedal Show will talk about how their wavelengths clip differently from each other, which affects the sound you hear through the amp speaker. Not to mention the amusing demonstrations of things like phasers versus flangers and reviews of rare, new handmade pedals. What's that, you say? You've never bothered with all these pedal effects, and you're more of a straight-into-the-amp kind of player? That was me until I dove into this channel. Steinhardt and Taylor's chemistry makes their show just as much entertainment as it is useful information.
Michelle Gooris is my favorite airline pilot channel on YouTube because she doesn't hide the fact that piloting an airliner is one of the most difficult jobs on earth. Watching her videos, you never lose the sense that an extraordinarily complicated machine requires a mental decathlon of skills to land, fly, taxi, and maintain. Gooris explains how piloting is done and pairs it with video footage that lets the audience peek into the blades of a jet turbine engine, or follow along with her engine startup sequence in the cockpit.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Each video tears into a specific subject to explain in-depth how it works, such as how tailwinds affect the angle of approach on a short, difficult runway and what all that jargon means when pilots are talking to air traffic controllers as they depart and approach airports. You have to watch to find out her answer to the age-old rivalry of which is better to fly: Boeing or Airbus.
There seem to be a million YouTubers unboxing the latest and greatest consumer tech, but if you ask me, it's the older hardware that's more interesting. The 8-Bit Guy is devoted to '80s and '90s—and sometimes early 2000s—tech that got left behind, long before anyone thought those early machines would be worth preserving. Folks like the 8-Bit Guy help show us rare old tech, like digital cameras that used full-size floppy disks. His videos show him unboxing rare, old computers and the occasional robot, taking apart and refurbishing old Bell & Howell and Compaq PCs, plus breaking down how vintage videogame controllers worked. Want to find out what telephone phreaking was? Head over to his channel.
Gene Nagata has been a professional videographer for more than a decade, but it's the cheaper equipment that seems to get him the most excited. Like he often says, you don't need premium-priced gear anymore to shoot good footage. Filmmaking and vlogging are more democratic these days than ever. But his best videos tend toward the extremes, from enormous professional cameras that could be used as battering rams on a castle to handheld gimbals for making movies with an iPhone. And then there are the peeks into the industry, such as how Hollywood films car chases. He's a relaxed natural in front of the camera, and you can tell he's always having a good time. It's infectious.
A part of Serious Eats' channel , the Food Lab's Katie Quinn and J. Kenji Alt-López take a scientific approach toward cooking methods, such as whether searing a steak actually locks in its juices. And then there are how-to videos for kitchen equipment, including how to sharpen a kitchen knife on a whetstone, a skill that trips up a lot of home chefs if they even know that it's a part of regular maintenance. Plus, you get a few of their favorite recipes to break things up once in a while. Why did it take this long for someone to invent a Nutella-and-brie grilled cheese? You'd think people would take better care of fancy, old paintings, but a lot of them arrive to new collectors in rough shape. Paint degrades under sunlight and artificial light, and throughout the centuries, misguided cheapos have paid for subpar restorations that only further ruin good art. But it can often be salvaged if the person knows how to remove degraded layers of paint and seamlessly touch up other areas so that it blends in naturally with the rest of the painting. Baumgartner Restoration shows a wide variety of methods on healing wooden split-panels, torn canvas, and masterpieces from the old masters.
Odds are you'll never make Polynesian arrowroot flour or build a round hut in the forest, but it's fascinating to watch what people can make out of a little more than dirt, water, and their own two hands. Everything in these videos is created from natural materials, and the creator is self-taught. The videos are shot in Far North Queensland, Australia, and although he doesn't live in the wild, by now he's got a cool collection of rather large huts of various designs, primitive agricultural fields, stoves, and kilns.
There's something so revealing about a walk through a big city. In these videos, there are no cuts, no dialog, and no voiceover. It's just a steady-cam walking down the streets and sidewalks of Mexico City, Buenos Aires, New York, London, Lisbon, and more in one long take. There are bits of overheard conversations from businesspeople on their morning commutes and families relaxing in the park, and it's a treat when the camera ducks off the sidewalks and into a food market or a Sunday art fair. Videos tend to run about 20 minutes, although some run more than double that.
John Darko dislikes audio snobs. He hates magazine clichés. He flat-out doesn't have the money to do blind tests and measure up all those crazy statistics that audiophiles love to hear when discussing stereo equipment. And he will be the first to tell you he has a different definition of high-end audio equipment. This channel is for the person who wants better sound and is willing to pay more than a few hundred bucks for it but isn't going to go on a hunger strike to afford an uber-expensive system the size of a falafel cart.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Darko doesn't mince words. If he has an opinion, he gives it to you straight, and brand names or consumer hype don't seem to hold any sway. As they shouldn't.
Bikes are having a moment. Everyone is using them to commute to work and run errands so they can stay off cough-covered subways and buses. Global Cycling Network leans toward road cycling, but a lot of the advice is applicable across the spectrum of mountain bikers and commuter bikers. Yes, there are discussions over the significance of uniform colors among international racers and stories of legendary racecourses, if you're into that—and maybe after some GCN, you will be—but there are also maintenance tips and advice on cycling more safely in cities, which everybody can use.
How masks went from don’t-wear to must-have Poker and the psychology of uncertainty An infrastructure arms race is fueling the future of gaming How to get Safari's privacy features in Chrome and Firefox Everything you need to work from home like a pro 👁 The therapist is in— and it's a chatbot app.
Plus: Get the latest AI news 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Writer and Reviewer Topics YouTube streaming gear Shopping Video Jaina Grey Eric Ravenscraft Simon Hill Adrienne So Julian Chokkattu Reece Rogers Adrienne So Jaina Grey WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,100 | 2,021 |
"How to Design the Perfect Yoga Space at Home | WIRED"
|
"https://www.wired.com/story/how-to-make-a-yoga-space-at-home"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Matt Jancer Gear How to Design the Perfect Yoga Space at Home Photograph: Nancy Honey/Getty Images Save this story Save Save this story Save So you're not a human Tetris piece and can't seem to wedge yourself anywhere in your tiny home for a badly needed session of yoga. Good news: You can make it work, even if you're separated from your regular yoga studio. It doesn't take much to get started. I spoke with Jessamyn Stanley , founder of The Underbelly and author of Every Body Yoga , for advice on how to begin turning your home into a one-person yoga studio.
Updated March 2021: We added a section on lighting sources and expanded our clothing options.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Lululemon Reversible Mat.
Photograph: Lululemon If you're just starting out with yoga, get a cheap mat, literally from anywhere. It'll force you to be more aware of your body positioning to keep from sliding around, instead of relying on an ultra-grippy mat to compensate for bad form.
"It's not a good idea to spend a lot of money right out the gate," Stanley says. "Sometimes if you start with a really good mat, you don’t learn all the really important foundational, tactical body things that are really necessary to have a more advanced physical practice." Once you start to grasp yoga principles, Stanley says it's time to step up to a better mat. She likes the Lululemon Reversible Mat ($88) , which is what she considers a starting point for “good mats.” Want the perfect mat? Shell out for the Jade Yoga Fusion Mat ($135).
Regardless of the mat, you're going to get it sweaty, so throw a towel over it. Stanley doesn't think yoga towels are worth it, so use a regular bathing towel, preferably one that's been washed a few times, because a brand-new one will be more slippery.
Muji oil diffuser.
Photograph: Muji Aside from making enough room around your mat so you won't bang elbows on any furniture, a yoga space needs to be inviting, even if it's just a temporary clearing on the living room floor with the coffee table pushed back. Try to make one spot your regular yoga area. Having a certain part of the home become familiar as your yoga space can help ease you into the mindset that you're exiting the workday and ignoring other flashy living room distractions—now it's time for yoga.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So All the personalization is optional. This is the easiest step, because as long as it doesn't get in your way or distract you, it's fair game. Scents might help put you in the right headspace, too. You can set up candles , burn incense, or use an oil diffuser.
Lavender and sage are especially prized for potentially relaxing effects. Adding indoor greenery with houseplants is one of Stanley's favorite ways to decorate a yoga space.
Anything that speaks to you and makes you relax into a state of mind that lets you begin to focus on yoga will do. You can even meditate before you switch to yoga. Your home meditation space can double as your yoga space.
Photograph: Bobby Quillard Locate your space near a window or skylight. Natural light boosts the release of serotonin, one of the chemicals that makes us feel happy and relaxed. If windows aren't an option, you can use smart bulbs and tweak brightness and hues when you're ready for yoga.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So A light-therapy lamp , a medically proven way to trigger the release of melatonin and serotonin to help wake you up, can also help before a yoga session if you're feeling drowsy or dreary. Or try a sunrise alarm , which mimics natural sunrises and sunsets to put you at ease.
If loud neighbors, roommates, or street noise keep you from focusing, buy a sound machine to drown them out. The LectroFan Classic is our favorite, because it has 10 fan sounds and 10 varieties of white, pink, and brown noise. Even silence can be deafening sometimes, so it can come in handy if you need some background noise to focus on your yoga.
Gaiam Yoga Essentials Block.
Photograph: Gaiam Get at least two yoga blocks.
There are going to be times that, no matter how good your form and strength are, you're going to wish your arms were a bit longer to pull off a pose. That's where a block comes in handy. When you need to plant a hand on the floor but aren't flexible enough to reach, the block will allow you to brace yourself.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So You can also use blocks in other ways, such as raising the pelvis or resting your head in other positions. It's the most useful and ubiquitous prop. "It's not about assisting the practice," Stanley says. "It's about deepening the practice." Other options are bolsters , which are large cushions used for support in various positions where you wouldn't want to use a hard block, and straps , which can help you reach your feet in poses where you need extra flexibility.
Like with the mat and towel, you can use stuff lying around the house as alternatives if you want to save money while you're still new to yoga. Tape cardboard boxes together to make blocks. Use books or a couch cushion. Stanley has even used a trash can as a block and her dog's leash as a yoga strap. You really don't need to buy stuff to practice yoga, she says, although once you start improvising equipment you'll start to realize the virtue in buying gear made for yoga.
Photograph: Lululemon "You should practice as close to naked as possible," Stanley says. If you're comfortable practicing naked, do that. If you can't because you're sharing your home or just aren't down with the idea of it, then practice in your underwear. I use these ExOfficio boxer briefs for hiking, but the synthetic, stretchy fabric is tight-fitting but flexible: perfect for yoga. The women's version is similarly made.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Still too much skin? Go for tighter yoga clothes instead of loose, baggy clothing. Tighter yoga pants let you be more aware of your body positioning and less concerned about extra fabric getting in your way. There are fewer yoga pant options for men than for women.
A lot of what's marketed toward men is loose-fitting, which hangs and gets caught up while positioning yourself.
It's easier to find a T-shirt in your wardrobe that'll work for yoga, but it could still help to buy one with some stretch in the material to prevent it from restricting your movements. Yoga clothes are expensive, but you don't need to spend big. Uniqlo has affordable, tight-fitting pants marketed as leggings for women and tights for men that will work just fine for yoga.
📩 The latest on tech, science, and more: Get our newsletters ! A boy, his brain, and a decades-long medical controversy My treadmill desk made working from home a cakewalk Why covering canals with solar panels is a power move How to export your passwords from LastPass OOO: Help! What if my new job sucks too ? 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Writer and Reviewer Topics buying guides how-to Yoga Shopping Louryn Strampe Louryn Strampe Eric Ravenscraft Matt Jancer Simon Hill Brenda Stolyar Eric Ravenscraft Adrienne So WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,101 | 2,021 |
"How to Get the Most Out of Your Meditation App | WIRED"
|
"https://www.wired.com/story/how-to-get-the-most-out-of-your-meditation-app"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Ashley Lauretta Gear How to Get the Most Out of Your Meditation App Photograph: Getty Images Save this story Save Save this story Save Some call it daydreaming; others call it fantasizing. Whatever you call it, it’s actually your brain’s default mode. We spend at least a third of our waking hours thinking about things other than what is happening immediately in front of us. Mind wandering isn’t all bad— it can foster creativity —however, when you need to be present, it takes practice and intention to get there. You can in fact train your brain to focus on the here and now using meditation, but it’s not something you just “get” immediately.
It is admittedly pretty difficult to be present in our lives (so much so that researchers out of University College London admit our smartphones have become a second home, in a sense), but technology isn’t entirely to blame. In the case of learning how to meditate, it can actually help. However, practicing mindfulness requires more than a meditation app and some free time.
You can’t become an experienced meditator without first understanding the goal of meditation. This first step is where a lot of people get hung up. There isn’t a right or wrong way to meditate, as long as you reach the desired outcome: bringing your mind back to the present.
“There is this expectation that you are going to be good and it's going to be easy,” explains Estevan Valdes , a yoga teacher and fitness professional whose offerings include meditation. “And that it is rigid. That you have to be completely still, you have to be completely erect and that is going to create what is seen as ‘success.’” The problem comes when you think you can clear your mind—that’s not the goal. In fact, Valdes admits, there are very fleeting moments of your mind being empty in meditation; they state that being present is meditation.
Deciding what you want to get from meditation determines what type of meditation you should do (which then dictates which app is the best for you). While there are many forms of meditation, research has confirmed that multiple meditative techniques can reduce neural activity in the parts of the brain associated with mind-wandering. It’s true that some types are more rigid than others; perhaps the most common in a scientific setting is Mindfulness Based Stress Reduction (MBSR) , which has been around since the 1970s and involves mindfulness meditation, body scanning, and yoga postures.
One such study that employed MBSR found that taking a meditation course—and therefore, becoming a more experienced meditator—had a marked effect on stress management.
Lead author of that study, Elizabeth A. Hoge, associate professor and director of the Anxiety Disorders Research Program in Georgetown University Medical Center's Department of Psychiatry, noted that MBSR is used in a clinical setting because it helps researchers “adhere to rigorous methodological standardization” thanks to its guide manual for instructors, but adds that there are other types of meditation—such as Metta meditation, based on Buddhist teachings of loving-kindness—that can have similar benefit.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So According to Fadel Zeidan, executive director of the UCSD Center for Mindfulness , MBSR contains a number of meditative practices that can be practiced on their own—without paying for the standardized program—including sitting meditation, body scan meditation, walking meditation, compassion meditation, hatha yoga, and breathwork (which he considers to be his favorite and the most easily accessible). “It doesn’t have to be a formal practice where you sit on a cushion and burn incense,” Zeidan muses. In fact, breathwork with the goal of having a mindful moment is what Zeidan says is the basis of most of the current meditation apps.
Diana Winston , director of mindfulness education at UCLA's Mindful Awareness Research Center (MARC) , notes that there is a lot of research on mindfulness, which is why a lot of the apps are mindfulness-based. This includes Headspace and Calm —which are some of the most well known—and even UCLA Mindful , guided by Winston and the MARC team.
Whether your goal is to reduce anxiety, become more mindful in your daily life, or develop a daily meditation practice, research has found that online meditation can work; you just have to know what you should be working with.
