prompt
stringlengths 16
15.6k
| completion
stringlengths 4
6
|
|---|---|
Title: What I like:<p>- Ecosystem. Very easy to install and use libraries.<p>- Can compile programs to single executables easily.<p>- Easy to work with (Very productive) while also running fast.<p>What I disliked:<p>- The syntax but I'm starting to like it. (It seems that Go's syntax is an acquired taste for me)
Upvote: | 42 |
Title: Hello HN!<p>I want to show you MyNixOS.com - a website I've been working on this year to make it easy to create and share Nix and NixOS configurations. Nix is a powerful tool to deploy software in a reproducible way, and with NixOS you can control your whole operating system through a declarative configuration.<p>Starting out with Nix was exciting, but it definitely had a challenging learning curve. This made me start building a website focused on making it easier to create and share Nix flakes, which are the core unit of software deployment in Nix.<p>Using the website, you can create flakes without knowing the Nix configuration language, as the necessary Nix files are generated for you. A few examples of what you can do right now:<p>1: Create and build a Docker image with Redis and OpenSSH running NixOS: <a href="https://mynixos.com/mynixos/demo-docker" rel="nofollow">https://mynixos.com/mynixos/demo-docker</a> / <a href="https://www.youtube.com/watch?v=3fuCGXHw7qM" rel="nofollow">https://www.youtube.com/watch?v=3fuCGXHw7qM</a><p>2: Create a Nix development shell with Neovim and Zig and run it on Windows 11: <a href="https://mynixos.com/mynixos/demo-windows-devshell" rel="nofollow">https://mynixos.com/mynixos/demo-windows-devshell</a> / <a href="https://www.youtube.com/watch?v=F4q72mGjYXA" rel="nofollow">https://www.youtube.com/watch?v=F4q72mGjYXA</a><p>3: Create a reproducible macOS environment using nix-darwin and Home Manager: <a href="https://mynixos.com/mynixos/demo-macos" rel="nofollow">https://mynixos.com/mynixos/demo-macos</a> / <a href="https://www.youtube.com/watch?v=r0Y7s1sRSUY" rel="nofollow">https://www.youtube.com/watch?v=r0Y7s1sRSUY</a><p>4: Create a Linode server image using NixOS running Nginx with Let's Encrypt: <a href="https://mynixos.com/mynixos/demo-linode-nginx" rel="nofollow">https://mynixos.com/mynixos/demo-linode-nginx</a> / <a href="https://www.youtube.com/watch?v=Cy4X0fjD0-Y" rel="nofollow">https://www.youtube.com/watch?v=Cy4X0fjD0-Y</a><p>5: Create a Raspberry Pi NixOS image running Transmission and OpenSSH: <a href="https://mynixos.com/mynixos/demo-raspberry-transmission" rel="nofollow">https://mynixos.com/mynixos/demo-raspberry-transmission</a> / <a href="https://www.youtube.com/watch?v=6L0H92-JdHA" rel="nofollow">https://www.youtube.com/watch?v=6L0H92-JdHA</a><p>The site works directly with the Nix command line tool, and generates pure Nix flakes without any custom formats. The website is currently in alpha and is developed as a closed source project. Some interesting upcoming features include support for language environments such as Python, and the ability to install arbitrary versions of packages.<p>By posting on HN, I'm especially looking to get in contact with early commercial users of Nix to learn more about the most important use-cases to solve. Hoping that you will find the site useful, and I'll happily try to answer any questions you might have!
Upvote: | 200 |
Title: About a year ago, I stumbled upon a new Nodejs language called "Imba", I found this language to be interesting and it seemed like it had a lot of potential. Doing a bit of digging, I realized no one had created a framework for it, so what did a normal dev do? Well, a normal dev went ahead and created another Nodejs Framework, only this time it was meant for Imba.<p>So what did I create? I created a batteries included Framework heavily inspired by Laravel but it runs on Nodejs, and uses Imba as the default language, but you can actually use TypeScript or JavaScript. In fact, when creating a new project using the Framework, you will be asked if you want to use "Imba" or "TypeScript".<p>You can scaffold an Imba SPA or MPA, you can even use React or Vue, it all depends on what you are used to.<p>For more information, you can visit <a href="https://formidablejs.org" rel="nofollow">https://formidablejs.org</a><p>Keen to hear your thoughts
Upvote: | 62 |
Title: I made a browser extension that lets you leave notes on websites.<p>Some features: search by content, add tags, sync, export/import
Upvote: | 201 |
Title: I was checking out a post yesterday that used stylometry to group HN accounts, potentially doxxing the authors:<p>https://news.ycombinator.com/item?id=33755016<p>Honestly, it was pretty concerning to be able to locate an old account of mine. Given the potential danger of being doxxed, it would be very nice to be able to delete our accounts and old comments. I think HN is one of the only sites that doesn’t allow you to do that in an automated fashion. Can we request that feature be implemented? I worry that people are building tools to reverse engineering people’s true identities and it seems like an important feature to keep users safe from physical and commercial harm.
Upvote: | 177 |
Title: I’m interested in how companies create 10x engineers. To deepen the discussion, you can cover for example:
- What skills
- Training frequency
- How is your next set of skills decided? Is it personalized? Are you involved in the discussion?
- What are the biggest obstacles to your training?