If there is no one meditation technique to rule them all, how do you know which one will work for you? This is where apps can be extremely helpful, as they provide an opportunity to try a lot of different techniques, all in one, easily-accessible place. According to Zeidan, however, you don’t want an app that has you doing too much, too fast. (For example, you shouldn’t be doing three different types of meditation in a 15-minute span.) “One way to judge the efficacy of an app is how many techniques they introduce to you at a given—small amount of—time,” Zeidan says. “You don't want that; you really want to master one thing and then move on. We have a tendency to want to try a lot of things, but I think focusing on breath and the body are really the most critical methods to start with.” Again, mindfulness meditation is growing in popularity and can be achieved through multiple practices—such as breathwork, body scan meditation, walking meditation, and more—but finding which one works best for you may require some trial and error. “Which app you choose depends somewhat on your goals,” adds Winston. “Is it mindfulness you are looking for or some other type of practice? If you want to learn mindfulness, there are many apps out there and it can be overwhelming; what people tend to do is go to the ones that are most well known, like Headspace, which are good apps. The issue is finding something that you resonate with.” If you don’t have a connection to your meditation app, it will be near impossible to have a connection to yourself in the moment. Winston says something as simple as finding the instructor's voice to be annoying is enough of a reason to try a new instructor on the app or, if that isn’t an available option, get a new app altogether.
“Trust your own intuition, listen and really watch the way that you instinctually react to the person [or instructor],” adds Valdes. “If you don't feel connected it might be hard to focus.” Ultimately, they say, if you don’t feel like you fit the atmosphere of a specific app, class, or instructor, don’t hesitate to move on. You’re not stuck with any one app or method. If you don't feel attracted to the vibration that the person or technique is offering you, there is so much stuff out there.” Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So It is important to keep in mind that certain meditation techniques, such as Vipsanna—a Buddhist practice focusing inward on the self—are rooted in ancient practices, which is a fact that is often lost in the colonization of the wellness space. Because of this, Valdes suggests that people who have an interest in starting a meditation practice seek out instructors that have it as a form of their indigenous or cultural practice. In app form, options include Plum Village , created by the monastic community led by Buddhist visionary Thich Nhat Hanh, and Liberate , a meditation app designed for the Black community, featuring BIPOC instructors.
If you’re looking to become an experienced meditator, then you’ll want to look for an app that has an education component of guided meditations and exercises—for example, popular app Waking Up includes lessons and conversations about meditation theory—until you find what helps you reach the goal of training your mind to be present.
Winston notes that many apps will offer courses in week-long increments, for example, as an introduction to the basics of meditation. Most educators suggest studying meditation in a one-on-one capacity, because many experienced meditators often receive individualized instruction or go so far to attend in-person retreats. Finding an app that comes with access to a professional is a feature to seek out should questions arise during your practice.
Ten Percent Happier is one such app, offering subscribers access to a personal meditation coach. “Some of the things that come up [during meditation] can be personal to that individual and there is awareness of other things that can be awoken, such as trauma, and side effects, such as seeing spots and feeling like you’re floating,” says Zeidan. “Having clarity can help you not let your mind wander on what it is.” In other words? Actually use the app. While there is no magic number experts can provide to tell you how much or how long to meditate, Winston encourages you to do it when you can. Of course a daily practice is preferable, but it’s less about how much time you spend per day and more about overall consistency. In fact, research suggests long-term meditation practices do have measurable impacts on the brain.
“To become an experienced meditator you have to keep practicing,” says Zeidan. “I actually asked the Dalai Lama [when showing] him my research, ‘How much training is needed to really be a good meditator?’ And he said: ‘A lifetime.’” Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Practicing doesn’t just involve how many times you open the app or the number of meditation sessions you complete. It’s also going to involve practicing the specific methods introduced. Again, mindfulness isn’t easy; our brains aren’t wired for it. “People should be patient with themselves,” says Hoge. “It does take some time to develop the practice. Also, people shouldn't give up because they ‘can't clear my mind.’ No one can do that for more than a few seconds. It’s more about what you do when you notice you've gotten distracted from your meditation focus.” It’s likely you’ll experience some sort of benefit after just one meditation session.
But how will you know when the app is really working for you? “One way to judge if it's helping is not asking yourself if you’re able to notice your breathing,” says Winston, “but How is it affecting my life? Am I feeling calmer and more peaceful? Do I notice I am less reactive with my kids or my partner? These are markers that the app is working. Look for changes in life instead of becoming the best meditator.” Zeidan notes studies have found our meditative state can become more trait-like over time. In this case, he likens the brain to a muscle; the way you feel when meditating becomes stronger and almost like a personality trait.
“You can never actually be ‘good’ at mindfulness meditation; that is one thing that is inherently American in the way that we think about this Eastern practice,” says Zeidan. “It is about cultivating awareness of the present moment. You will always find your mind to be distracted, just hopefully you get better at not getting agitated with yourself for being distracted. That is meditation; when you can stop judging yourself and the stuff around you that you are experiencing. That is really the magic of it: Being present without judgement.” 📩 The latest on tech, science, and more: Get our newsletters ! A people's history of Black Twitter Scientists just ‘looked’ inside Mars.
Here's what they found This tool calls out thousands of hackable websites Intel's ambitious plan to regain chipmaking leadership Power up anywhere with the best travel adapters 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🏃🏽♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Contributor X Topics mental health psychology Apps Justin Pot Jordan McMahon Reece Rogers Nena Farrell David Nield Justin Pot Jaina Grey Reece Rogers WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,102 | 2,021 |
"How to Get Free Kindle Books With Your Library Card (2021) | WIRED"
|
"https://www.wired.com/story/how-to-get-free-kindle-books-with-your-library-card"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Jordan McMahon Michael Calore Gear How to Get Free Kindle Books With Your Library Card Photograph: Getty Images Save this story Save Save this story Save You've always wanted to read Infinite Jest, and now you finally have enough time on your hands to get through all 1,079 pages. Sure, you could grab it from a local bookseller , or order it on Amazon.
But you might be able to read a digital copy for free by borrowing it from your local library. With a library card, an internet connection, and an e-reader , you can start reading the book right away without ever leaving your house.
If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
First, you'll need a library card. If you don't already have one, visit your local branch to get one. That may be difficult if your library is still closed.
But check the website of your local branch to see if you can get an electronic card issued online.
Some libraries will give you a card without requiring you to show up.
Use your credentials to access your library's e-book collection. Many libraries use OverDrive , a cross-platform service with millions of e-books and audiobooks. Scroll through OverDrive's catalog in your browser, or download the company's app, called Libby , to scroll through the selection on your phone. Once you find the book you want, you should be able to click a button and borrow it.
Most books are available right away. Some books, especially new releases or popular titles, will show a wait time. You might even have to wait as long as a few weeks or months to borrow a best seller. This is because libraries don't have unlimited copies of digital books; they only get a finite amount to pass around, and the more popular a book grows, the more scarce those digital copies become.
So relax and grab a spot in the queue. Once you request a loan, Libby will send an alert once the book is available for you to borrow. The app can also tell you the current wait time as copies get returned to the library and the line grows shorter.
There are a few ways to read your borrowed book. If you have a Kobo reader, it integrates directly with OverDrive—you simply search for a book on OverDrive on your Kobo and download it. You can also download books directly in the Libby app, or on any Kindle device. We find a dedicated e-reader to be a more pleasant, and much less distracting, experience.
A Kobo reader might be slightly easier, but setting up a Kindle isn't hard. Within the Libby app, tap on the user menu at the top of the screen. Under Help & Support, find the menu item "Read books with," then select Kindle. The app will guide you through the process of linking your Libby account with your Amazon account.
After it's set up, whenever you borrow a book, the Libby app will shuttle you over to Amazon for a moment so you can tell Amazon which Kindle reader you'd like the book delivered to. After that, with your Kindle connected to Wi-Fi, just turn on the device and go to the main menu. You should see the book automatically appear.
Just like the rest of the books in the library, there are limits on how long you can keep the e-books you check out through OverDrive. These limits vary from library to library. Unlike physical books, you don't have to do anything to return an e-book you've checked out. After your time's up, the book will simply disappear from your e-reader.
If you don't have a Kindle, that's fine. You can still just read e-books directly inside the Libby app. Or, if you have another type of e-reader—a Nook, a Kobo reader , a ReMarkable tablet , or any device that supports reading digital books —you can transfer your book directly to the device from the Libby app or the OverDrive website.
However, just know that support for direct transfer is not as thorough on a device that isn't a dedicated e-reader. You may need to download your e-book (in standardized ePub file format) onto a computer, then transfer it to the e-reader manually over USB.
In addition to e-books, most libraries also let you check out audiobooks. You can stream those directly through the Libby app, and sometimes you're allowed to download them too.
Libraries with films and TV shows in their collections (which is most of them by now) also offer digital loans of those. That's right, free movies! The best place to start is Kanopy.
You can use your library card to access the platform's selection of streamable movies. Kanopy's catalog is heavy on documentaries, independent films, and educational programming, but there's some fun, mindless stuff in there too.
How UFO sightings became an American obsession A critical internet safeguard is running out of time Covid-19 is bad for the auto industry— and even worse for EVs Going the distance (and beyond) to catch marathon cheaters Uncanny portraits of perfectly symmetrical pets 👁 If AI's so smart, why can't it grasp cause and effect ? Plus, get the latest artificial intelligence news ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Senior Editor X Instagram Topics how-to Kindle Books back to school Adrienne So Eric Ravenscraft Adrienne So Jaina Grey Brenda Stolyar Simon Hill Julian Chokkattu Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,103 | 2,022 |
"30 Best Cheap Gear Under $30 (2023): Phone Cases, Camera Bags, and More | WIRED"
|
"https://www.wired.com/gallery/our-favorite-gear-under-20-dollars"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Adam Speight Gear Team Gear Our 30 Favorite Gadgets and Gear for Under $30 Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Low-Cost Buds $25 at Amazon Portable Sound Machine $30 at Amazon Top-Up Dock $30 at Target For Loose-Leaf Lovers $12 at Amazon Saving cash is never a bad thing, and when words and phrases like “inflation” and “cost-of-living crisis” are all over the news, finding value for money has become even more important to many. WIRED's Gear team has tested a broad range of products across many categories—many of which, handily, cost under $30. This guide brings together those top value-for-money picks into one list.
The choices here are useful for any time of year, but if you’re looking to spend thriftily this holiday, check out our 25 Amazing Gifts Under $25 guide for ideas. Don't forget to dive into our buying guides for more recommendations.
Updated December 2022: We’ve added an entirely new selection of our favorite budget finds.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Photograph: JLab Low-Cost Buds JLab Audio Go Air Pop The Go Air Pop are a great pair of cheap earbuds that fit well, come in cool colors, and have an AirPod-beating 8 hours of battery life. They don't sound quite as good as Apple's finest, but they perform more than well enough for listening to music and podcasts, especially as a pair you don't have to worry too much about. The included charging case also has a built-in USB cable, which means you'll never hunt through a drawer for one.
$25 at Amazon $25 at Walmart Photograph: Amazon Portable Sound Machine Dreamegg D11 The Dreamegg D11 is our favorite sound machine for portability. While it's aimed at the parents of babies, there's nothing stopping adults in need of some soothing sounds from using this too. Its small size makes it easy to take with you on the go, and there's 11 sounds for you to try, from a fan to lullaby music and more.
$30 at Amazon $40 at Dreamegg Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Sony Top-Up Dock Sony DualSense Charging Station This PS5 accessory is an absolute must-have. Using the included cable is such a hassle, especially if you have more than one controller. With the dock, I simply pick my controller up to use it and place back down after every gaming session. Simple. There's really not much else to it. It's an essential gadget for those who like the easy life.
$30 at Target Photograph: Amazon For Loose-Leaf Lovers Oxo Brew Twisting Tea Ball Infuser This clever gizmo from Oxo is a swift way to deliver your loose-leaf tea fix. You simply open the infuser basket by twisting the handle, then you can scoop up your leaves, close again, and proceed to dunk in your cup of choice. The closed basket makes it easy to transport and ditch the leaves once you're done too.
$12 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Amazon Iced Tea Tool Hario Cold Brew Tea Pot Of course, tea isn't just for warming up the cold among us. There's iced tea too. This tea pot from Hario is our cold brew choice in our best tea accessories guide. Get your loose leaf in there, whack in some water, then pop in the fridge the day before you need it. In the morning you'll have your cherished iced tea fix.
$20 at Amazon Photograph: Logitech Portable Keyboard Logitech K380 Apple and Logitech itself sell more elaborate keyboard cases that comprise of, well, a case and a keyboard. But if you're not a regular user of a tablet and keyboard combo, you might not want to have your case always bound to a keyboard 24/7. Enter this portable keyboard from Logitech. One of our top iPad accessories , the K380 is a compact and quiet, yet tactile, keyboard that's easy to sling in a bag or stow away at a desk. There are a few colorful shade options too.
$27 at Amazon $40 at Logitech Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Harbor Freight Tough Tool Transport Harbor Freight Hercules Tool Tote This small tool bag is a great option for the home, to whip out when a household DIY situation hits. It may just be fabric but it's built to resist bumps and the like. There's also 22 pockets to accommodate all the home tools you need, with pockets on both the inside and out for easy access.
$27 at Harbor Freight Photograph: Belkin Upgrade Your Webcam Belkin iPhone Mount With MagSafe for MacBooks If it's possible to solve a problem in both an elegant and inelegant way, then this is it. The idea of attaching a phone to your laptop as a way to improve your webcam experience feels like overkill, but Apple has softened the blow as best it can. The Belkin iPhone Mount with MagSafe for MacBooks (the name is also inelegant) is one of our favorite MagSafe accessories and achieves what it says on the tin. The mount will let your iPhone be used as a webcam using Apple's Continuity Camera feature, improving picture quality to no end.
$26 at Amazon (For MacBooks) $30 at Apple (For MacBooks) $40 at Amazon (for Mac Displays) $40 at Apple (for Mac Displays) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Anker Powerful Plug Anker Nano Pro This Anker charger is one of the best iPad accessories , but it's great for phones and Android tablets alike too. It can achieve up to 20W output, meaning it's able to fast charge an iPad Pro. The big benefits here are its diminutive size and value-for-money proposition—coming in slightly cheaper than Apple's own plugs. There's no cable included, but that's another thing Anker can help you out with.
$14 at Amazon Photograph: Amazon An Outdoor Dog Bed Coolaroo The Original Cooling Elevated Pet Bed A cheap and cheerful place for your dog to just chill out, Coolaroo has it covered. The Original Cooling Elevated Pet Bed is one of our recommendations for a top dog bed.
The bed's raised form factor allows air to circulate around your doggo while they sit comfortably. There's plenty of choice here too, with a bunch of sizes and colors available.
$30 at Amazon $33 at Chewy Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Cat Person Feline Fun Cat Person Toys Filling up our best cat furniture guide with some entertainment for your pet is Cat Person's range of toys. WIRED's feline fanatic Medea Giordano was a big fan of Georgia the Chicken (pictured). Cat Person offers a variety of cat-friendly products but these particular toys come attached to a string and stuffed full of catnip.
$7 at Cat Person Photograph: Roku A Simple Streaming Stick Roku Express HD We think the Streaming Stick 4K Plus is the best Roku for most people, but if you want to spend the least amount of money and still enjoy Roku’s simple interface, get the Express HD. It’s for those with a standard HDTV. Roku works with all the major streaming services, and even the least techy among us can figure it out. But at this price, the remote can’t control your TV’s volume or power. — Medea Giordano $28 at Amazon $29 at Walmart Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: B&H A Camera Strap Hex Ranger Camera Wrist Strap The strap of choice for WIRED reviews editor Julian Chokkattu, this camera accessory from Hex offers a neat trick. Once attached to your wrist correctly, if you drop the camera, the strap will tighten, then loosen again once you grab a hold of it for your next snap. No need for extra fastenings to mess around with. It's also comfortable and doesn't feel too restrictive.