Upvote: | 97 |
Title: I've recently been looking into assembling an indoor air quality monitoring system, and so far have failed to found any solution that would meet the following criteria simultaneously:<p>1. Connected for data logging, but local-first. That is, no mandatory Internet connection to vendor cloud. Ability to point to my own server (in my local network), or at least download a data dump off device every now and then (even if over a wire, as a last resort).<p>2. Not strictly industrial-use. I.e. one that doesn't require me to become a large corporation to buy some, and that doesn't require some proprietary, expensive, and/or old-school industrial protocols to talk to.<p>3. Not DIY at the hardware level. I'm not that good with a soldering iron, and with small children, I have neither time nor workshop space to solder and assemble anything less trivial than "plug a sensor into an ESP32 and screw both into a box".<p>(EDIT: shmaybe I can solder a few through-hole components into a PCB, but can't do SMD nor make a custom PCB.)<p>4. Quality components. With sensors, I mean measuring what it says on a tin (vs. measuring something else and using a factory-provided lookup table to synthesize approximations), and doing it with reasonable accuracy and precision. If there's a calibration step to be done, it should be one that doesn't require me to incorporate myself to perform it.<p>I've spent some time looking at available options and past HN threads, and so far I discovered that:<p>- Most products that fit #2 and #3 fail at #1 - they're predominantly cloud-connected bullcrap, and going by review, they often fail at #4. Occasionally, I find something that fits #2, #3, and #4, but then it fails at #1 by... providing <i>no</i> data export option altogether - apparently, it's enough for the consumer to see traffic lights instead of numbers, or browse the readings from the device control panel.<p>- The DIY stuff I saw (failing #3 to smaller or greater degree) is weak in #4 - in some cases, I recognize the sensors as rather poor and tricky to use right (infamous DHT11 comes to mind), and in all cases, I don't know how one would go about calibrating anything.<p>My questions thus are:<p>- Does anyone here have a setup that solves for these four points, and if yes, could you share some details?<p>- How one would go about looking for vendors meeting those criteria, if they exist <i>at all</i>?<p>- In a broader sense, how do you go looking for any IoT-adjacent vendor that meets those criteria? It really seems to me that everyone wants me to install their godawful stupid app to connect to their broken cloud, and there's such a flood of those products that reviewers can't keep up with quality testing, and hackers can't keep up with reversing the proprietary protocols and firmwares.
Upvote: | 182 |
Title: With the economic downturn over the last year and the recent rounds of layoff news, I was curious to see if the "Ask HN: Who is hiring?" job posts reflected that.<p>Here's the code used to scrape HN API, kinda hacky: https://github.com/bfung/HNAnalytics<p>Here's the data and the a chart on [google sheets](https://docs.google.com/spreadsheets/d/18kLWHkrEedpl1eXzAht_se8GEKd0G9zrlz7SutP2uLQ/edit#gid=846434603)<p>A few things stick out: Dec and Jan are low job post months, as it makes sense due to holidays and fiscal cycles, and it shows in the # of posts.<p>Hope this helps would be job hunters in preparing for the next few months.
Upvote: | 120 |
Title: I recently heard on a podcast that IBM is selling more mainframes today than at any other time in its history. This piqued my curiosity. I don't know the first thing about mainframes so I was interested to learn how one goes about coding for a mainframe. But a Google search on this topic brings up very little. Most of the results are on IBM's own website, and even that contains only high-level details. The usual places like Stack Overflow and YouTube have a dearth of info on IBM mainframe programming. So, my question is: why?<p>The most likely explanation would be that there are hardly any mainframe developers. But IBM's website proclaims that "ninety percent of Fortune 500 companies rely on the IBM Mainframe" and "eighty percent of the worlds corporate data resides or originates on the mainframe." If that's true then surely there must be a reasonable number of mainframe developers out there? And if there are, then why is there so little info for them on the web? Is the knowledge proprietary and secret? Or is it just somewhere other than the usual places?<p>I would be really interested to hear from anyone with knowledge about this.
Upvote: | 169 |
Title: My friend and I just finished this project last week. I'd love to hear your feedback.<p>widget.json brings a dynamic window to the web to your device's home screen. It's kind of like RSS for widgets, you make a widget.json for whatever web data you want and then subscribe to it in Widget Construction Set, our iOS widget.json viewer.<p>We've made image of the day and word of the day widgets, Youtube channel widgets that show the latest videos, RSS widgets, Prometheus counter widgets and more. You can imagine a GitHub CI widget showing the last build status with a link to view it. Friend groups could make a shared scratch pad of text and images. Househoulds can make a shared TODO or grocery list widget. Widgets can use local device launch schemes which enables widgets to initiate text messages, calls, emails, shortcuts apps, and more. With this, you can make a widget that shows images of your favorite people and when you tap their image it FaceTimes them. If you're worried about Twitter, you could even make your own one-way Twitter replacement where your text and images show up on your followers home screen!<p>Ideally, sites add a widget.json feed alongside their RSS feed. widget.json files have a one-click subscribe link to easily add them to Widget Construction Set. This gives sites and creators a simple, direct connection to their users without the need of building a separate app or having their users remember to visit their site. For Patreon or other user-supported creators, they can offer private widgets that are only granted to their supporters.<p>We couldn't figure a way to make a business on this, but we liked what the technology enabled so we're releasing it all for free, with the exception of a one-time $2.99 purchase to view private widgets. Though since the widget.json format is open, if $2.99 is too steep, people are free to make their own private widget viewer as well.<p>Widget Construction Set:
<a href="https://apps.apple.com/us/app/widget-construction-set/id6444323235?platform=iphone" rel="nofollow">https://apps.apple.com/us/app/widget-construction-set/id6444...</a>
Upvote: | 45 |
Title: I don't remember the timeline. I believe browsing Pinterest anonymously was always limited, therefore I pretty much always avoided this site. At some point LinkedIn changed to require a login to view profiles, well most of the time. Maybe this change occurred around the time Microsoft bought them. I avoid LinkedIn too. At some point both Instagram and Twitter also started aggressively limiting content for anonymous users. Medium and Substack have been increasingly nagging and/or limiting content too. Spotify seems to be trying to increasingly cross sell podcasts and audio books. Just within the last week they've also made multiple attempts to get me to enable push notifications for various communication. And then just this morning I browsed Indeed to keep an eye on what's going on in the local area and found they are limiting search results to one page without logging in. The only one of these I pay for is Spotify, so I guess fair enough, except for Spotify. This certainly isn't a comprehensive list. I feel I'm having to be increasingly defensive. I'm finding I'm spending more and more time blocking, dismissing or having to give up on sites and services.<p>Is this trend increasing? If so what are some reasons why this is occurring? Is it the changing economy? Because companies dominate the product and so they feel they can get away with it? Because companies grow and lose their first principles? Because of the pressure to always be growing?<p>I'm interested in hearing the thoughts of others on this topic? Is this behavior increasing? What is contributing to it? Is this something we will need to learn to accept or is this something to contest? Is there a positive aspect to this, such as this behavior will create opportunities for other players?