$29.95 at B&H $29.95 at Hex Photograph: Lamicall Adaptable Arm Mount Lamicall Gooseneck iPad Holder Ever been lying in bed, back flat to the mattress, looking up at your phone, and had it smash you right in the face? Now, imagine it's an iPad… ouch. This bendable arm is one of our favorite iPad accessories and is here to avoid unnecessary bumps and bruises, as well as save the odd sore neck. It can attach to a desk or nightstand and lets you position it perfectly for reading, watching, game-playing, and more. As a budget pick, the arm isn't the most stable we've tested, so it's best for passive viewing rather than tapping the screen regularly, but the Lamicall is extremely useful nonetheless.
$26 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Nintendo Cardboard Creativity Nintendo Labo Cardboard Kits Nintendo wowed the gaming world when it launched Labo, with a cornucopia of creative ideas to merge seamlessly with your Switch. Some of the kits represented a bit of a high bar to entry, but options like this Vehicle Drive Kit are pleasingly cheap. This model comes with a steering wheel and pilot joystick to build, alongside an accompanying game for hours of fun.
$45 at Amazon Photograph: Anker Pint-Sized Power Anker PowerPort Cube WIRED reviewer Eric Ravenscraft absolutely loves the Anker PowerPort Cube and it's easy to see why. The cubed charger offers extension cable–like benefits in a package that's far less space-consuming, allowing you to smartly place it under your couch or in similar locale.
$22 at Amazon $22 at Walmart Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: PopSockets Getting A Grip PopSockets PopGrip for MagSafe One for PopSocket fans, and another one of our top picks for MagSafe accessories to consider, this PopGrip uses Apple's magnetic tech to snap to the back of your iPhone. Admittedly, solely leaving the fate of your phone grip down to MagSafe is slightly less reassuring than an embedded case or accessory that uses an adhesive, but this is a convenient option nonetheless. If you get bored of this look, you can even switch out the top portion for something else.
$30 at Amazon $30 at PopSockets Photograph: Case-Mate A Blocky iPhone Case Case-Mate Blox MagSafe Case There's a wide variety of cases you can buy for your iPhone, but it hasn’t felt like there's been something truly different for a long while … until now. One of our best iPhone 14 cases , the Case-Mate Blox MagSafe Case is something out of the box. This case turns your iPhone into an angular slab. And the interesting shape is accompanied by some eye-catching colors, in case the build wasn't enough to grab some attention. It isn't the very best for protecting your screen, but it does have MagSafe support.
$25 at Amazon (Pro Max) $40 at Case-Mate Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Miir Top Travel Mug Miir Flip Traveler (16 Ounce) No ifs, no buts, no leaky cups, this travel mug from Miir is the best around. WIRED reviewer Matt Jancer has put it through its paces for years and highly rates its leak-proofing. Plus, its slender size means it will fit snuggly in backpacks and cup-holders alike.
$35 at Miir $39 at Amazon Photograph: Amazon A Cheap Knife Kiwi Stainless Steel 8-inch Chef's Knife A good knife shouldn't cost a fortune. These Kiwis are our top cheap pick among the best knives around. The steel isn't the best, but if you sharpen regularly they'll keep an edge just as well as a $100 knife. Just take some of the money you save on these and invest in a good sharpening system. We like this Gatco rod-guided sharpening system , which eliminates much of the guesswork of sharpening.
$10 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Logitech Cheap Gaming Mouse Logitech G203 This low-price gaming mouse is our favorite under $50. The Logitech G203 offers a decent 8,000 DPI along with six customizable buttons and RGB lighting. Sure, you'll find better mice at higher price points, but this is a top value pick.
$40 at Amazon $40 at Walmart Photograph: Chronicle Books A Colorful Read The Brilliant Deep This book from Kate Messner and Matthew Forsythe is an entertaining and informative look at environmental preservation and the work of scientist Ken Nedimyer, founder of the Coral Restoration Foundation.
The Brilliant Deep delves into coral reefs and scuba diving alongside tales of Nedimyer's life.
$12 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Anker A Wireless Charger Anker PowerWave Pad and Stand Wireless charging has become standard in smartphones over the past few years, and it’s lovely not having to fumble with cables. Anker’s reliable and affordable chargers come in various shapes and sizes, but we think the PowerWave Stand makes a great gift for your loved one’s desk or bedside table. With your phone propped up and charging, it’s easy to see incoming notifications and tap that touchscreen when you need to.
$16 at Amazon (Pad) $24 at Amazon (Stand) Photograph: Philips No-Fuss Cleaning Philips One by Sonicare The cheap Philips One electric toothbrush is for the in-betweeners. You don’t want the most powerful vibrations or app support while you brush your teeth, but you want a little more help than a manual toothbrush. It vibrates enough to aide in your cleaning, though you still have to do most of the work. This version takes one AAA battery, or you can spend $40 for the rechargeable one.
$25 at Amazon (Battery) $40 at Amazon (Rechargeable) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Prostorm Budget 'Brella ProStorm Vented Travel Umbrella Keeping out of the rain shouldn't cost the earth, and Prostorm has us covered, literally. This vented travel umbrella has a fiberglass and steel frame for batting back wind and rain. It offers plenty of space for one person, though, annoyingly, the handle itself is a tad on the small side.
$20 at Amazon Photograph: Nimble A Cable For The Eco-Conscious Nimble PowerKnit USB-C to USB-C Want a cable that's eco-friendly but doesn't compromise on quality? This one from Nimble has been the go-to for WIRED reviews editor Julian Chokkattu for several years now with nary an issue, and it sits pride of place in our best USB-C cables guide. This cable dodges feeling cheap and plasticky, with its mix of certified recycled plastic and aluminum feeling nice and textured. There are three lengths to choose from, plus there's a two-year warranty for your peace of mind.
$22 at Nimble Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Verbatim In A Flash Verbatim Pinstripe (256 GB) It may not be the most glamorous gift, but this USB flash drive is a virtual filing cabinet for your pocket. Whether your recipient wants to take their saved games with them, backup and transfer photos, or share the first draft of their novel, this practical thumb drive will come in handy. It slides shut, so there’s no cap to lose, and there is a handy loop for sliding onto a keychain. Plus, you can never have too many thumb drives.
$23 at Amazon Photograph: Sandisk Need Some Space SanDisk 128 GB High-Speed MicroSD Card The best thing I did with my Nintendo Switch, beyond playing The Legend of Zelda: Breath of the Wild , was beefing up the storage. This 128-GB microSD card let me go all-digital and ditch the requirement to lug around cartridges, and it's pretty cheap. That's why it's in our best Switch accessories roundup.
$14 at Amazon (128 GB) $24 at Amazon (256 GB) Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Photograph: Monoprice 360 Extender Monoprice 8 Outlet Rotating Surge Strip Ever thought of using a surge stripe with rotating outlets? You may never go back. Sitting in our Work From Home guide, this Monoprice extender more easily accommodates your different plugs by allowing you to rotate the sockets to your needs. Who would’ve thunk.
$27 at Amazon Photograph: JBL Wired For Sound JBL Tune 205 The JBL Tune 205 are a solid pair of wired earbuds with ergonomic tips and an included mic for calls. They come in a nondescript black and with a convenient carrying pouch, so they won't tangle up around all your other belongings in your bag or pockets.
$20 at Amazon Writer and reviewer X Topics Shopping buying guides gear Scott Gilbertson Scott Gilbertson Boone Ashworth Reece Rogers Carlton Reid Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,104 | 2,021 |
"18 Gifts for People Who Really Need Some Sleep (2021) | WIRED"
|
"https://www.wired.com/gallery/gifts-for-sleeping"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Jaina Grey Gear 18 Gifts for People Who Just Need a Good Night’s Sleep Facebook X Email Save Story Facebook X Email Save Story If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Twin Lamps $116 at Casper Reset Your Circadian Rhythms $449 at SkyView Bedside Tea Service $144 at Amazon Bedside Humidifier $20 at Amazon I've always had trouble sleeping. Between anxiety and insomnia, I take all the help I can get. And I'm not alone. The world came apart at the seams last year, and that has wrecked many people's nights. Chances are, someone you know is not getting enough sleep , and that can have a serious impact on their health.
I've tested dozens of sleep products over the past couple of years. The best of the best are listed here, and I can attest that each one of these has helped me sleep a little better at night. I hope they help you, or a loved one, too.
Be sure to check out our many other buying guides this season, including the Best Gifts to Relieve Stress , Gifts for New Parents , and Great Gifts Under $25.
Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).
This includes unlimited access to WIRED.
com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.
Updated November 2021: We've added retailers throughout, included the Beats Studio3 Wireless and BIOS SkyView Lamp, and updated prices.
Photograph: Casper Twin Lamps Casper Glow Lamp When it comes to gentle, glowing bedside lamps, Casper’s Glow is on the high end of the price spectrum, but for $229 you do get two of the little guys. The compact lamp doesn’t feature much in the way of external controls—there’s just one button on top and another on the bottom. You mostly control it with touch gestures. Twist it to brighten or dim, and flip it over to turn it on or off. It sheds a warm sun-like light that gradually darkens when it’s time for bed. There’s also an app you can use to control the lamp. Tell it when you’d like to wake up and the Glow Lamp will brighten gradually to help you rise and shine.
It's also a great night light. If you have to get up in the middle of the night, you can pick it up off its charging base, give it a wiggle to put it in night-light mode, and carry it around like a little lantern.
$116 at Casper $116 at Bed Bath & Beyond Photograph: BIOS Reset Your Circadian Rhythms BIOS Skyview Lamp The BIOS SkyView lamp uses satellite data and an array of internal LEDs to precisely mimic the day and night cycle in your location—the idea being to keep your sleep cycle more regulated. When I first started testing this lamp I was skeptical, but after a couple days with it in my living room, my partner and I found ourselves getting tired and going to bed much earlier than usual.
I can’t say it gave me better sleep, but it definitely had an effect on my sleep cycle. Plus, it’s a gorgeous piece of decor. The daylight colors flow down the lamp’s enormous bulb in hues of blue and white, and as the sun goes down shades of red, purple, and orange creep in to mimic a sunset. It’s gorgeous.
$449 at SkyView Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Ember Bedside Tea Service Ember Mug 2 (14 Ounces) Ember's smart Mug is a great choice for coffee in the morning, keeping your cup of motivation warm throughout your workday. But it's also a surprisingly capable sleep aid. Fill it up with a calming herbal tea (I'm a sucker for Sleepytime), and set it up at your bedside. You'll have warm sleepy tea waiting for you if you wake up in the middle of the night and can't get back to sleep.
$144 at Amazon $150 at Target Photograph: Amazon Bedside Humidifier HealthSmart Cool Mist Humidifier Lamp When you’re trying to get a good night’s sleep, the right lighting is super important. The HealthSmart humidifier lamp is an LED lamp that sheds gentle multicolored light that can help you wind down at bedtime.
The humidifier inside plays two roles to help you fall asleep. First, if you’re stuffy or a little sick, a humidifier can help keep your nasal passages from getting too inflamed while you sleep. It can also be used to diffuse essential oils for a little aromatherapy. Just know that some essential oils can be dangerous to pets.
$20 at Amazon $30 at Target Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Gravity A Different Kind of Mask Gravity Blanket Sleep Mask I wasn’t a sleep mask person before I tried this one. Something about having a mask on my face always kept me from getting to sleep. Even the nice cooling ones full of gel beads felt weird on my face. This one, full of the same kind of heavy material as Gravity’s weighted blankets, feels incredible.
Just strapping this 1-pound mask on my head makes me sleepy.
$39 at Amazon $40 at Gravity Photograph: Casper Cozy Weight Casper Weighted Blanket When it comes to modern sleep aids, you’ve probably heard a lot about weighted blankets. They live up to the hype. They’re often filled with sand and give you a comforting sense of being gently held—a little like a swaddle for adults. They’re great for anyone with an anxiety disorder (me!) or anyone who generally has trouble falling asleep (also me!). They can get quite warm, though, which is why this Casper model is one of my favorites.
It comes in 10- and 15-pound versions, which is a lot lighter than most weighted blankets, and it stays very cool, in comparison. A lighter weight also makes it approachable for people who are new to weighted blankets and might not know exactly how much weight they prefer. Our household has been sharing this one for a couple of weeks now, and we find that it’s a great choice for a wide variety of body types.
If you’re looking for a heavier blanket, I can wholeheartedly recommend the 20-pound option from Gravity.
We also have a full list of the best weighted blankets.
$161 at Casper $161 at Amazon Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Beats Headphones to Sleep In Beats Studio3 Wireless While these aren’t designed specifically for it, the Beats Studio3 wireless headphones are super comfy to sleep in, thanks to their lightweight build and plush ear padding. They’re great for nights when you just can’t get to sleep and need some music or rumbly bass-heavy storm sounds to lull you into a restful slumber. Not to mention, they’re great headphones to boot. Check out our review for more.
$350 at Amazon Photograph: Google Mini Noise Machine Google Nest Mini (2nd Gen) Just say, “Hey Google, play rain sounds,” and the Nest Mini will play you a gentle rain shower loop until you tell it to stop. As white-noise machines go, that’s about as easy as it gets. You can even set up a routine in the Google Home app to play a particular white noise or music playlist at a particular time to help you go to sleep and a different one when it’s time to wake up.
There are plenty of reasons why you might want to be wary of bringing an always-on microphone into your bedroom, but the Nest Mini really can help you get a better night’s sleep. Having one on a bedside table is nice, because the mute button is within easy reach.
Check out our favorite sound machines for more help with "white noise." $38 at Walmart $50 at Best Buy $49 at Target Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Jambys Snuggle Pants Jambys Pajama Shorts These are the softest, stretchiest, comfiest boxer-style shorts you're likely to find anywhere. They're plush to the touch and they even have pockets. Even on these cold winter nights, they're a constant companion of mine. As a warm sleeper who often kicks off the blankets in the middle of the night, it's nice to have sleepwear that's comfy and breathable without being too warm or stifling.
$35 at Jambys Photograph: Gravity Scented Slumber Gravity Blanket Shredded Memory Foam Pillow A good pillow can go a long way toward getting you or a loved one a better night’s sleep. Gravity’s pillow is packed full of shredded memory foam to keep you cool, and it molds to your head and neck while you sleep.
It also has a trick up its sleeve. The pillow has a couple of internal pockets you can fill with Gravity’s proprietary scent packs. These little scent cartridges give the pillow a lavender aroma that can be very relaxing. It’s a light scent, too; I only really smell it when I shift or really bury my face in the pillow. It’s like a gentle background melody, subtle but present enough to set the tone and help you drift off.
$68 at Amazon $60 at Gravity Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Casper Like Sleeping on a Cloud Casper Nova Mattress Casper's Nova mattress has been an absolute joy. I'm a picky sleeper, and a mattress that's too soft or too firm will keep me up at night. Casper's Nova is right in the middle, fitting for a hybrid mattress with springs, foam, and a plush—but not too plush—pillow top. It's honestly hard to get out of in the morning, it's so comfortable. The springs really make the Nova mattress for me. It's soft but springy and contours to my body perfectly. This one also keeps me cool in the middle of the night, even when sleeping with a partner.
Check out more of our favorite mattresses here.
$1,653 at Casper Photograph: Tuft and Needle Cool Down Tuft & Needle Mint Mattress (12-Inch) Getting a great night’s sleep is a lot easier if you have a great mattress. The Tuft & Needle Mint Mattress is designed to relieve pressure, contour to your body, and keep you cool. There’s a lot of technology and materials science in this mattress. From ceramic gel to “heat-wicking graphite,” Tuft & Needle pulled out all the stops to help you get to sleep. We found it very comfortable in our testing.
Our guide to the best foam and hybrid mattresses has other recommendations for a good pad to sleep on.
$1,595 at Tuft & Needle Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Parachute Modern, Classic Sheets Parachute Linen Sheet Set If there's one thing you should invest in when trying to get a better night's sleep, it's a good set of sheets. Linen sheets are kind of an extravagance. They age well, get softer over time, and are extremely durable—but they are pricey, and these linen sheets from Parachute are no exception. They're designed for longevity, and they have a well-earned reputation.
$279 at Parachute Photograph: Nest Heavy but Comfy Nest Merino Wool Comforter The right comforter makes a big difference when you're a notoriously restless sleeper. I'm a fan of weighted blankets, and while this merino wool comforter isn't weighted specifically, it does have a good solid weight to it. It's soft, plush, and airy, but heavy enough that sleeping under it feels like wrapping yourself in a warm hug. The wool filling is cozy and warm, but it's also breathable, so you don't get sweaty underneath.
$300 at Nest Bedding Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Parachute Napping Companion Parachute Cloud Cotton Quilt If weighted blankets aren't your taste but you'd like a good napping blanket, the Cloud Cotton Quilt from Parachute is a killer choice. It's stretchy and soft and just heavy enough that it drapes comfortably over your body without weighing you down. It'd be perfectly at home folded up on the back of a couch, or at the foot of a bed. It's also a great blanket for houseguests sleeping over on the couch.
My favorite way to use this plush and cozy quilt is to fold it up and lay it down on the floor like a big body pillow. Seriously, you'll never have a better nap.
$249 at Parachute Photograph: Thuma Build-a-Bed Thuma Wooden Bed Frame (No Tools Required) A mattress is important, but a bed frame can be just as important. Thuma’s platform bed frame is super sturdy, made from solid wood and fitted together with cleverly designed joints. Those joints offer the bed just enough give to let it settle into itself, but not so much that it creaks or makes noise when it’s getting a good jostling. This bed is remarkably quiet and makes me feel a lot less self-conscious about tossing and turning in the middle of the night.
Did I mention you can build it in about 10 minutes without a single tool? $1,095 at Thuma Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Photograph: Dame An Adult Lullaby Dame Pom Flexible Vibrator Let's be real here. When you're trying to get to sleep, sometimes the best thing you can do is give yourself a little extra self-care.
Dame's Pom vibrator is a personal favorite. It's small, powerful, and versatile. Packed with a wide variety of vibration patterns and intensities, it's a great toy for people of all genders and sexes—whether you're playing solo or with partners. Pom just feels friendly and approachable, and is a good choice whether it's your first sex toy or your hundredth.
Check out our sex tech buying guide for an in-depth look at toys and tech for every body.
$95 at Amazon $99 at Dame Photograph: Olly Curtis/Getty Images The Gift of Music YouTube Premium Subscription Music streaming services are a great way to help yourself or a loved one get a better night’s sleep.
Spotify and Apple Music all have playlists of dedicated rain sounds, ocean sounds, or other white noise that can help you relax and unwind at the end of the day. I prefer these to buying albums of relaxing sounds because streaming services offer a wider variety of tunes.
YouTube Premium is also a great option (and it includes YouTube Music) if you’re more visually inclined. Having a TV on all night isn’t too bad if it’s just displaying a serene river scene on a 10-hour loop.
$10 at YouTube Writer and Reviewer X Instagram Topics Shopping buying guides gift guides Sleep Scott Gilbertson Scott Gilbertson Boone Ashworth Reece Rogers Carlton Reid Virginia Heffernan Boone Ashworth Boone Ashworth WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,105 | 2,018 |
"Microsoft Surface Studio 2 Review: A Brawny, Shape-Shifting PC | WIRED"
|
"https://www.wired.com/review/microsoft-surface-studio-2"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Lauren Goode Gear Review: Microsoft Surface Studio 2 Facebook X Email Save Story Microsoft Facebook X Email Save Story $3,499 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 8/10 Open rating explainer Clear your desk: Microsoft’s Surface Studio 2 is here. Actually, you might want to get a new desk. That’s what I had to do, because the Surface Studio’s 28-inch display didn’t fit well on the cluttered desk where I normally sit. All week, WIRED people walked by my (new) desk and said one of two things: Why are you sitting over here? Or, Oh wow, look at that screen.
The Surface Studio 2 is a personal computing workstation, a glossy hulk of a display with a sleek aluminum frame, a minimal base, and a hinge that lets you tilt the touchscreen display so that it hovers, nearly-flat, above your desk. It’s the second-generation Surface Studio— the first one came out in the fall of 2016—and most of its updates are internal. It runs Windows 10 Pro. This is a performance PC, designed for people who do a lot of heavy multimedia work. To an extent, it’s for people who enjoy playing PC games too.
It also costs $3,500. Or really, for a configuration with the maximum amount of memory, $4,200. That price does include the keyboard, mouse, and a Surface Pen, but not the $99 Surface Dial , a puck can you place directly on the Studio’s giant display and turn and press and click to interact with apps. (You really don’t need this dial , though it’s a fun tool to take for a spin, pun intended.) While the Surface Studio 2 isn’t as costly or as powerful as Apple’s $5,000 iMac Pro , the machine that Microsoft is taking direct aim at with this, the price still puts it in the category of you-really-need-to-justify-it computers.
But just look at this thing! (You can’t, because you are not here, staring at the screen alongside me; you’ll have to trust me.) It’s the kind of computer that makes you believe you’ll make great things with it when you’re not, you know, playing Forza or watching Netflix. You’ll be so productive! Think of how much you can fit on the screen, and more importantly, the detail you’ll be able to see. But really: You will work on your life’s oeurve on this computer.
Like the first Surface Studio, the main attraction on the Surface Studio 2 is its 28-inch PixelSense display. That’s Microsoft’s trademarked phrase, and what it means is that there are roughly a bajillion pixels. 13.5 million pixels, to be exact, with a resolution of 4,500 by 3,000 and a brightness level of 515 nits. It has a 3 by 2 aspect ratio, which Microsoft starting using in its Surface computers back in 2014 and has stuck with ever since. (The iMac Pro, in comparison, has a 16:9 aspect ratio.) But the Surface Studio 2’s display is a touchscreen, which means you can move fluidly between the Studio’s Bluetooth keyboard, mouse, and actually touching the screen when the mood strikes you. And the mood will strike you: The screen is so luminous, you’ll want to reach for it. No matter that you’ll smudge up the Gorilla Glass that coats it. You’ll want to tap and swipe your way across it.
The display isn’t dramatically different from the one on the original Surface Studio. It even has the same, inch-thick bezels. But Microsoft has made some improvements. The brightness and contrast have been bumped up. While I didn’t have the two Surface Studio models set up side-by-side for comparison (I would surely need another desk for that), colors showed well in photos in Lightroom and in Adobe After Effects, which my WIRED colleague Paul Sarconi usually works in and which he volunteered to use on the Surface Studio 2.
At the top of the display there’s a Windows Hello facial recognition camera, which, again, was on the first Surface Studio. It’s been working more smoothly than Windows Hello has ever worked on a Surface laptop for me, although let’s assume I’m opening laptops at weird angles sometimes, whereas this is set in position. The display is enclosed in an aluminum chassis, which is attached to the base via two stainless steel arms.
And then there’s the “zero gravity” hinge, named as such because of the way the display appears to hover above the base when you’ve tilted the screen way back. Some of you might recall that Lenovo tried to do this years ago with a 27-inch “tabletop PC” called the IdeaCentre Horizon. Things got awkward, more awkward even than its name suggested. Somehow, when Microsoft first introduced the Studio, it made tilting back a giant touchscreen look sexy. I can tell you in all honesty that I felt almost no need to actually use the Surface Studio 2 in this mode. But I wanted to. Sort of.
Microsoft Surface Studio 2 Rating: 8/10 $3,499 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Microsoft The base, which houses all of the Studio’s most critical components, is a nondescript gray box. All of its ports have been positioned on the back of the base, which means you’re reaching far behind the display to do something as simple as plug in your headphones. Along with that headphone jack, you get an SD card reader, an Ethernet port, four USB 3.0 ports, and one USB-C port. The USB-C port is both a positive addition and an imperfect one. Microsoft has left USB-C off of some of its newer Surface computers, so I’m thankful it’s represented here. But this USB-C port doesn’t support Thunderbolt 3, which would let you connect a variety of different devices to the machine.
The biggest update to the new Surface Studio 2 is its internals. The first Surface Studio shipped with a sixth-generation Core i5 processor in its base model, along with a Nvidia GeForce 965M graphics card. This new Studio ships with a seventh-generation Core i7 chip and GeForce GTX 1060 graphics card, the latter of which is a significant upgrade.
Microsoft Surface Studio 2 Rating: 8/10 $3,499 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED It’s worth noting, though, that the seventh-gen Intel Core processor is already a generation behind , and Microsoft won’t say why it has gone with this chipset rather than using newer, more powerful Intel chips. But Microsoft is standing by its claim that the Surface Studio 2 is the fastest Surface computer it has ever shipped, likely because of the way the CPU and GPU are coupled and because of the change from a slower hybrid disk drive to a full solid-state drive. It’s also offering up to 2-terabytes of storage, and has bumped the base RAM from 8 gigabytes up to 16.
This makes it a PC that’s very capable of supporting power-hungry media projects as well as console-level gaming, even if it’s not the most powerful workstation on the market. It easily handled Forza Horizon 4 , which I was lucky enough to play for my job, and Paul said the Surface Studio 2 was a dream to work on for an afternoon using AfterEffects. The program was responsive when he called up multiple source files, and his project rendered quickly (“way faster” than it would on his MacBook Pro, he said, though that’s his day-to-day machine that’s been loaded with apps and files at this point.) Do you need the Microsoft Surface Studio 2 for your day-to-day work? Probably not, unless you’re a serious multimedia professional. Even then, you’ll have to make a critical choice between the Mac and Windows ecosystem, and for some people, that’s a deal-breaker—especially at this price. And as a workstation, it’s not as though the Surface Studio 2 is unparalleled. There is, of course, the iMac Pro.
But in six short years, Microsoft has gone from making accessory hardware to making its own laptops to making a powerful workstation that is an absolute thing of beauty. That’s something I can get behind, impractical for me though it may be.
Microsoft Surface Studio 2 Rating: 8/10 $3,499 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $3,499 at Microsoft Senior Writer X Topics Microsoft Computers Christopher Null Jeffrey Van Camp Adrienne So Lauren Goode Lauren Goode Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,106 | 2,023 |
"Microsoft Surface Laptop Studio 2 Review: Fancy, Expensive, and Very Hot | WIRED"
|
"https://www.wired.com/review/microsoft-surface-laptop-studio-2"
|
"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories.
Close Alert To revisit this article, select My Account, then View saved stories Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Christopher Null Gear Review: Microsoft Surface Laptop Studio 2 Facebook X Email Save Story Photograph: Microsoft Facebook X Email Save Story $2,000 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Rating: 6/10 Open rating explainer Over the past 11 years, Microsoft’s Surface hardware has evolved from a humble tablet running a stripped-down Windows operating system to a massive collection of devices that spans phones, desktop PCs, and tech accessories. Hybrid laptops of course remain the primary focus for the Surface, and these days you’ll find some of the most powerful—and expensive—portables represented under the brand umbrella.
Today Microsoft launches its most ambitious—and, again, expensive—Surface yet: the Surface Laptop Studio 2, a do-it-all hybrid designed for “I need everything” creative types with an unlimited budget and a distaste for MacOS. Building on the success of 2021’s Surface Laptop Studio , there’s no limit to how you can interact with the device. Flip it open and it works like a standard clamshell laptop, or pop the bottom half of the screen out to push it forward into a model called Stage Mode, which covers the keyboard but leaves the trackpad available. Keep pulling the screen toward you and you can lay it down flat against the bottom half of the chassis in a tablet-style setup Microsoft calls Studio Mode.
Both of the latter two modes are designed for interacting directly with the touchscreen, though if you want to use a stylus instead of a finger, note that the new Surface Slim Pen 2 is no longer included with the device. You’ll need to drop another $130 for that, which illustrator types will probably want to do, as it can attach and charge wirelessly when magnetically clipped to the laptop. I didn’t receive one for testing.
Design-wise, the Laptop Studio Pro 2 is similar to the original Laptop Studio, only more.
The weird pedestal design remains, with the keyboard tray jutting out over a thick base that is recessed on all sides. This base is vented on both the right and left sides of the laptop; otherwise all heat dissipation occurs through the anodized aluminum frame. (More on this later.) It is a very strange and unique design that makes the laptop look like it’s floating above the desk when viewed from an angle, though when you pick it up, the heft of the machine will quickly dissuade you of its ability to levitate.
The Surface Laptop Studio 2's design enables a number of configurations.
Photograph: Microsoft The screen remains a focus of the Studio 2, and it’s still a 14.4-inch touchscreen model with 2,400 x 1,600-pixel resolution (which works out to a tall 3:2 aspect ratio). The screen is bright but not blinding, and touch controls are responsive and accurate. I don’t wholly love the keyboard, but it ultimately feels about average in today’s laptop world. Audio quality is exceptional, including a beefy subwoofer that offers ample bass punch. And the haptics-enabled touchpad remains a standout in the field; using it for any amount of time makes it tough to go back to a standard touchpad.
While the surface of the Surface is mostly the same, a whole lot of work has been done under the hood, giving the Studio 2 a well-advertised “2X the power” over … well, Microsoft doesn’t say over what, but it’s twice the power, so don’t worry about it. When I threw benchmarks at it, I didn’t really find a good comparison for what “2X the power” might relate to. On general business apps, it had exactly 1X the power of the Acer Swift Edge 16, a $1,000 AMD-based system that I just tested last week. It however had up to 4X the power of the same Acer laptop when it came to graphics-heavy tests and gaming-related benchmarks. If you’re hoping to be blown away by how fast the Studio 2 recalculates spreadsheets, you might be disappointed, but on GPU-heavy work, the system is right up there with some of the best on the market.
All of this is made possible by state-of-the-art components, which included (on my test unit) a 2.9-GHz Core i7-13700H processor, a massive 64 GB of RAM, and an Nvidia GeForce RTX 4060 graphics processor. The addition of Intel’s Gen3 Movidius 3700VC VPU AI Accelerator is designed to help power the new Copilot tool that’s being pushed out to Windows 11 PCs. I doubt many will get an immediate benefit from this addition—Microsoft says it will help make videoconferencing look better in some subtle ways—but the world of generative artificial intelligence tools is changing so rapidly that it isn’t something I’ll sniff at.
Microsoft Surface Laptop Studio 2 Rating: 6/10 $2,000 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED Connectivity includes two USB-C ports with USB4/Thunderbolt 4 support, one USB-A port, and a microSD card reader. The unit uses Microsoft’s long-running Surface Connect magnetic charger, and you’ll find an additional USB-A port on the charger box as well. Note: The unit can also charge via one of its USB-C ports but at a slower rate than you’ll get with the approved magnetic charger.