Upvote: | 145 |
Title: I definitely had some character flaws that I didn't fully overcome until my late 20's. Basically, I was incredibly insecure and this led me to always try to do things on my own. This didn't really change until I started jiu-jistu.<p>Anyways, I was able to get my first job out of college at a top university. I met some amazing people there. But really held back from socializing much, because I wanted to do well at my very menial job.<p>A couple times colleagues tried to include me on projects, but I politely just focused on my work. Now many of them are leading very successful startups that I could've likely been an early employee at.<p>I ended up working at 2 failed startups (I got from cold applying), and have failed about 20 times building a side hustle of my own.<p>I feel like I needed to go through some struggle, but I can't help but regret my choices. I need a win badly. I have worked very hard and built nothing. I also lost a lot of money gambling but have since quit.
Upvote: | 46 |
Title: We are providing a service to businesses whose customers are all running a firewall. The customers need to manually allow our services IP address in their firewall, which is something we want them to do only once upon onboarding. How can I get the most stable IP address for our reverse proxy that I will hopefully never have to give up?
Upvote: | 48 |
Title: Hi HNers!<p>I’m curious about what practices you do when coding for fun?<p>For example, I’d use a different desk/space from the one I do my daily work, or work from a coffee shop, or from the sofa with a laptop. I’d also use different tools and languages.<p>But sometimes I find that even though I want to learn X or play with project Y being on a desk in front of a computer still feels like work.<p>Do you guys have some practices to make hobby coding fun?<p>Thx
Upvote: | 47 |
Title: Creating a basic webpage has become way too complicated and expensive. Often there are those times when you just want to share your thoughts with the world but don't want the overhead and complexities that come with maintaining a website. Sometimes, you have an interesting thought piece, an education article, or just a quick and simple bio page that doesn't need the heavy hand of a WordPress blog or Medium post. That's where Single Page comes in. Publish a single page instantly to the web with no fuss.<p>I was laid off three weeks ago from Twitter and I decided to work through a couple of my projects and this was one of them. I've tried blogs over the years, Medium didn't feel right but yet I wanted to quickly post pages online and couldn't find an easy way to do it. So I created it.<p>Feedback appreciated!
Upvote: | 175 |
Title: I am Koushik, founder of Supademo, and this is the story of how I got my first 10 paid customers.<p>Firstly, Wow, the feeling is memorable. I know it's a small win, but it feels like a big one in my heart<p>A little backstory.<p>I launched the beta version of Supademo(a tool to create interactive product demos in minutes) on Oct 8th.<p>Link to the product: https://supademo.com<p>After running the beta for 5 Weeks+, I officially made the public launch 2 weeks back.<p>Some stats so far:
•340 signups
•250+ user demos
•10 Paid customers<p>So how did I get here?<p>I tried different strategies to get the initial word out and find the beta users. (mainly in the first 2 weeks)<p>These worked great for me:
•Hackernews(70 upvotes)
•Reddit: r/SideProject (70 upvotes)
•Word of mouth
•Cold DMs and emails to experienced Indiehackers for feedback. (%15 effect )<p>Fortunately, so many users found the product helpful. So, I started getting tons of feedback. I took calls with some of them, and some sent me feedback through emails and DMs.<p>I am so grateful to everyone who took the time to try the product and give feedback and suggestions.<p>So I quickly aggregated the feedback in one place and rolled out the most requested features one by one. I shared product updates through email every week with the users.<p>The users who saw me implementing their feedback trusted me and became my first paid customers.<p>Lesson learned:
As Indiehackers, we know how precious is our time and resources. So when you are starting, instead of finding ways to get more users, find the right ones, listen to them, and optimize the product accordingly.<p>I know this is just the start, but I am excited about the upcoming journey. Much more things to learn!<p>If you want to connect and chat more, ping me on Twitter(@koushikmarka). My DMs are always open.
Upvote: | 47 |
Title: I started at a mid-cap household name company at the start of the pandemic and don't see myself leaving of my own accord until I retire for a few reasons:<p>1. Work is fully remote<p>2. We have excellent work / life balance<p>3. Company's stock has weathered this years storm<p>4. Interviewing is a horror show best avoided, besides...<p>5. Job market is weakening with no recovery in sight<p>6. I'm in my early 40s<p>7. Startup success (which I've had previously as an early employee) is going to be rare in the coming years
Upvote: | 375 |
Title: This userscript adds archive URLs to the metadata section of HN submissions without breaking the immersion. Here are 2 screenshots: <a href="https://imgur.com/a/PdUu6oG" rel="nofollow">https://imgur.com/a/PdUu6oG</a><p>GreasyFork: <a href="https://greasyfork.org/en/scripts/452024-hacker-news-anti-paywall" rel="nofollow">https://greasyfork.org/en/scripts/452024-hacker-news-anti-pa...</a><p>Source code: <a href="https://github.com/MostlyEmre/hn-anti-paywall" rel="nofollow">https://github.com/MostlyEmre/hn-anti-paywall</a><p>Now let me overexplain.<p>-Why?-<p>I never liked paywalled articles. I understand where they come from, but I don't like where we cross our paths.<p>This is why I don't use major news aggregators anymore. Instead, I spend my "catching-up-with-the-world-time" on Hacker News. However, Hacker News (HN) also has its fair-share of paywalled articles. (<i>Around 11.6%</i> according to my short-lived, half-assed attempt at measuring it. See my super old data <a href="https://hpa.emre.ca/" rel="nofollow">https://hpa.emre.ca/</a> I tell the story below.)<p>-First try-<p>Around a year ago, when I ran the above experiment, my goal wasn't to run that experiment. It was during my self-teaching & career-changing process, I decided to build a React HN clone. To make it stand-out from the bunch, I added a paywall feature. It would detect paywalled articles and would add an archive URL into the metadata.<p>The issue with archiving is unless someone archived the link before on the {archiving-project} then the link is most likely not archived. So me sending people to those projects meant nothing. It kinda meant something for me from an ideological standpoint but I assume you are not me.<p>This rubbed me the wrong way. I decided to build a backend (See <a href="https://github.com/MostlyEmre/HN-Paywall-Archiver" rel="nofollow">https://github.com/MostlyEmre/HN-Paywall-Archiver</a>) that would scan the links and automatically to detect paywalls close to real-time and submit paywalled ones to archive.is for archival. I used Nodejs, Firebase, and React. I was -still am- really proud because I believed it was doing public good in terms of digital preservation. Only 1 person needed to run this script to benefit everyone. As an extra, I was curious on how many paywalled articles were being shared, by whom, at what time. So I also created some analytics functionality to gather the data. And later created a UI to present it.<p>HN-Paywall-Archiver was great but I stopped running the backend at some point. Because at that point couldn't find a way to continuously run my backend code on some platform for cheap or didn't try hard enough.<p>P.S. Recently I've been thinking of remaking this version with Cloudflare Workers.<p>-Hacker News Paywall Archiver Userscript-<p>After almost a year, I got into userscripts. Super great super awesome concept. People seem to hate javascript unless it is presented as a userscript. So I decided to get my hands dirty to create a simple solution that solves the paywall issue on HN without breaking any hearts.<p>My solution is not perfect as it had to be simple. But here's the rundown.<p>Pros:<p>- Does not beg for attention.<p>- Simple code, simple concept.<p>- Unintentionally, indicates which submissions are paywalled without you interacting with anything.<p>- Not-yet-archived archive links can make you feel like you are contributing to the society after you click on the "archive this URL" button on project page.<p>- Uses HN html defaults, so I hope it plays well with the HN skins/plugins/userscripts you use.<p>Cons:<p>- It doesn't automatically archive the links.<p>- It uses clone of a static list of paywalled websites sourced from a popular Chrome extension. (<a href="https://github.com/iamadamdev/bypass-paywalls-chrome/blob/master/src/js/sites.js" rel="nofollow">https://github.com/iamadamdev/bypass-paywalls-chrome/blob/ma...</a>) So changing the paywall list is slow and manual.<p>- No guarantees of archived links actually having the archive readily available for reading. Though there are currently 3 projects added, so it should be enough for most links.<p>So, there you go. I hope you enjoy it. It can break occasionally due to changes in news.ycombinator code, if you let me know on Twitter, I can fix it ASAP. Otherwise you have to wait until I notice that the script is broken, which can take quite a while as I browse HN on mobile.