All of this stuff, of course, comes at a price. The first is portability: At 4.3 pounds and 24-mm thick, the computer looks big and feels big. It weighs more than any other laptop in the 14-inch class that I’ve seen since 2014. Microsoft says it is prioritizing performance over portability here in response to customer demands, and to be sure there are many more-portable Surface devices on the market. The design has also taken a serious toll on battery life. While we clocked the previous Laptop Studio at 12 hours on a looped-video battery drain test, I managed to get only 4 hours, 12 minutes on the new Studio 2. I doubt many users of this device will ever be far from a power outlet, but it’s something to keep in mind.
And by the way, that 2X performance also has an impact on your lap. Despite a new heat-dissipation system and new “thermal capacity performance”—which add weight—the laptop can get hot. Really hot. Under even moderate loads (like web browsing), the palm rest quickly gets warm to the touch, but the exhaust blasting out the sides of the device gets even hotter. I measured this heat at a peak of 109 degrees Fahrenheit, which is hotter than a jacuzzi should be. That might be a nice plus in the dead of winter, but for most users I think it will be alarming and uncomfortable. (Oddly, the fan is very quiet even at peak load, muffled perhaps under all that aluminum.) The other cost you’ll face here is of course the literal one: The Surface Laptop Studio 2 starts at $2,000 and tops out at a whopping $3,700. The system I tested, as configured above, is priced at a cool $3,300, which makes it the most expensive laptop I’ve reviewed in a decade. I may not be the target market for this machine—I just bought a $1,300 ultralight—but even if I had zero restrictions on budget, I don’t know that I’d opt for a device with this many caveats, no matter how fancy the display and touchpad are.
Microsoft Surface Laptop Studio 2 Rating: 6/10 $2,000 at Microsoft If you buy something using links in our stories, we may earn a commission. This helps support our journalism.
Learn more.
Please also consider subscribing to WIRED $2,000 at Microsoft Topics Shopping review Microsoft Surface laptops Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,107 | 2,022 |
"If You Know These Keyboard Shortcuts, You Won't Need a Mouse | WIRED"
|
"https://www.wired.com/story/quick-select-keyboard-shortcuts-no-mouse"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter David Nield Gear If You Know These Keyboard Shortcuts, You Won't Need a Mouse Photograph: Eggy Sayoga/Getty Images Save this story Save Save this story Save The mouse and the trackpad are pretty fundamental to how we use our computers, but what if you're unable to use a mouse or a trackpad in the usual way? Or if your mouse or trackpad malfunctions? You can actually do just about everything you use a mouse and trackpad for using your keyboard, if you know the right shortcuts.
Underlined characters show you which key to press to make selections.
Windows via David Nield In Windows, the keyboard shortcuts you can use instead of a mouse or trackpad start off simple and can get quite advanced—to begin with, of course, there's the Win button to open the Start menu, the Alt+Tab shortcut to switch between your open applications, and Alt+F4 to close down programs.
If you're inside a menu, program, or website, you can use Tab to jump between sections or fields, and the arrow keys to go Up , Down , Left, or Right.
You can search your computer with Win+S , or open the File Explorer interface with Win+E.
Use Enter to confirm choices and make selections and Esc to exit out of menus and dialogs.
To control the behavior and position of open application windows, Win+Up maximizes them and Win+Down minimizes them. You can also tap Win+Left or Win+Right to snap the current window to the left or the right of the screen.
Alt+Space gives you more options, including the ability to move windows (using the arrow keys).
A couple of other keyboard shortcuts that you might not have come across: If you're not actually typing anything, you can use Space to scroll down long web pages or open documents. Also, if you need to access a right-click context menu without a mouse or a trackpad, Shift+F10 is the keyboard combination you're looking for.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft As you move through menus and dialogs, you'll often see certain characters underlined, tipping you off to the fact that the key can be used to select the item directly—this can save you a lot of time tapping around with the arrow keys. If you're selecting text, meanwhile, use Shift and an arrow key; to move one word at a time, use Shift+Ctrl and an arrow key.
In addition, some keyboard shortcuts work in a similar way across all Windows programs: Think Ctrl+C to copy, Ctrl+V to paste, Ctrl+S to save, or Ctrl+A to select everything in a section or on screen, for example. The Ctrl+W combination usually closes down whatever it is you currently have open, be it a browser tab or a document. Dig deeper into your individual programs, and you'll find they all have bespoke keyboard shortcuts—and for even more shortcuts, check out Microsoft's list.
One final tip: If your keyboard has a numeric keypad at the side, go to Settings and choose Accessibility and Mouse , and then enable Mouse Keys.
This lets you control the on-screen cursor using the keypad on your keyboard (so 8 moves the cursor up, 2 moves the cursor down, and so on).
Mouse Keys lets you control the pointer with a numeric keypad.
Apple via David Nield A lot of keyboard shortcuts work the same across Windows and macOS, so some from the previous section apply to a Mac as well. Shortcuts that work the same include Cmd+C to copy, Cmd+V to paste, Cmd+S to save, and Cmd+A to select everything in the current field or document. You can also use Cmd+W to close down the current browser tab, document, or Finder window.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Other keys that work the same on macOS and Windows are the arrow keys to maneuver around menus and dialog boxes, the Tab key to jump between text fields and program sections, and Space to scroll down webpages and documents, as long as you're not inputting text. Use Esc to go back and Enter to confirm or select something.
As for switching between open apps, that changes to Cmd+Tab if you're on Apple's operating system, and you can also press Cmd+Space to search your Mac.
Ctrl+F2 will switch the focus to the menu bar, and Ctrl+F3 brings up the dock (if you're using a keyboard with the Touch Bar, you need Ctrl+Fn+F2 and Ctrl+Fn+F3 ). Once the focus has been moved, you can make use of the arrow keys, Esc , and Enter as needed. You can also use Cmd+ to open the preferences pane for the current app.
The text selection shortcuts are similar to those on Windows because you can hold down Shift and then use the arrow keys to select text. If you want to select one word at a time, use Shift+Option and the arrow keys. When it comes to managing open program windows, meanwhile, Cmd+M will minimize the currently selected window, but there's no built-in keyboard shortcut for maximizing windows.
Some menu items inside programs will have their own keyboard shortcuts, which will be displayed on the menus themselves where they're available—it pays to remember what these are, as it can really speed up your day-to-day computing in the applications you use the most. For a host of other useful shortcuts, you can consult Apple's list.
There are also some accessibility tweaks in macOS that make it easier to use your keyboard as a replacement for a mouse or a trackpad. Open System Preferences, then choose Keyboard and Shortcuts.
Check the box marked Use keyboard navigation to move focus between controls to make Tab more universal as a way of moving focus (and Shift+Tab for going in the opposite direction).
You can also take full control over the pointer with the keyboard. From System Preferences, choose Accessibility , Pointer Control , and Alternative Control Methods , then check the Enable Mouse Keys box. If you have a numeric keypad on your keyboard, you can then use it to move the pointer ( 4 to go left, 6 to go right, and so on.) 📩 The latest on tech, science, and more: Get our newsletters ! The metaverse-crashing life of Kai Lenny Indie city-building games reckon with climate change The worst hacks of 2021 , from ransomware to data breaches Here's what working in VR is actually like How do you practice responsible astrology? 👁️ Explore AI like never before with our new database ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers Contributor X Topics operating systems software tips how-to Eric Ravenscraft David Nield Eric Ravenscraft Eric Ravenscraft Simon Hill Julian Chokkattu Brendan Nystedt Louryn Strampe WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,108 | 2,020 |
"How to Back Up and Move Your Photos Between Services | WIRED"
|
"https://www.wired.com/story/backup-google-photos-facebook-icloud-onedrive-dropbox"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter David Nield Gear How to Back Up and Move Your Photos Between Services Photograph: Apple Save this story Save Save this story Save Most of us now have our digital photos and videos automatically backed up to the cloud.
It means they can be accessed from any device, and are kept safe and sound should something happen to your smartphone or laptop.
What happens, though, when your photo storage platform of choice changes its features, or its prices , or goes out of business completely? It's vital to have an exit strategy in place, just in case—if only to keep your precious files backed up somewhere else.
We can't cover the process for every service out there, but we can give you guidelines for five of the most popular ones. If you're using something different, you should be able to find export options somewhere in the interface.
You can download some or all of your Google Photos albums.
David Nield via Google Google actually makes it relatively easy to get your stuff downloaded and moved elsewhere, whether that's emails in Gmail or images you've uploaded to Google Photos. With the free storage tier disappearing next year , you might be looking to move your pictures and videos to another service, and with Google Photos it's not difficult to do.
To get at your files, go to your Google Account page on the web. Once you've signed in, click Data & personalization , and then Download your data. You'll see all the various Google apps and services listed, so just tick the Google Photos option, and use the All photo albums included button if you only want to download certain albums.
Click Next step to set some export options (you can save the exported files to disk or add them to Google Drive, for example), and then click Create export.
If you've chosen the Send download link via email option, you'll be sent an archive of your photos and videos over email.
Make sure all your photos and videos are downloaded to your Mac.
David Nield via Apple Apple is very keen that you should use its photo storage service—and its music service, and its mapping service, and its messaging service—rather than anyone else's, and there aren't really any options to get your files out of Apple Photos on iCloud like there are in Google Photos. You can download individual photos and videos from iCloud on the web , but that's likely to take you a long, long time.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Your best approach here is to install the app you want to transfer your photos and videos to on your iPhone, iPad, or Mac, and forget about the intermediate step of downloading all your files to a computer. You need to make sure all your photos and videos are stored on your device of choice though, not in the cloud. To do this, go to iOS Settings and choose Photos then Download and Keep Originals , or open Photos on macOS and choose Photos , Preferences , iCloud , and Download Originals to this Mac.
If you know all your photos and videos are on your computer or mobile device, you can move them somewhere else by installing the relevant app: Dropbox for iOS or macOS , for example, or OneDrive for iOS or macOS.
If you have access to a Windows computer, you can use iCloud for Windows to sync all your files to the local hard drive before uploading them somewhere else.
OneDrive on Windows lets you choose which folders are synced locally.
David Nield via Microsoft Like Apple Photos and unlike Google Photos, OneDrive doesn't have a mass export tool to download all of your photos and videos in one go. You can select and download bunches of files via the web interface or the mobile app, but if you've got thousands of pictures and video clips to transfer, it's not really practical to transfer them all like this.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So If you're using OneDrive for your files, we're assuming you have access to a Windows laptop or desktop. You can make sure all of your photos and videos are synced locally to this computer by opening OneDrive in File Explorer, then right-clicking on the folders holding your images and videos and choosing Always keep on this device.
You can then install another app— Dropbox , Google Backup and Sync , iCloud for Windows —and point it towards these OneDrive folders.
If you use a Mac instead of a Windows computer, use the OneDrive client for macOS to get all of your photo and video folders synced to your local drive instead. Once the sync has completed, you can move the pictures somewhere else (choose File and Import to load them into the Photos app and iCloud on your Mac, for instance).
Dropbox lets you sync files to your computer or download them from the web.
David Nield via Dropbox While Dropbox doesn't offer a mass downloading tool for all your photos and videos, it does at least let you download entire folders at once through the web interface : Click the three dots next to the folder you want to save to disk, then Download, and all of its contents can be saved to your computer in an archived zip file, ready to be moved somewhere else.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So If you have the Dropbox client installed on your Windows or macOS computer then all of your photos and videos might well be already saved to disk anyway. Open the Dropbox app, click on your username (bottom left), then choose Preferences and Sync to make sure the folders you need (with your photos and videos in them) are currently being synced to the hard drive.
Once your images and video clips are safely saved to your computer, you can get them moved somewhere else: You can move them into the Photos app on a Mac for example (File then Import) or install the Google Backup and Sync desktop program and get them sent to Google Photos.
With just a few clicks you can download a copy of your Facebook photos and videos.
David Nield via Facebook If you need to get your photos and videos out of Facebook, open up the Facebook Settings page on the web, and choose Your Facebook information.
Click View next to Download your information , and you're then able to see everything Facebook holds on you: From all the comments you've ever made on the social network to all the Facebook events that you've ever committed to.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Tick the Photos and videos option, and make sure the Media quality option is set to High , then choose Create File.
Once Facebook is done collecting all your files, you'll be emailed a download link—this link will give you a copy of all your photos and videos that you can download to your computer, ready to be moved somewhere else.
Back on the Settings page, you can also click Your Facebook information and then View next to Transfer a copy of your photos and videos : The subsequent screen lets you transfer your files directly to another cloud service, without any downloading in between. Dropbox and Google Photos are two of the services supported.
📩 Want the latest on tech, science, and more? Sign up for our newsletters ! Google Photos storage is changing.
Here are your best options A Navy SEAL, a drone, and a quest to save lives in combat There’s something super weird about Netflix anime The history of poop is really the history of technology Thinking about holiday parties? Look at this troubling map 🎮 WIRED Games: Get the latest tips, reviews, and more 🎧 Things not sounding right? Check out our favorite wireless headphones , soundbars , and Bluetooth speakers Contributor X Topics cloud tips how-to Brenda Stolyar Julian Chokkattu Justin Pot Simon Hill Simon Hill David Nield Jordan McMahon Julian Chokkattu WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,109 | 2,023 |
"How to Use Your Smartphone to Counteract Vision Loss (2023): iPhone, Android, Apps | WIRED"
|
"https://www.wired.com/story/smartphone-features-blind-vision-impairment"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Simon Hill Gear How to Use Your Smartphone to Counteract Vision Loss Photograph: Flashpop/Getty Images Save this story Save Save this story Save Vision loss is common and is highly likely to impact you or someone close to you in your lifetime. The World Health Organization estimates that 2.2 billion people worldwide have a near- or distant-vision impairment. Around 12 million Americans aged 40 years and up have some vision loss today, according to the Centers for Disease Control and Prevention , and 4.2 million of those have uncorrectable vision impairment (1.02 million are blind), a number that the CDC expects to double by 2050, due to the rise in diabetes and other chronic diseases.
Whether you struggle to read distant signs or find yourself squinting to decipher small print, you probably have a gadget that can help. Too many of us ignore accessibility features, assuming they are only for the blind or severely vision-impaired, but they can also help folks with a wide range of vision loss issues.
Below, I’ve highlighted several smartphone features I tested with the help of family and friends with varying degrees of vision loss. I also spoke to Apple and Google to learn more about these features in iPhones and Android. Both companies claim they work with blind and vision-impaired communities to gather feedback and new ideas.
Updated February 2023: We added Android's new Reading Mode and instructions for using Reader in Safari on an iPhone.
Ways to Protect Your Vision How to Customize Your Display How to Use Reading Mode How to Magnify or Zoom How to Get Audio Descriptions How to Use Voice Commands How to Identify Objects, Doors, and Distances How to Take Better Selfies How to Get Help Gaming Final Tips There are many causes of vision loss. The CDC estimates that 93 million adults in the US are at high risk for serious vision loss. Because diabetes is a major cause of preventable vision loss, it’s crucial to manage your blood sugar, blood pressure, and cholesterol. Stay healthy with fitness apps and trackers or smartwatches.
If you are staring at screens all day, you should look into how to prevent eye strain.
The 20-20-20 (every 20 minutes, look at something 20 feet away for 20 seconds) rule is a simple technique. Reducing brightness (Android and iOS have sliders) is a good idea in darker environments, and you might even try dark mode or gray scale.
We’ll run through deeper display customization for your smartphone in a moment.
You should also wear protective eyewear for sports or dangerous activities and consider the best sunglasses when you go outdoors.