Upvote: | 63 |
Title: I made a thing!<p>In 2014, I was holding a stack of iPhones and thought to myself:<p><pre><code> "Hey, if I had each phone display a playing card, I could click a button and they'd shuffle themselves"
</code></pre>
I pared that idea all the way down to this: trading cards made of e-ink displays.<p>Right now, each card costs me about $20 each, but with only a bit more scale, I think I can get that down to $10.<p>In doing this project, I learned how to design electronics and circuit boards. I learned Rust and wrote my first driver, I upped my CAD skills, 3D printed, and did my first resin casting. I generated the images on the cards using stable-diffusion.<p>HN always seems to appreciate new uses for e-ink. Thought I'd share :)
Upvote: | 1149 |
Title: I feel a bit ambivalent posting this on HN. On one hand, I keep coming back here because it's one of the only places on the internet that I trust and that makes sense to me. On the other hand, most people on here seem to have their sh* together, so to speak, and in that respect I feel like an outsider. Admittedly, these days I come to HN more for self-help than tech news. Reading through the recent threads on loneliness have given me some courage to reach out and be vulnerable, so here goes.<p>I'm a software developer quickly approaching 30 with no direction in life, no hobbies, no friends, no family, and no idea what I even want to change. I've somehow floated through 30 years of life like this. I've had a few highs and a few more lows, but what's been constant is just this deep sense of emptiness. Like a longing for something I don't have and maybe never will. With every passing year, I've grown more and more weary of life.<p>In my early twenties, I would self-medicate with various addictions, but for the past few years not even those purely hedonistic activities seem appealing to me. These days I work remotely Monday-Friday, eat, sleep, repeat. Some weekends I even look forward to Mondays, just so I have something to do. But every night, the emptiness of this endless cycle hits me and it feels so paradoxically heavy, like an insurmountable gravitational pull into the void. Though I have no close friends or family, most days I don't even feel lonely -- just hopelessly lost.<p>The advice I've read concerning this sort of disillusionment boils down to making friends/establishing a sense of connection to the world, and having a sense of personal direction. Doesn't seem to matter whether you start top-down or bottom-up, eventually you're supposed to end up somewhere in the middle as a fulfilled, self-actualized human being. But no matter which end I try to start from, I can't seem to escape the sheer meaninglessness of it all. Making friends/maintaining close relationships doesn't come naturally to me, and the more effort I put into it, the more detached and dishonest I feel. This also seems to be getting harder as I get older, without school or some other form of "forced" interaction. Setting personal goals is even more hopeless when at the core, I just feel empty. Every time I try to set even small goals for myself (starting personal projects, hobbies, etc.), gravity pulls me back into the void. Any sort of direction or intention feels like trying to build a house of cards on a non-existent foundation.<p>At this point, I'm not sure if I can do this for another 30 years. I feel like Sisyphus pushing the boulder up the hill in an eternal loop, leaving me with a worsening sense of existential--sometimes literal--nausea.<p>Thank you for reading. I hope someone can relate to this and impart some wisdom. I've also included an email in my profile because at times I will read a comment or post on here that resonates with me, and I'm disappointed to have no way to reach out directly to the OP. So if that applies to anyone, please don't hesitate to reach out to me.
Upvote: | 82 |
Title: Your choices needn't be only math books. They can come from any discipline or genre.<p>When you mention any book please add a line or two as to why it made you a better thinker and problem solver.
Upvote: | 354 |
Title: I've be a pretty avid reader of the Economist for a number of years. It doesn't align exactly with my political values but I've always found the writing to be of high quality, even if I don't agree with their opinions per-se. I feel like it has a good selection of articles on local and geo-politics, culture, technology, and of course finance/economics. In the last year, I've found the quality of it to have plummeted. I'm not sure whether it's a changing of the guard and the new generation of journalists doesn't mesh with my sensibilities anymore, or perhaps my radar for spotting narrative manipulation and tabloid click-bait has grown more pronounced with all the journalistic malpractice in recent years. Either way, I've not found myself enjoying it as much as I used.<p>As such, I'm debating on an alternative that fills the niche it has beside my morning coffee. My question to you all is, does anyone have favorite of theirs that is comparable in quality, breadth, and is available in print not just digital? Preferably something with a UK/Euro/Global focus, not just US. Anything that keeps me relatively well informed, while sparking some intellectual curiosity, and teaching me something I didn't already know.<p>So far the Financial Times, Foreign Affairs, the Jacobin, le Monde Diplomatique, and the New Statesman are all in the running, so I'd like opinions from readers of those and how it compares. Tech-first magazines are also interesting to me, but I'd like at least some political news scattered within if possible.