The first thing most people should do is customize their display settings to make the screen and text as legible as possible. On an Android phone, go to Settings > Display, and you can tweak things like brightness, colors, and theme. Make sure you tap Display Size and Text to choose a font size, icon size, and bold or contrasting text that works for you. Some folks with sensitivity to light, vision loss, or color blindness find dark modes, inverted colors, and different contrasting combinations boost clarity and comfort.
Google via Simon Hill Google via Simon Hill On an iPhone, go to Settings and tap Display & Brightness to find similar options. You can dig deeper in Settings > Accessibility > Display & Text Size to invert colors, apply filters, and more. Some people will also benefit from tapping Motion in Accessibility and toggling on Reduce Motion.
1 / 3 Anyone with an Android device can try Reading mode to remove ads, menus, and other website clutter and get streamlined versions of online articles that only display the important text and images. Reading mode was designed for people with low vision, blindness, and dyslexia. You can use it to customize your screen-reading experience by tweaking color, text size, spacing, and font types. Reading mode also offers text-to-speech.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft If it hasn't popped up on your Android device, download the Reading mode tool from the Play Store. Go to Settings > Accessibility and tap Reading mode and then Allow to turn it on. When you want to use it, simply tap the onscreen accessibility button. You can customize how it looks via the gear icon at the bottom left, hit the play button to have it read aloud, and increase or decrease text size by tapping the icon at the bottom right.
For a similar option on the iPhone, open a web article that you want to read in Safari and tap the AA icon at the bottom left, then select Show Reader.
If you tap AA again, you can change the background color, font, and text size. You can also tap Website Settings and toggle on Use Reader Automatically for the website you’re visiting.
Even after customizing your display, there may be times when you want to magnify something on the screen. Thankfully, there are built-in options to do just that. On the iPhone, go to Settings > Accessibility > Zoom to configure different magnification settings for text and other content on your iPhone screen. With Android phones, go to Settings > Accessibility and tap Magnification to turn on the shortcut. You can choose full-screen magnification (including zooming in temporarily), partial-screen magnification, and magnifying text as you type.
What if you want to zoom in on objects or signs around you? The built-in camera app on your phone can zoom in, but the clarity of the close-up will depend on the quality of your phone’s camera. You can pinch to zoom, and zoom levels appear as numbers (like 2X) at the bottom of the camera view. If you press and hold on the zoom level, you get pop-up controls showing the full range of zoom options. But any movement while zoomed in can make it hard to read or examine details.
You can also use the Magnifier app on every iPhone (search or find it in the Utilities folder in your App library). Point it at whatever you want to see and zoom in using the slider. Tap the cog at the bottom left, choose Settings to decide which controls you want to include, and select filters to make things more readable. We will discuss the handy Detection Mode and some of the other features of the Magnifier app in the “How to Identify Objects” section below.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft There's no built-in equivalent on Android, but Android phone owners can choose from several popular magnifier apps in the Play Store, such as Magnifier + Flashlight.
Screen readers describe what is on your device screen and tell you about alerts and notifications.
The Android screen reader is called TalkBack, and it can be turned on via Accessibility > TalkBack > Use TalkBack.
You can also say, “Hey Google, Turn on TalkBack” or use the volume key shortcut (press and hold both volume keys for three seconds). With TalkBack on, you can touch the screen and drag your finger around to explore as TalkBack announces icons, buttons, and other items. You simply double-tap to select. To customize things like the verbosity, language, and feedback volume, tap the screen with three fingers or swipe down and then right in one stroke (gesture support depends on your device and Android version) and select TalkBack Settings.
You can also turn on the virtual braille keyboard in these settings, and Google beefed up out-of-the-box support for braille displays in TalkBack with the Android 13 update.
Google via Simon Hill Google via Simon Hill Select-to-Speak is another Android feature that might be of interest. It provides audio descriptions of items on your screen, like text or images, and enables you to point your camera at pictures or text to hear them read or described aloud in certain languages. Turn it on via Settings > Accessibility > Select-to-Speak.
Once activated, you can access it with a 2-finger swipe up (3-finger swipe if TalkBack is on). Tap an item or tap and drag to select multiple items and tap Play to hear them described.
Apple’s screen reader is called VoiceOver, and you can find it in Settings > Accessibility , where you can set your preferred speaking rate, select voices for speech, set up braille output, and configure many other aspects of the VoiceOver feature. Tap VoiceOver Recognition to have images, whatever is onscreen in apps, and even text found in images described to you.
Apple via Simon Hill If VoiceOver is more than you need, consider going to Settings > Accessibility > Spoken Content , where you will find three potentially handy options. Toggle on Speak Selection to have a Speak button pop up when you select text. Toggle on Speak Screen to hear the content of the screen when you swipe down from the top with two fingers. Tap Typing Feedback and you can choose to have characters, words, auto-corrections, and more spoken aloud as you type.
For audio descriptions of video content on an iPhone, go to Settings > Accessibility and turn on Audio Descriptions.
On an Android phone, it’s Settings > Accessibility > Audio Description.
You can use voice commands to control your phone. On iPhone, go to Settings > Accessibility > Voice Control and tap Set Up Voice Control to run through your options and configure voice controls. On Android devices, go to Settings > Accessibility > Voice Access and toggle it on. If you don’t see the option, you may need to download the Voice Access app.
You can also dictate text on Android phones or iPhones by tapping the microphone icon whenever the keyboard pops up.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft If full voice control is a bit much, you might use Siri on iPhone and Google Assistant on Android to open apps, tweak settings, and more. You likely set up Siri when you first set up your iPhone, but there are a couple of settings that can make Apple’s voice assistant more useful for folks with vision loss. Go to Settings > Accessibility > Siri , and consider some changes. If you turn on Always Listen for “Hey Siri” , your iPhone will listen even when it’s face down or covered. You can also lengthen the time Siri waits for you to finish speaking under Siri Pause Time , you can toggle on Prefer Spoken Responses , and you can toggle on Announce Notifications on Speaker.
Apple via Simon Hill To make similar changes to Google Assistant go to Settings > Google > Settings for Google Apps > Search, Assistant and Voice , and choose Google Assistant.
You may want to tap Lock Screen and toggle on Assistant Reponses on Lock Screen.
If you scroll down, you can also adjust the sensitivity, toggle on Continued Conversation , and choose which Notifications you want Google Assistant to give you.
First launched in 2019 , the Lookout app for Android enables you to point your camera at an object to find out what it is. This clever app can help you to sort mail, identify groceries, count money, read food labels, and perform many other tasks. The app features various modes for specific scenarios: Text mode is for signs or mail (short text).
Documents mode can read a whole handwritten letter to you or a full page of text.
Images mode employs Google’s latest machine-learning model to give you an audio description of an image.
Food Label mode can scan barcodes and recognize foodstuffs.
Currency mode identifies denominations for various currencies.
Explore mode will highlight objects and text around you as you move your camera.
The AI-enabled features work offline, without Wi-Fi or data connections, and the app supports several languages.
Apple has something similar built into its Magnifier app.
But it relies on a combination of the camera, on-device machine learning, and lidar. Unfortunately, lidar is only available on Pro model iPhones (12 or later), iPad Pro 12.9‑inch (4th generation or later), and iPad Pro 11‑inch (2nd generation or later). If you have one, open the app, tap the gear icon, and choose Settings to add Detection Mode to your controls. There are three options: Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft People Detection will alert you to people nearby and can tell you how far away they are.
Door Detection can do the same thing for doors, but can also add an outline in your preferred color, provide information about the door color, material, and shape, and describe decorations, signs, or text (such as opening hours).
This video shows a number of Apple's accessibility features, including Door Detection, in action.
Apple via Simon Hill Apple via Simon Hill Image Descriptions can identify many of the objects around you with onscreen text, speech, or both. If you are using speech, you can also go to Settings > Accessibility > VoiceOver > VoiceOver Recognition > Image Descriptions and toggle it on to enable detection mode to describe what is depicted in images you point your iPhone at, such as paintings.
You don't need a Wi-Fi or data connection to use these features. You can configure things like distances, whether you want sound, haptics, speech feedback, and more via the Detectors section at the bottom of Settings in the Magnifier app.
Guided Frame is a brand-new feature that works with TalkBack, but it's currently available only on the Google Pixel 7 or 7 Pro.
People who are blind or low-vision can capture the perfect selfie with a combination of precise audio guidance (moving right, left, up, down, to the front, or the back), high-contrast visual animations, and haptic feedback (different vibration combinations). The feature tells you how many people are in the frame, and when you hit that “sweet spot” (which the team used machine learning to find), it counts down before taking the photo.
The Buddy Controller feature on iPhone (iOS 16 and later) allows you to play along with someone in a single-player game with two controllers. You can potentially help friends or family with vision impairment when they get stuck in a game (make sure you ask first). To turn this feature on, connect two controllers and go to Settings > General > Game Controller > Buddy Controller.
While this guide cannot cover every feature that might help with vision impairment, here are a few final tips that might be handy.
You can get spoken directions when you are out and about on an Android phone or iPhone, and they should be on by default. If you use Google Maps, tap your profile picture at the top right, choose Settings > Navigation Settings , and select your preferred Guidance Volume.
Both Google Maps and Apple Maps offer a feature where you can get a live view of your directions superimposed on your surroundings by simply raising your phone. For Apple Maps, check in Settings > Maps > Walking (under Directions ) and make sure Raise to View is toggled on. For Google Maps, go to Settings > Navigation Settings, and scroll down to make sure Live View under Walking Options is toggled on.
If you are browsing the web on an Android device, you can always ask Google Assistant to read the web page by saying, “Hey Google, read it.” You can find more useful advice on how technology can support people with vision loss at the Royal National Institute of Blind People (RNIB).
To find video tutorials for some of the features we have discussed, we recommend visiting the Hadley website and trying the workshops (you will need to sign up).
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Contributor X Topics vision accessibility ios Android how-to phones Julian Chokkattu Boone Ashworth Boone Ashworth Julian Chokkattu Simon Hill Michael Calore Simon Hill Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,110 | 2,022 |
"How to Use Passkeys in Google Chrome and Android | WIRED"
|
"https://www.wired.com/story/how-to-use-passkeys-google-chrome-android"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons David Nield Security How to Use Passkeys in Google Chrome and Android Illustration: Andriy Onufriyenko/Getty Images Save this story Save Save this story Save Google recently announced that passkey support is coming to both the Android operating system and the Google Chrome web browser—and if you're wondering exactly what that means, you're in the right place. Passkeys are essentially a replacement for passwords that are designed to be more secure. You use them instead of traditional passwords to get into your various digital accounts, whether that's Google, Twitter, Dropbox, or anything else.
You don't get an actual key. Instead, some kind of unlocking mechanism—typically facial recognition or fingerprint recognition, or just a PIN code—is used to prove you are who you say you are for the purposes of logging in.
However, it's not just a case of pressing a button and switching over. Developers need to also code passkey support into their apps and websites, which is why Google made the announcement on its Android Developers Blog.
The move is part of a broader industry push toward a passwordless future—you might have noticed that Microsoft is doing something similar.
Users don't have to remember passwords, and there aren't any passwords for hackers to steal.
You'll soon be able to create passkeys on your Android devices.
Google via David Nield As Google puts it , a passkey “identifies a particular user account on some online service.” At its center is a cryptographic private key that gets stored on the devices you use. This is then matched against a public key held by the digital services you're signing into to confirm your identity.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To make sure it's really you, you'll need to unlock your phone or computer, which on a phone usually means entering a PIN code or letting your face or fingerprint get scanned. On computers, passwords may still be used to verify your identity, but the industry is moving toward biometric authentication all the time.
You don't actually see the passkey itself or need to know what it is—you just have to be you. Your face or fingerprint replaces that long list of passwords on a Post-it note that you might have, so it's much simpler and more convenient.
These passkeys use public-key cryptography, so if they're involved in a data breach, they're useless to bad actors without your face or your fingerprint. Similarly, if your laptop or phone gets stolen, your accounts can't be accessed because you're not going to be around to provide the necessary authentication.
This isn't just a Google initiative. Organizations such as the FIDO Alliance and the W3C Web Authentication group are busy working toward a passwordless future as well, so you'll be able to use these systems across any device, whether made by Google, Apple, Microsoft, or any other hardware maker.
Biometric authentication can be used in place of a password.
Google via David Nield The good news is that using passkeys is as easy as unlocking your phone—it's intended to be as straightforward as possible. You'll be able to choose to move to a passkey system for your accounts, but only when the app you're logging in to and the device you're using have been upgraded with passkey support.
Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Let's say Google has finished rolling out passkey support to Android, you're logging in to an app that has been updated to use passkeys, and you've said yes when prompted to make the switch from a standard password. You'll then be asked to create a passkey, which will involve you having to do the same action you do to unlock your phone—show your face, press down your fingerprint, or enter a PIN. That creates the passkey and authenticates the link between the app in question and the device in your hand. Whenever you need to log in to that app in future, you'll need to go through the same unlock process. As with passwords, how long that authentication lasts will vary: With your banking app, you'll usually have to log in every time, whereas with a social media account one login per device is often enough.
You'll also be able to log in to sites on your computer through your phone via the magic of a QR code. The site will display a QR code that you scan with your phone—once you've gone through the unlock process on your mobile device, your identity will be confirmed and you'll be logged in to the site.
Encrypted synchronization across devices will also be handled—Google Password Manager is adding support for passkeys, for example, so should you lose access to one device, you can still get at your accounts from another one or from the cloud, assuming you're able to provide the necessary authentication (and you haven't changed your fingerprints or face in the meantime).
You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Contributor X Topics Passwords identity encryption Chrome Android Lily Hay Newman Kate O'Flaherty Andrew Couts Justin Ling David Gilbert Dell Cameron Andy Greenberg Lily Hay Newman Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,111 | 2,018 |
"How to Share and Store Pictures with Google Photos, Dropbox, AirDrop, and More | WIRED"
|
"https://www.wired.com/story/how-to-share-photos-airdrop-google-photos-dropbox"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter Pia Ceres Gear How to Share and Store Your Photos in the Cloud Hotlittlepotato; Getty Images Save this story Save Save this story Save Minimalism is nice, but when it comes to special occasions—family gatherings, vacations, that once-in-a-lifetime concert—you’ll want to capture every single detail. The smartphone camera in your pocket not only takes great photos , but lets you share them quickly with all your loved ones. Cloud storage also ensures that you have a backup in case of a hard drive crash, or if you lose your phone. You can store pictures of everything, and we truly mean everything: the picturesque turkey, your little nephew's gap-toothed grin, your distant uncle who likes to point out that you used to be thiiiis tall.
So whether your loved ones are finally together for the holidays, or you're jetting off for a long-awaited getaway, here are some of the best ways you can share a ton of photos, then store them for later reminiscing. There are a handful of options out there to suit your needs and your devices. Our favorite is Google Photos, which does it all and does it best.
File hosting service Dropbox has a 2GB limit for free users. Create a folder on the website or on your Dropbox app (free, iOS and Android ). Upload photos from Great Aunt Barbara’s birthday party, select “Share,” then add the email addresses of everyone in your extended family. The recipients don’t need a Dropbox account to view or download the photos, but they’ll need one to add photos of their own.
Amazon Prime members can store and share unlimited full-res photos with Amazon Photos.
Set the Amazon Photos app (free, iOS and Android ) to auto-save photos from your phone camera. You can share your unlimited photo storage with up to five other people in your Family Vault. You can also share links to your photos and albums with anyone, even if they're not Prime members.