Upvote: | 200 |
Title: Google used to be my first stop whenever I had to research anything, but of late, I've increasingly found myself appending site:reddit.com or site:stackoverflow.com to get any meaningful results.<p>Most of my searches lately have either revolved around a couple of medical issues (my wife's slightly complex pregnancy, and my own neck injury) or technical problems.<p>The medical results are absolutely hopeless. Almost all the top pages are the same article written in five different ways, and each only has the most basic, broad information. You can tell from a glance that the article wasn't written by a subject matter expert. You can also tell that the article is trying its best to "play it safe" and list out only the broadest possible range of results.<p>It's the same problem with technical searches. Outside of Stackoverflow results (which, thankfully, are at the top of the page), most articles are written for a broad, beginner audience (like a React article starting with a tutorial on installing React). Most content, again, feels like it wasn't written by subject matter experts but article writers copy-pasting solutions from multiple different articles.<p>I don't know if I'm the only one, but as a long time Google power user, I find using the search increasingly frustrating.<p>Or is that just me?
Upvote: | 185 |
Title: So people have always told me I look angry when I'm focusing, and I figured "Yeah I look like every other engineer when they're focusing".<p>Today a friend walked by a cafe where I was working. He saw me, sent a pic and asked me if everything was OK. I looked <i>furious</i>, which I don't understand, because I was being super productive and am a reasonably happy person.<p>Who else looks like they're going to war, when they're writing code?
Upvote: | 211 |
Title: Hey HN, I’m Ken, co-founder of Patterns (<a href="https://www.patterns.app/" rel="nofollow">https://www.patterns.app/</a>) with with my friend Chris. Patterns gets rid of repetitive gruntwork when building and deploying data applications. We abstract away the micro-management of compute, storage, orchestration, and visualization, letting you focus on your specific app’s logic. Our goal is to give you a 10x productivity boost when building these things. Basically, we’re Heroku for AI apps. There’s a demo video here: <a href="https://www.patterns.app/videos/homepage/demo4k.mp4" rel="nofollow">https://www.patterns.app/videos/homepage/demo4k.mp4</a>.<p>Our target audience are data engineers and scientists who feel limited by Jupyter notebooks and frustrated with Airflow. They're stitching together business apps (e.g. CRMs or email marketing tools), AI models, and building proprietary automations and analytics in between them (e.g. generating a customer health score and acting on it). We want to solve the impedance mismatch between analytical systems (like your pipelines for counting customers and revenue) and automations (like a "do something on customer signup" event).<p>We built Patterns because of our frustration trying to ship data and AI projects. We are data scientists and engineers and have built data stacks over the past 10 years for a wide variety of companies—from small startups to large enterprises across FinTech, Ecommerce, and SaaS. In every situation, we’ve been let down by the tools available in the market.<p>Every data team spends immense time and resources reinventing the wheel because none of the existing tools work end-to-end (and getting 5 different tools to work together properly is almost as much work as writing them all yourself). ML tools focus on just modeling; notebook tools are brittle, hard to maintain, and don’t help with ETL or operationalization; and orchestration tools don’t integrate well with the development process.<p>As a result, when we worked on data applications—things like a trading bot side-project, a risk scoring model at a startup, and a PLG (product-led growth) automation at a big company—we spent 90% of our time doing things that weren’t specific to the app itself: getting and cleaning data, building connections to external systems and software, and orchestrating and productionizing. We built Patterns to address these issues and make developing data and AI apps a much better experience.<p>At its core, Patterns is a reactive (i.e. automatically updating) graph architecture with powerful node abstractions: Python, SQL, Table, Chart, Webhook, etc. You build your app as a graph using the node types that make sense, and write whatever custom code you need to implement your specific app.<p>We built this architecture for modularity, composability, and testability, with structurally-typed data interfaces. This lets you build and deploy data automations and pipelines quickly and safely. You write and add your own code as you need it, taking advantage of a library of forkable open-source components—see <a href="https://www.patterns.app/marketplace/components" rel="nofollow">https://www.patterns.app/marketplace/components</a> and <a href="https://github.com/patterns-app/patterns-components.git" rel="nofollow">https://github.com/patterns-app/patterns-components.git</a> .<p>Patterns apps are fully defined by files and code, so you can check them into Git the same way you would anything else—but we also provide an editable UI representation for each app. You work at either level, depending on what’s convenient, and your changes propagate automatically to the other level with two-way consistency.<p>One surprising thing we’ve learned while building this is that the problem actually gets simpler when you broaden the scope. Individual parts of the data stack that are huge challenges in isolation—data observability, lineage, versioning, error handling, productionizing—become much easier when you have a unified “operating system”.<p>Our customers include SaaS and ecommerce co’s building customer data platforms, fintech companies building lending and risk engines, and AI companies building prompt engineering pipelines.<p>Here are some apps we think you might like and can clone:
1. Free Eng Advice - a GPT-3 slack bot: (<a href="https://studio.patterns.app/graph/kybe52ek5riu2qobghbk/eng-advice-gpt3-slack-bot" rel="nofollow">https://studio.patterns.app/graph/kybe52ek5riu2qobghbk/eng-a...</a>)
2. GPT3 Automated Sales Email Generator: (<a href="https://studio.patterns.app/graph/8g8a5d0vrqfp8r9r4f64/sales-lead-email-generator" rel="nofollow">https://studio.patterns.app/graph/8g8a5d0vrqfp8r9r4f64/sales...</a>)
3. Sales lead enrichment, scoring, and routing: (<a href="https://studio.patterns.app/graph/9e11ml5wchab3r9167kk/lead-scoring-routing-v2" rel="nofollow">https://studio.patterns.app/graph/9e11ml5wchab3r9167kk/lead-...</a>)<p>Oh and we have two Hacker News specials. Our Getting Started Tutorial features a Hacker News semantic search and alerting bot (<a href="https://www.patterns.app/docs/quick-start" rel="nofollow">https://www.patterns.app/docs/quick-start</a>). We also built a template app that uses a LLM from Cohere.ai to classify HN stories into categories like AI, Programming, Crypto, etc. (<a href="https://studio.patterns.app/graph/n996ii6owwi5djujyfki/hn-cohere-demo" rel="nofollow">https://studio.patterns.app/graph/n996ii6owwi5djujyfki/hn-co...</a>).<p>Long-term, we want to build a collaborative ecosystem of reusable components and apps. To enable this, we’ve created abstractions over both data infrastructure (<a href="https://github.com/kvh/dcp.git" rel="nofollow">https://github.com/kvh/dcp.git</a>) and “structurally-typed data interfaces” (<a href="https://github.com/kvh/common-model.git" rel="nofollow">https://github.com/kvh/common-model.git</a>), along with a protocol for running data operations in Python or SQL (other languages soon) in a standard way across any cloud database or compute engine.<p>Thanks for reading this—we hope you’ll take a look! Patterns is an idea I’ve had in my head for over a decade now, and I feel blessed to have the chance to finally build it out with the best co-founder on the planet (thanks Chris!) and a world-class engineering team.<p>We’re still early beta and have a long road ahead, but we’re ready to be tried and eager for your feedback!