If you already use iCloud to back up your data, you can use that for photo storage and sharing as well. Head to Settings > Photos on your iPhone or iPad, then switch on “iCloud Photos.” By default, you get 5GB of free storage, with the option to buy more. Want to share them, too? Switch on “Shared Albums.” In the Photos app, from the Albums tab, you can create a new shared album with friends and family. Select the photos that you want to share, tap the share icon in the bottom left corner, and choose the album. Shared albums hold a maximum of 5,000 photos and videos, so coordinate the photos of your trip to Disneyland accordingly.
Another neat trick for iPhone users: Photo sharing with friends nearby is a cinch with Airdrop. First, make sure that the recipient has Airdrop on by going into Settings > General > AirDrop and select your receiving options. Opt to receive photos from “Contacts Only” or “Everyone.” To send photos, select the photos, then tap the share icon in the bottom left corner. Choose the recipient’s name, and voila! Instant shared photos. Just remember to set AirDrop back to “Contacts Only” after you’re done sharing, to avoid any unsavory trolls.
Of the multitude of options out there, we think Google Photos outpaces them all. It’s free, works on any device, and gives you unlimited storage, as long as you don’t mind your photos being compressed. Plus, Google Photos’ machine learning and AI tools help organize your photos and find exactly the images you need.
Download the Google Photos app (free, iOS and Android ) and sign in to your Google account. You'll be prompted to turn on "back up and sync," which automatically saves photos and videos you take on your phone to your Google Photos library when you have internet access. It's wise to keep this handy feature on, so that even if your phone takes a dunk in the beautiful seas of Sayulita, you'll still have a backup of all of your vacation photos in your Google account.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So The app recognizes people and pets, which means you don’t have to spend hours tagging individual photos. It can even suggest contacts for you to share, say, a group selfie with. Need to find a specific shots? Narrow down your library with search terms like “prom 2013” or “city at night.” Google’s “smart” features make it a breeze to make and share albums. On the Albums tab, select “New Album.” Here, you can populate the album with selected photos from your library, or automatically add photos of selected people and pets. If you want to make an album devoted to hanging out with your grandparents, select the thumbnails of their faces, and see photos of your dear ones appear right in your album. When you want to share the album, tap the ··· icon in the upper right corner. Select “Options,” where you can access a link to share your album. You can also decide whether you want to make this a collaborative album, so recipients can add their own photos of Gram and Pops.
Finally, if you want to share your photos with a partner who has a Google account, tap “Add partner account” from the menu. You can grant them access to all of your photos, or photos of specific people.
No matter which option you choose, the best part of storing photos in the cloud is having the freedom to take as many photos as your heart desires—so you can capture every moment of the soccer tournament, document your heirloom tomato garden, and re-take family photos until everyone has their eyes open. (OK, almost everyone.) Storing your photos on a cloud not only makes them easier to share with loved ones, but more secure for you, so keep all your favorite memories, and share them again and again.
This chemical is so hot it kills nerve endings.
Good! So you're thinking of deleting your tweets.
Should you? The Hail Mary plan to restart a hacked US electric grid Does Latinx Twitter exist? My dad says he’s a “ targeted individual.
” Maybe we all are Looking for more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Digital Producer X Topics how-to Julian Chokkattu Brenda Stolyar Julian Chokkattu Justin Pot Boone Ashworth Simon Hill Julian Chokkattu Simon Hill WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
2,112 | 2,022 |
"How ‘Buy Now, Pay Later’ Really Works | WIRED"
|
"https://www.wired.com/story/gadget-lab-podcast-576"
|
"Open Navigation Menu To revist this article, visit My Profile, then View saved stories.
Close Alert To revist this article, visit My Profile, then View saved stories.
Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter WIRED Staff Gear How ‘Buy Now, Pay Later’ Really Works Illustration: Jacqui VanLiew; Getty Images Save this story Save Save this story Save Money is tight these days. Holiday shopping, ballooning inflation, and a looming recession have forced people to more carefully consider their finances. Those factors might help explain the explosion of “buy now, pay later” services. BNPL plans offered by companies like Affirm, Afterpay, and Klarna let you spread the cost of a purchase—anything from a Peloton bike to a basket of groceries—over multiple installments, without the fees or interest rates of most credit cards. Of course, free money always comes with a catch.
This week on Gadget Lab , we dig into the buy now, pay later phenomenon and what it means for the future of shopping.
Read Lauren’s interview with Max Levchin.
Check out more of WIRED’s reporting about buy now, pay later programs. Follow our coverage of all things ecommerce.
Michael Calore is @ snackfight.
Lauren is @ LaurenGoode.
Bling the main hotline at @ GadgetLab.
The show is produced by Boone Ashworth (@ booneashworth ). Our theme music is by Solar Keys.
If you have feedback about the show, or just want to enter to win a $50 gift card, take our brief listener survey here.
You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link.
You can also download an app like Overcast or Pocket Casts, and search for Gadget Lab.
If you use Android, you can find us in the Google Podcasts app just by tapping here.
We’re on Spotify too. And in case you really need it, here's the RSS feed.
Michael Calore : Lauren.
Lauren Goode : Mike.
Michael Calore : Lauren, how are you paying for things these days? P2P, BNPL, good old-fashioned CC? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : Are you using all these abbreviations because we're a tech show and tech companies love to abbreviate things? Michael Calore : No, I'm using all these abbreviations because I'm trying to be hip.
Lauren Goode : That might be worse.
Michael Calore : OK. What I'm actually really fascinated by is this whole trend of buy now, pay later, and how techies are trying to disrupt borrowing.
Lauren Goode : They are in fact trying to disrupt borrowing, and we should definitely talk about this.
Michael Calore : Let's get to it.
Lauren Goode : All right.
[Gadget Lab intro theme music plays ] Michael Calore : Hi, everyone. Welcome to Gadget Lab.
I am Michael Calore. I'm a senior editor at WIRED.
Lauren Goode : And I'm LG. I'm an SW at W.
Michael Calore : Awesome.
Lauren Goode : I'm Lauren Goode. I'm a senior writer at WIRED, and I'm trying to abbreviate everything.
Michael Calore : A lot of us have got money on our minds these days. It's the end of the year. The holidays are here, inflation is still making it all sting. And of course, there's all the online shopping. If you're doing any of it, you have surely noticed all of those options that let you buy something now and pay for it later. And when you check out on a web store, you'll see offers from companies like Affirm, Klarna, and Afterpay, all giving you the option to pay for things in installments rather than all at once. This is the rise of buy now, pay later—BNPL for short. And yes, it's yet another way that big tech is trying to disrupt your wallet. Lauren, you've been reporting on buy now, pay later for a while, and you've just talked with Max Levchin, the founder of Affirm. He also happens to be a cofounder of PayPal, along with the guy who owns Twitter now.
Lauren Goode : Who was that again? Michael Calore : Did we forget already? Lauren Goode : Yes.
Michael Calore : What have you learned about buy now, pay later, both from Max and from your reporting? How does this work? Lauren Goode : Well, if you've seen an option to use buy now, pay later at the point of checkout online and you haven't used them before, then what you probably don't know is that most of them will break things down into installments over let's say eight weeks or six payments over approximately that amount of time. Part of their appeal is that they're pretty immediate to use, and during that short period of time, if it's a short loan, it's generally 0 percent in interest or fees. There are going to be fees eventually if you take on a longer-term loan, or of course if you default on your payments, you might eventually get charged fees. But they're supposed to be appealing because of how relatively easy they appear to be to use, how quickly you get approved for these loans. And they don't have some of the financing fees that are associated with credit cards.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Is it really no interest and no fees? Lauren Goode : I mean it is for a short period of time, like in the case of Affirm, which is the company I think we're primarily talking about today, I have used Affirm before. I used it to buy an area rug for my bedroom, and it was broken down— Michael Calore : An area rug? Lauren Goode : An area rug.
Michael Calore : Is that a throw rug or is it bigger than a throw rug? Lauren Goode : It was bigger. I think it was an 8 x 10.
Michael Calore : So not a small purchase.
Lauren Goode : Not a small purchase, but I mean, it wasn't a Persian rug. It wasn't something that was super, super expensive, but I was actually curious about Affirm. And so I thought, “Let me try this, instead of using my credit card,” which a lot of people have stored in their Apple wallet at this point, or it sort of auto-fills in your browser if you're using Google autofill or Safari autofill. It's really easy to buy stuff these days with a credit card online. But I just figured, let me try Affirm because I want to see who actually serves this loan, what is the bank providing the loan, what's the fine print, how much am I going to owe? And sure enough, the area rug was paid off, the money was sucked out of my account, it was tied to a traditional debit card, and it was sucked out of my account, over four payments for 0 percent.
Michael Calore : Wow. So it's automated, so the payments just hit at regular intervals. You don't have to go and initiate anything.
Lauren Goode : You can set it to do that, yes.
Michael Calore : You can.
Lauren Goode : You'll get a notification, and there's also an app. Affirm has an app, so you could just go into the app and manage it that way.
Michael Calore : How is this different from a credit card? Lauren Goode : This is a great question because it's the number one question that people have. Well, there are going to be certain people who use credit cards, let's just say, more responsibly. They pay it off every 15 days, 30 days. They really want to avoid the high interest rates, the APRs, the compounded interest over time, and they sort of treat it just like, “Hey, I need to buy a flight, so I'm just going to put it on my credit card, but I'm going to pay it off as soon as I get my next paycheck.” Or “I'm going to use my credit card to stack up points, but I know I can pay it off at the end of every month.” But then there's definitely a certain customer of credit cards who just carries a balance all the time, and those fees can be pretty high. If you let it go for a few months or longer, in some cases, you could end up paying what, 19 percent? You end up paying a lot, in some cases, just to hold the credit card itself, if it's one of the sort of premium credit cards. And two, you end up paying interest if you just can't pay off your entire balance at the end of every month. With buy now, pay later, they're offering a little bit of a longer-term loan. You could take as long as three months or something to pay for that item or items that you want to buy for 0 percent. In many cases, the banks that are actually providing the loans, like Affirm has these bank partners that most people have never heard of before like Cross River Bank or Celtic Bank. This is not like Wells Fargo, Bank of America, JP Morgan, because they have their own buy now, pay later services now. You may never have heard of these banks before. What you're really interfacing with is the tech platform Affirm, Klarna, Afterpay, and they're providing all of the service of the payment too.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : I see. They're kind of acting as a broker.
Lauren Goode : Yes.
Michael Calore : Between two parties.
Lauren Goode : They're a middle man. They're a platform.
Michael Calore : I see. And they're making money— Lauren Goode : Tech companies love platforms, they call it platforms these days.
Michael Calore : They do.
Lauren Goode : Yes.
Michael Calore : And they're only making money on the longer-term payments? Lauren Goode : This is a good question. Yes, they do. They make money if you take out a long-term loan or if you default and they have to collect fees. But another way that they make money is they actually charge the merchants they work with to provide the loans for them. Here's a great example. During the pandemic, a lot of people bought into Peloton, but a lot of people would also look at a Peloton purchase, let's say a $2,400 bike or a $2,000 bike, depending on which one you got, and say, “I can't pay for that all up front.” Front and center on Peloton's web page was “Finance this for 18 months or 24 months with Affirm, 0 percent.” And so, Peloton would pay Affirm a fee for every time someone bought a Peloton and financed it through Affirm. The merchants want this to happen because they'd rather have you, Mike, not walk away from the purchase and say, “I don't want to buy this.” They want you to buy the bike and fine, Affirm will take on the loan, take on the risk. They'll handle all of this. We just want you to buy the bike. So the merchants will pay a service like Affirm or Klarna to basically work with them or be listed in their app, for example.
Michael Calore : I see. Normally, if you're getting a loan, or even if you're getting a credit card, there's a credit check involved. Is there a credit check if you want to pay for something with Affirm or Klarna? And does that affect your credit at all if you don't pay it back in time? Lauren Goode : There's a soft credit check that happens at the point of checkout. You get approved or not approved pretty quickly, I want to say in minutes, if not seconds, in my experience. Everyone's different, of course, because everyone's credit check might be run differently. It's this interesting combination of, it's a soft credit check, it's not a hard credit check, but also there's a lot of tech and machine learning involved in that really rapid credit check.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Machine learning? Lauren Goode : So Affirm, one of the things that Max Levchin talks about a lot with Affirm is how he believes Affirm is different from some of the other buy now, pay later companies out there, in that they underwrite their loans, which means they do this sort of rapid analysis to figure out what your credit score is, whether or not they think you are at risk of defaulting on this loan, how much of a loan they should extend to you, what's the amount or the max amount that you should pay? This all happens in seconds using machine learning. It's both a soft credit check and sort of a deeper analysis of what your whole credit picture is to determine if you're a good candidate for Affirm. And then, eventually, even though it's a soft credit check, it's not a hard credit check. Eventually yes, if you do keep defaulting on these buy now, pay later payments, it will affect your credit score.
Michael Calore : It'll probably also affect your ability to get more buy now, pay later stuff.
Lauren Goode : Exactly. Yes. No more Pelotons for you in case you want six of them.
Michael Calore : In your interview with Max Levchin, he mentions that he really hates credit cards. Now, I'm sure part of this is coming from the fact that he's a founder of this company that's trying to upend the credit card industry, but also, I mean, he really has to believe that credit cards are bad and that his system is good in order to make it work. Break down this hatred for us.
Lauren Goode : It's very real. He has very much positioned Affirm as the anti-credit card company. He's blogged about this before on Affirm's blog. There's sort of a surface level answer to that, which is, yes, it's marketing and positioning of his tech company. There's another answer that's a little bit longer that sort of takes us back into the days of the early 2000s and then the 2008 recession, which is that broadly speaking, Americans love. We love our credit cards. A lot of us have credit cards. Currently, we have this huge national debt, this huge balance on our collective credit cards, but that ebbs and flows. There's this period of time in the early 2000s, I don't know if you remember this, but I was graduating undergrad in the early 2000s, and there were financial pundits like Suze Orman who write entire books on— Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : The lady with the hair.
Lauren Goode : Yes. On why you should basically leverage your life with a credit card if you are just starting out and can't afford your rent, and why it's a good idea to build up this credit-to-debt ratio and start taking out credit cards. And then in the 2008 financial crisis, there was sort of a reaction to that, and consumers started to get wiser and realize that actually borrowing is not necessarily always a good thing. We've been taught to build equity, but it's really easy to get over leveraged. And that was a reckoning that we had as a nation. Then during the pandemic, when we were getting stimulus checks, our collective credit card balance in the United States went down significantly. People started paying off their credit card bills. But now they're back up again. We do have this relationship with credit and credit cards here in the United States, that's like it kind of flows in and out. And so, I think when Levchin started Affirm, and it launched in 2012, this was as we were emerging from the financial crisis of 2008 and rethinking the way that we borrow. I think he just saw it as a way to reformulate or, yes, hashtag-disrupt our traditional credit card system. And this was the approach that he decided to take.
Michael Calore : All right. Well let's take a break and when we come back, we'll talk about how that's going.
[ Break ] Michael Calore : The US Consumer Financial Protection Bureau, which is basically the watchdog for the lending and banking industry, they've raised a few eyebrows at these buy now, pay later schemes recently, haven't they? Lauren Goode : That's one way to put it.