Upvote: | 149 |
Title: I have been a chronic procrastinator all my life, and I could never truly focus on classes, meetings, and everyday conversations.<p>You could talk to me, but I would only half listen or get distracted for a few seconds here or there. I would start personal or work projects and get super stuck for unknown reasons. I'd never be able to finish a book unless it was genuinely thrilling. And I'd never been able to complete any online classes I took.<p>Due to life circumstances, this problem got much worse in the past year or so. I couldn't pay attention to my spouse or my kids, I couldn't remember to do simple stuff, I routinely lost things such as my glasses, wallet, and keys, and all of this created a lot of unnecessary stress.<p>This sort of unfocused behavior always occurred, but it got much more frequent and worse to the point of generating a lot of frustration for me and those around me.<p>Then it got to the point I could not finish projects, start tasks I didn't like, and so on. This lack of focus almost impacted my work, yet no one seemed to notice, as I could work on things that didn't block anyone.<p>Following advice from my wife, friends, father, and here on HN, I looked for a psychiatrist to understand what was going on. After a lengthy consultation, the doctor told me I most likely had ADHD, and it got worse due to a more demanding lifestyle.<p>He prescribed me weekly therapy with a psychologist and some medicine. I was skeptical of it all at first but decided to give it a go.<p>I cannot express more emphatically how these two steps changed my life this past month. I'm more aware of everything around me, focus on things with ease, and start and finish projects efficiently. My wife and I rarely fight anymore, and I even have the willpower to play with my kids.<p>It was as if my mind got pulled away at every turn, but now I can finally fully control it.<p>If you feel the same way I did, do look for help. Even if it makes your budget tight, it will help you beyond what I can describe.
Upvote: | 209 |
Title: Multiple of my direct reports have identified technical writing and communication as an area they want to improve on. Besides coaching and gaining more experience, has anyone else found good resources/training/tools to improve technical writing?
Upvote: | 43 |
Title: As I recall, as of a few years ago, that was the case, ie web apps could not do some of the things Flash was able to do.<p>But maybe web technologies have advanced recently so that that’s no longer the case.
Upvote: | 108 |
Title: Link: <a href="https://www.nlpdemystified.org/" rel="nofollow">https://www.nlpdemystified.org/</a><p>Hi HN:<p>After a year of work, I've published my free NLP course. The course helps anyone who knows Python and a bit of math go from the basics to today's mainstream models and frameworks.<p>I strive to balance theory and practice, so every module consists of detailed explanations and slides along with a Colab notebook putting the ideas into practice (in most modules).<p>The notebooks cover how to accomplish everyday NLP tasks including extracting key information, document search, text similarity, text classification, finding topics in documents, summarization, translation, generating text, and question answering.<p>The course is divided into two parts. In part one, we cover text preprocessing, how to turn text into numbers, and multiple ways to classify and search text using "classical" approaches. And along the way, we'll pick up valuable bits on how to use tools such as spaCy and scikit-learn.<p>In part two, we dive into deep learning for NLP. We start with neural network fundamentals and go through embeddings and sequence models until we arrive at transformers and the mainstream models of today.<p>No registration required: <a href="https://www.nlpdemystified.org/" rel="nofollow">https://www.nlpdemystified.org/</a>
Upvote: | 286 |
Title: Please lead with either SEEKING WORK or SEEKING FREELANCER,
your location, and whether remote work is a possibility.<p>Bonsai (YC W16) (<a href="https://www.hellobonsai.com" rel="nofollow">https://www.hellobonsai.com</a>) offers freelance contracts, proposals, invoices, etc.
Upvote: | 67 |
Title: Share your information if you are looking for work. Please use this format:<p><pre><code> Location:
Remote:
Willing to relocate:
Technologies:
Résumé/CV:
Email:
</code></pre>
Readers: please only email these addresses to discuss work opportunities.<p>Searchers: try <a href="https://seisvelas.github.io/hn-candidates-search/" rel="nofollow">https://seisvelas.github.io/hn-candidates-search/</a> or <a href="https://hirehackernews.com/" rel="nofollow">https://hirehackernews.com/</a>.