Michael Calore : Well, last year the agency opened up an inquiry into BNPL. It has warned consumers that these programs could potentially lead them to overextend themselves financially. Tell us a little bit about this inquiry.
Lauren Goode : There are some concerns that buy now, pay later is a little too easy to use, because the extension of the loan happens so quickly at the point of checkout, takes seconds to get approved or not approved. It's right there next to “Enter your credit card number, pay with Apple Pay, pay with Google Pay.” Or like, here's Affirm, or buy now, pay later. It's all so easy to use that I think there are just concerns that consumers could get into a little bit of hot water with it. And in particular, some of the concern is around younger people. These may be people who are technically adults, but maybe they don't have a lot of disposable income at this point in their lives. Maybe they're just starting out in their careers, and they're seeing lots of products these days. I don't mean to sound old, those kids are seeing all these products, but it's true, you see things in Instagram and TikTok, and influencers that are totally hawking these products and saying, “You have to buy this bag, this beauty product, these sneakers.” Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : This water bottle.
Lauren Goode : This water bottle. And it's really easy to shop these days directly from social media. You've got this sort of path of, here's a young person who wants the latest thing, they're clicking on this link, they're being taken directly to a web page—and by the way, just pay this off in four payments for 0 percent. You don't even need to use your credit card or your parents' credit card if that's what you're using. I think there have been some articles written and some concern expressed about the ways in which young people in particular might be exploring this as an alternative to traditional credit cards, but they aren't necessarily building up the right kind of credit to start, either. And so, the Consumer Financial Protection Bureau is just keeping an eye on it, has been just sort tracking how these companies are operating. It hasn't taken any kind of official action yet, but I think it wants to just keep an eye on it to determine if this is something that's problematic.
Michael Calore : I will say that the ease of that path where you can just click a button and two minutes later the thing is being boxed up and sent to you, and you haven't yet paid for it, that kind of turns me off. I understand how that's attractive, but I think it also could be hindering the growth of these companies. Because I'll tell you what, I have been using credit cards for decades. I understand how they work. I have one of them, as you said, already in my phone and already ready to go and auto-fill. But when I see like Affirm wants to buy it for me and then have me pay them back, I'm thinking like, "Zero percent? What's the catch?" Because buying something has always come with the responsibility of paying it off or else getting hit with interest payments. So what's the catch? I'm skeptical about using it, and it's prevented me from using it up until— Lauren Goode : So you have not used a buy now, pay later service at all, yet? Michael Calore : Right. Just because, clearly, that is the psychological hurdle that is holding me back from using it, where I'm looking at it and I'm thinking, “It's not really 0 percent, is it?” And like, “Do I really want to step into that world and get entangled in another financial system when I already have one that I've been using that I'm comfortable with?” You know what I mean? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : I think that's very real and very valid. It is so interesting because there are some credit cards that really don't have super beneficial terms, and yet if they have a brand bank name attached to them or we've been using them for years, we're just sort of like, “These are the terms.” Right? And if you do a side-by-side comparison, buy now, pay later services might, and you know that you could pay something off in four payments, it might actually be a better deal. But there is that hurdle, that like, “What's the catch? Free money? What's the catch?” I mean, another thing that we would end up dealing with if you did use one of these services, I've used both Klarna and Affirm, is that you're just in their email marketing loop until the end of time. Particularly now that it's the holidays, I've gotten so many emails from them promoting so many products, and one of the emails I got was actually kind of dark. It was from Affirm, and it said, “When the holidays are coming and you're supposed to be thankful, but you're hosting and you're not very thankful.” I talked to Max Levchin about this and said, “The subtext is like, you're broke, but you're supposed to be hosting.” And to me that's like, “Are we supposed to be using buy now, pay later to buy food?” Michael Calore : Are people using it to buy groceries? Lauren Goode : They are, interestingly enough. Some of the Black Friday, Cyber Monday data that has come through so far from some of these services, I got notes from Affirm and Afterpay. Afterpay indicated that actually food was one of the bigger categories for buy now, pay later during this period. And that's an interesting shift, because it's not “Here's a 21-year-old who's spending a lot of time on TikTok, who wants to buy the latest sneakers.” People are using buy now, pay later increasingly for things like fuel and food. And so when you look at the terms of the lending, is that necessarily a bad thing? Well, we don't really know yet. When you think about it sort of societally, it's an interesting time we live in, when there are people who are really struggling to have their basic needs met and are turning to these relatively new, decade-old consumer lending systems that are backed by tech.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : It's kind of like Uber and Lyft, where those companies have a really hard time being profitable, but that's OK because they're backed by venture capital.
Lauren Goode : Right. It's kind of like back in the 2010s, this kind of frothy era of technology, particularly here in San Francisco where we live. Our pal Kara Swisher always says, “It's like assisted living for millennials here in San Francisco,” because you just have all these services that will do anything for you. Laundry, food delivery, ride sharing, whatever it is.
Michael Calore : Find you a date.
Lauren Goode : Right, or find you a scammer on Hinge. But yes, companies like DoorDash, Uber, and Lyft that have had a really challenging time turning a profit but are so heavily funded by all these entities that we are basically as consumers benefiting from this relatively new structure that's in place in society that is funding our rides. And so, you do have to wonder about buy now, pay later and long term profitability and what their businesses look like in a really serious downturn, and how much that “free money” will continue to flow, and who ultimately is funding our purchase of the thing.
Michael Calore : You talked to Levchin about what the world would look like if people stopped using credit cards and started using buy now, pay later services, and he has a pretty rosy view of this future, right? Lauren Goode : I mean, he's just so anti-credit card. He was very on the message. When I posed the question of, “What does a society look like when we're buying all of our things on buy now, pay later versus credit cards?” He was just like, “Well, that's great.” I mean, better than credit cards.
Michael Calore : I mean, he has skin in the game, of course, so we can't really trust him to paint any kind of skeptical scenario. But what do you think would happen if they really did succeed? Not just Affirm, but Klarna, Afterpay, all these companies really did succeed in replacing the credit card as the traditional way of offsetting financial responsibility for something to the near future for most Americans? Lauren Goode : I think what you see is then more fees start to emerge, maybe in different ways, because what a buy now, pay later company has to do is strike this delicate balance between what they're charging to partner with merchants and handle their transactions and what they're charging consumers, if anything at all, or eventually charging consumers. And in the event of creeping interest rates, if interest rates go up again, a serious downturn, people stop shopping in 2023, whatever may happen, a company like Affirm or its competitors are going to constantly have to manage that balance to figure out where they're going to get money from. And so, who are they going to cater to more in that kind of dynamic? The merchants or the customers, the consumers, people who are clicking Afterpay or Klarna or whatever it is at the point of checkout? Right now, Affirm says they only have about 2 percent of the ecommerce market, so there's a lot of room for growth. As they grow, where does that cost get shifted? I wouldn't be surprised if it was more on the consumer. I'm not running the business, so I don't know. But I imagine over time there have to be more fees or more ways to just get more people onto the platform, baked in, in ways we notice and in ways we don't probably.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : So maybe what we need to do is watch now and find out later.
Lauren Goode : It's like the thing that your editor, Mike, never wants you to write at the end of a story.
Michael Calore : I guess we'll just have to wait and see.
Lauren Goode : I guess we'll just wait and see.
Michael Calore : Boy, that's my favorite thing to cut out of any story. Let's take another break, and when we come back we'll do our recommendations.
[ Break ] Michael Calore : Welcome back. Lauren, what is your recommendation? Lauren Goode : I was really hoping we would start with you, because I feel like I've been talking a lot.
Michael Calore : You have been talking a lot because you are our guest, but of course, the rules of the show dictate that the guest goes first.
Lauren Goode : OK. My recommendation is Dead to Me , season 3.
Michael Calore : Very nice.
Lauren Goode : Have you finished it? Michael Calore : Finished it last night.
Lauren Goode : You did? So Dead to Me is a show starring Christina Applegate and Linda Cardellini, among other excellent … I know Mike just put his hand to his heart. Who does not love Judy? Everyone loves Judy. There are some other fabulously talented actors in it too. James Marsden, like wow, that guy is— Michael Calore : He has range.
Lauren Goode : He has a recurring character as well. He actually played twins in the show, but Linda Cardellini and Christina Applegate play best friends, these middle-aged women who met through a grief support group and murder ensues. If you go back to season 1, you'll catch up. So they end up basically being in cahoots, trying to cover up this murder, and their friendship blossoms as a result of this. And it's this really, really deep, funny but deep friendship that I think happens because they're these two middle-aged women are in this situation together. It's really funny, but it's also a really beautiful friendship. Season 3 is the final season. Christina Applegate has been having some really serious health issues. She's in public about this. She has multiple sclerosis. She was diagnosed in 2021, and they shot the final season, the season 3, with her sort of finding her way through this disease. There was a lot of blocking that had to happen in order to shoot it, and it's like remarkable that she did this.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : A lot of scenes with her sitting in a car or at a table. Not a lot of scenes of her walking around.
Lauren Goode : Like bursting through doors and that sort of thing. And they sort of find interesting ways to work it into the storyline, but she, not that specifically, but she does a fantastic job, the whole cast, it's a really great show.
Michael Calore : I think the casting is key for the show. It's really great to watch these two actors really just stretch. But also the tone is really interesting because it's a mystery and it's a comedy and it's a drama. I wanted to use the word “blubbery” drama. There's a lot of tears in the show, but it's not really that blubbery. It's kind of interesting how they mix it all together, and sometimes, there are a lot of shows that do this and it usually just feels silly or kind of forced, but this show does not feel silly even when it is. And it does not feel forced, even when it's being almost melodramatic, it kind of teeters on the edge of melodrama and then pulls you back with jokes. I really liked it. I thought it was really just a nice, beautiful three seasons.
Lauren Goode : I think that's a good way to describe it, that just when it gets to the point where it could be melodramatic, something happens that is deeply weird or funny, or literally the kitchen ceiling crashing in, and it all ties back really well. It's really well written, these little plot points that show up again and again.
Michael Calore : For sure. And it takes place in my hometown.
Lauren Goode : No, really? Wait, Laguna? Michael Calore : Laguna Beach.
Lauren Goode : Wait, I think I did not realize that Laguna was your hometown.
Michael Calore : But I grew up in that whole part of the world. Dana Point, Laguna Niguel, Laguna Beach.
Lauren Goode : I mean, I know we talked about surfing down at Dana Point, but wow. Was it actually shot there? Michael Calore : Most of it, like the exterior scenes. I don't know where they shoot the whole show, but the locations are all locations that I'm intimately familiar with from my teenage years.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : So great. It's one of those shows that you kind of don't want to leave. You want to just be in it, and you told me about it, was it two years ago? Michael Calore : I think I recommended it.
Lauren Goode : I think you recommended it during the pandemic. We could talk about this forever. Let's just make this the Dead to Me podcast. Mike, what's your recommendation? Michael Calore : I'm going to recommend a podcast that I was a guest on.
Lauren Goode : Yes.
Michael Calore : Can I do that? Lauren Goode : Yes, you can.
Michael Calore : All right.
Lauren Goode : Shamelessly self-promote.
Michael Calore : I mean, I'm sure if you listen to this show, you don't get enough of me talking, so you have to hear more of me talking. But you can hear me in the hot seat. I think it's fun. The show is called Select Five , and it's hosted by my good friend Pam Torno, who's a DJ, DJ Pam Chop. We have done DJ gigs together. That's how we met. We've become friends over the years, and she has hosted this podcast for a few years where she invites a creative person on, either like a musician or another DJ or somebody who just has a creative profession, to talk about five songs around a specific theme. So it could be the five songs that remind them of where they grew up, or it could be like some sub-genre that they're really into. She asked me to be on the show. We tossed some ideas around, and we decided to talk about sleep music, because I'm obsessed with music for sleeping. I have been listening to music falling asleep as long as I can remember, my entire life. And through the years with the radio era and then CDs, and then streaming, the types of music and the songs that I've had access to have changed a lot, grown mostly. So I sort of have gone on this journey of the music that I listened to, to fall asleep 10 years ago, five years ago now, it's all represented in the talk. We talk about the selections, and we talk a little bit about my life, and it's fun because it's way different than what I normally talk about into a microphone.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : Which is tech.
Michael Calore : Which is technology. We were going to talk about technology on her show as well, but we just ended up talking about sleeping.
Lauren Goode : Can you give us a sneak preview of some of the things that you recommended? Some of the tracks? Michael Calore : Sure. There's a Brian Eno generative piece in there. I talk about the Max Richter piece, Sleep , which is like an eight-and-a-half-hour-long album, classical album that's intended for you to listen to while you are asleep. It's good times.
Lauren Goode : I really need to try that. My current sleep music is “Hey Google, play ocean sounds,” for hours on end.
Michael Calore : You just triggered everybody's Nests.
Lauren Goode : Sorry. But enjoy the ocean sounds.
Michael Calore : Yep. There's no white noise in my selections, but there are some fake rain sounds in my selections. You have to listen to the show.
Select Five is the name of the podcast, and I'm on episode 19. You'll see my photo.
Lauren Goode : What happens if you travel and you don't have access to a speaker in the room that you're staying in? Michael Calore : I usually just use my phone. I'll just play something on my phone and put it down next to me. And true story, one time I logged on to the hotel Wi-Fi, and then I turned the music on and went to sleep, and I woke up to an alert saying that I just used 2 gigabytes of data.
Lauren Goode : Was it a good night's sleep? Was it worth it? Michael Calore : Nope.
Lauren Goode : That is the worst. I mean, music streams aren't usually that heavy.
Michael Calore : Well, I have everything cranked up too extreme, because I can't stand crappy audio quality.
Lauren Goode : Just the highest quality.
Michael Calore : Only the best.
Lauren Goode : The best.
Michael Calore : Only the best for me for my little precious ears, the princess and the highly compressed pea.
Lauren Goode : That's a great recommendation. Thank you. I really need to use this—as you know, I'm not a good sleeper.
Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : I'll set up some playlists for you.
Lauren Goode : Thank you, Mike. I say this every time I'm coming to the office. “How are you doing?” “Well, I didn't sleep well last night,” per usual.
Michael Calore : Try listening to music. All right. Well, that's our show for this week. Thank you all for listening. Lauren, thank you for being on the show.
Lauren Goode : Thanks for having me on my show. This is really fun. I love it when it's just the two of us.
Michael Calore : Right. We could talk about anything for an hour, and at least two people would be interested inside this room.
Lauren Goode : Exactly.
Michael Calore : If you have any feedback about the show, you can find all of us on Twitter. For now, just check the show notes. Our producer is the very handsome Boone Ashworth. Goodbye, and we will be back next week.
[Gadget Lab outro theme music plays ] [ Outtake ] Hi, everyone. Welcome to Gadget Lab.
I am Michael Calore. I'm a senior editor at WIRED.
Lauren Goode : And I'm Lauren J— [ Lauren and Michael laugh ] Lauren Goode : I can't even pronounce my own name. What's wrong with me? Michael Calore : All right, let's back up.
Lauren Goode : OK.
You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer.
Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Topics Gadget Lab Podcast podcasts eCommerce Finance banks Michael Calore Julian Chokkattu Lauren Goode Brenda Stolyar Brendan Nystedt Julian Chokkattu Simon Hill Julian Chokkattu WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights.
WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.
Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia
"
|
Subsets and Splits
Wired Articles Filtered
Retrieves up to 100 entries from the train dataset where the URL contains 'wired' but the text does not contain 'Menu', providing basic filtering of the data.