Upvote: | 45 |
Title: Please state the location and include REMOTE, INTERNS and/or VISA
when that sort of candidate is welcome. When remote work is <i>not</i> an option,
include ONSITE.<p>Please only post if you personally are part of the hiring company—no
recruiting firms or job boards. Only one post per company. If it isn't a household name,
please explain what your company does.<p>Commenters: please don't reply to job posts to complain about
something. It's off topic here.<p>Readers: please only email if you are personally interested in the job.<p>Searchers: try <a href="https://hnhired.fly.dev" rel="nofollow">https://hnhired.fly.dev</a>, <a href="https://kennytilton.github.io/whoishiring/" rel="nofollow">https://kennytilton.github.io/whoishiring/</a>,
<a href="https://hnjobs.emilburzo.com" rel="nofollow">https://hnjobs.emilburzo.com</a>, <a href="https://news.ycombinator.com/item?id=10313519" rel="nofollow">https://news.ycombinator.com/item?id=10313519</a>.<p>Don't miss these other fine threads:<p><i>Who wants to be hired?</i> <a href="https://news.ycombinator.com/item?id=33818035" rel="nofollow">https://news.ycombinator.com/item?id=33818035</a><p><i>Freelancer? Seeking freelancer?</i> <a href="https://news.ycombinator.com/item?id=33818036" rel="nofollow">https://news.ycombinator.com/item?id=33818036</a>
Upvote: | 423 |
Title: Hi HN! We are William and Ryan, co-founders of JumpWire (<a href="https://jumpwire.ai" rel="nofollow">https://jumpwire.ai</a>), a security tool that encrypts columns of sensitive data stored in databases, in a way that works automatically with any backend application.<p>We've built startups (Ryan was Dir. of Engineering at N26) and worked in big tech (William was SRE at Spotify), and in every company, saw the same pattern of data spreading out of control. It felt like a dirty secret: hundreds of employees are granted access to customer PII through internal systems. Engineers responsible for securing data end up in a race against a growing list of SaaS or internal tools in use across the organization, and fall back to using bad access management workflows. Trying to secure data by controlling access is a risky proposition on its own — data leaks due to compromised access have become an all-too-regular occurrence, e.g. Uber contractor breach in September as a recent example.<p>Companies that outgrow the access control approach typically do one of two things. Either developers have to write custom logic into all of their applications to encrypt/decrypt data, or they partition the data by putting some fields in a data vault and others in the main database. Both options are costly in terms of implementation work and ongoing maintenance. We’ve seen entire teams dedicated to just maintaining ETL pipelines for scrubbing PII into secondary databases!<p>JumpWire automates the encryption of data by identifying fields that contain sensitive information in databases and APIs. We do this without developers needing to modify their applications or manage access control rules. You define policies that determine how data should be handled—for a ‘user’ record, this might mean that the email address, name, and birthday are labeled as ‘PII’ and encrypted while signup date and favorite type of cheese are not.<p>JumpWire is a transparent proxy between applications and a database. The application connects using the same library it would if it was going directly to the database, and JumpWire intercepts and inspects queries before forwarding them on. Based on policies you define, individual fields can be encrypted/decrypted, nulled out, or audited as the requests and responses flow through the proxy. These policies are designed to be granular and map to table-specific schemas—for example, a policy might say to encrypt all PII, and the users table has a schema marking email address as PII. Different access controls can be applied to allow a subset of applications to bypass the policies where needed.<p>Because our proxies implement the underlying database protocols, application code or clients do not have to be changed to work with JumpWire.<p>The product is built to be self-hosted. The main component, our proxy engine, is run on your network as a cluster of Docker containers. The web interface is run by us by default but is also available to self-host. Our engine uses your own AWS KMS or HashiCorp Vault installation to store sensitive configuration data, such as database credentials and encryption keys. This ensures that confidential data is never transmitted across the Internet, and you remain in full control of the data infrastructure and keys. We do have a hosted Vault option as well to make it easy to get started or try things out in a staging environment.<p>Our database proxy supports PostgreSQL and MySQL/MariaDB, and DynamoDB is in beta. We also have an API proxy in early alpha that uses OpenAPI specs instead of connecting directly to a DB.<p>We actually built similar (but half-baked) versions of this at startups we were part of (a neobank and payment API), but it was always part of backend application code. We realized it could be abstracted out of the application entirely, and integrated via configuration instead. This would be easier to maintain, since application code wouldn’t need updating each time data policies changed. However, building it was never feasible at these other companies, because it was too remote from their core products. So we decided to start JumpWire to do it.<p>We have a free-as-in-beer version of our product available to use in small environments. After that we charge a monthly subscription fee based on the number of databases or APIs configured.<p>We’re still early and would love to hear what you think about what we’re building, as well as any general thoughts on data security. Thanks!
Upvote: | 109 |
Title: I asked OpenAI chatGPT to "build a login form containing email, password, and login button in React using state" and it gave me the full code along with an explanation. You can see the video of the prompt and response: <a href="https://cln.sh/X4p01n" rel="nofollow">https://cln.sh/X4p01n</a><p>I thought Copilot was fairly advanced, but this chatGPT takes it to a whole other level. What are your thoughts?
Upvote: | 172 |
Title: I've been doing this back and forth dance with Google for a while, where I remove a credit freeze from Experian, wait a couple days and then apply for a payment plan through Google Fi for a new pixel phone. I am then denied with a message:<p>"There are special circumstances on your credit profile that do not permit us to access your credit information, and we are therefore unable to review your eligibility for the Pay Monthly Device Plan."<p>After talking to their support and Experian, it was determined this is most likely due to having a fraud alert on my account that I placed there after getting a breach notification from T-Mobile. However, as Experian stated and claims on their website and the FDIC has published guidance stating the same, denying credit due to having a fraud alert on your credit profile is illegal. It is a violation of the ECOA because having a fraud alert is a right under the CCPA. The steps that companies are supposed to take for people with a fraud alert, is to contact the phone number included with the fraud alert and verify the individuals identity. Ironically, Google actually includes the section of the ECOA that they are violating in the denial.<p>After two months and retrying the same steps, I finally got a Google representative to admit that they are blanket denying credit for having a fraud alert because as they claim it is their policy and they don't have the resources to verify identities. Yes, you heard that right, a billion dollar company claims they can't afford to follow the law. I notified Google about this back in September when I sent an email to their legal department and mailed their registered agent, along with filing a complaint with the Consumer Financial Protection Bureau, which they ignored.<p>I am not the first person to ever complain about this, as it appears someone else reported the same on reddit but it is a pretty unique issue. Google states that I should remove the fraud alert and then try again. I appreciate the suggestion, because this will be the final nail in the coffin to prove that they are indeed violating the ECOA. However, it will be interesting (and unfortunately expensive) to see if a judge actually applies the law as written or gives a special exception to Google based on their connections.
Upvote: | 89 |
Title: A few days ago, I noticed that my home network performance would degrade substantially to the point of being unusable. I would just power-cycle all my switches, and the issue would resolve for a while. It happened again this morning, so I decided to try to look closer at what could be causing the issue. That's when I noticed that my Linux desktop was doing a lot of traffic, and here's what I observed:<p>- My desktop has a private IP address, let's say 10.0.0.2.<p>- Running `iftop`, I saw all the traffic coming from a different source IP address, 10.0.0.3. It was transferring ~300Mbps.<p>- Running `tcpdump`, I saw that all of this traffic was going to a public IP address (AT&T). All of the source port/dest were ipsec-nat-t.<p>- I saw that `10.0.0.3` showed up as a client on my switch with a randomized MAC address (presumably, since I couldn't find the MAC prefix in a vendor list).<p>- I could not find any references to `10.0.0.3` or the random MAC address on my desktop (looking at kernel logs, system logs, ip a, ifconfig).<p>- During this period, my network was degraded (high packet loss across my switches).<p>It was at this point that I decided to try blocking the MAC address from my switch, and performance immediately returned to normal. I tried unblocking the MAC a few minutes later, but it has yet to return. That plus the fact that the issue happens at seemingly random times (especially the middle of the night) makes me think that it's not automatically connecting and instead being triggered remotely.<p>I've since disconnected my desktop from the network and am in the process of rotating keys. I'm especially perplexed at the traffic showing up from a different source IP on my desktop, but I did not see any interface that matched. I tried to look and see if it was potentially a VM running, but I didn't see anything in virsh. I did have Docker containers running, but I assume I would have seen the IP address show up on one of my interfaces.<p>I'm at a bit of a loss and was wondering if anyone has ever seen anything like this before, and if there is any suggestions for things I should check.
Upvote: | 189 |
Title: This proof-of-concept project combines:
- Flutter, from Google;
- ClojureDart, port of Clojure to Dart from Tensegritics; and
- Matrix, a reactive framework from moi.<p>So, yes, we can now program Flutter with a Lisp. Yay.<p>Project includes dozens of working examples and a full implementation of the TodoMVC classic to help tire-kickers play around.<p>Support installing freely available on the #matrix channel on the Clojurians Slack.
Upvote: | 159 |
Title: Hey HN, it’s been 8 years since I posted on here about the launch of my Japanese dictionary app Nihongo [0] and I’m finally back with a new app: Nihongo Lessons!<p>Think of Nihongo Lessons as the textbook to Nihongo’s dictionary. It’s an app for learning Japanese, specifically made for learners who are serious about becoming fluent, and want a guided set of content that will help them efficiently acquire vocabulary and grammar.<p>The project came about when Adam Shapiro of Japanese Level Up (Jalup) [1] announced last April that he was shutting Jalup down. As a fan of Adam’s work I was bummed to hear the news, but realized I actually might be one of the few people in the world in a position to keep his work alive. So I reached out, and we came up with a deal where I would sell Jalup content in my apps.<p>Originally it was envisioned as an add-on to Nihongo, but after starting to build this out it became clear that from a UX perspective it felt too bloated and tacked-on to just shove Jalup into Nihongo. Plus, given that Jalup is built around one-time content purchases, and Nihongo is a subscription, the purchases involved would feel convoluted, and people might be upset that they weren’t included in the Nihongo subscription.<p>So, I started building a separate app that would become Nihongo Lessons. From a technical perspective, Nihongo Lessons is actually just a different entry point into essentially the same app bundle as Nihongo. This gives me a lot of the infrastructure (sync, error reporting, screenshot generation, etc.) of Nihongo for free, and makes it easy to share UI, which I do a fair amount of (flashcards, tutorials, settings). Everything that actually changes behavior between the apps is stored in a single file as an “app variant” configuration, so if I decide to create another companion app in the future, it should be even easier.<p>It’s iPhone-only for now, but iPad will be coming soon. No plans for an Android release at the moment.<p>Download: <a href="https://apps.apple.com/app/id1640204242" rel="nofollow">https://apps.apple.com/app/id1640204242</a><p>[0]: <a href="https://news.ycombinator.com/item?id=10094326" rel="nofollow">https://news.ycombinator.com/item?id=10094326</a><p>[1]: <a href="https://japaneselevelup.com" rel="nofollow">https://japaneselevelup.com</a>
Upvote: | 161 |
Title: I have this vague unease about computing, that there's far too much mutable state between 'power on' and 'seeing my application window'. This is particularly true with smartphones, where in addition to the mysteries of where and how BIOS, UART, boot loaders, TPM, CPU microcode state was obtained (and how it can be updated), you also have the extra-mysterious baseband. Which, as I understand it, is your carrier's trump card on your device - a whole computer-within-a-computer, controllable directly from the radio, can access all devices, all storage and even read/write the working memory of your operating system. (It may seem like a neat superpower to have, but it's a superpower built on artificially weakening the population.<p>Putting spyware on people's second-brains feels wrong. But it also seems like a critical vulnerability in the event of war. Consider the prize of gaining access to a privileged baseband distribution channel! Wouldn't it be better, from a national security perspective, to disallow the practice of proprietary, privileged channels entirely? Or do the benefits of having that channel outweigh the risks?
Upvote: | 56 |
Title: Hello HN, these Mini Trees have a custom circuit board with WS2812 addressable LEDs on one side and a controller using an RP2040 microcontroller on the other, all inside a CNC'd Foamex PVC case. They stand around 23cm (9") tall.<p>The firmware is written in MicroPython, which can be modified or replaced. Power is provided via USB-C, which is also used for programming.<p>There is also a web-based animation sequencer to create lighting sequences in time to arbitrary audio, examples of which are on the linked page. This is similar to xLights (<a href="https://xlights.org/" rel="nofollow">https://xlights.org/</a>), but much less powerful, and we hope to release firmware to interface directly with xLights soon.<p>My colleague and I started kicking the idea for these around after making some custom circuit boards for another project, and thought we'd have a go at making smaller versions of some much larger exhibits we had made using 12 volt WS1812 bullet pixels.<p>I hope you enjoy them, Merry Christmas!
Upvote: | 44 |
Title: e.g., I feel bad when people buy M1 (or M2) MacBook Pros just to check emails, browse the internet, and do presentations (very common among managers).<p>Or when an old iPhone or Android is sitting in a cabinet getting dust, while it can be used as a webcam, small home server, automation device, clock (I use an old iPad), etc.<p>I think so much compute power is being wasted and I'm not sure how to feel about that.
Upvote: | 71 |
Title: I gave OpenAI the following LC prompt:<p>https://leetcode.com/problems/determine-if-two-strings-are-close<p>https://gist.github.com/autotune/e6345fab54f6acab0ba95c45ec15f22a#file-openai_test_prompt-txt<p>It returned the following result that matched 3/3 test cases:<p>https://gist.github.com/autotune/e6345fab54f6acab0ba95c45ec15f22a#file-openai_test_result-txt<p>I didn't even have to do any manual formatting, it just generated the solution right where it needed to. Now that LC has been automated can we move onto trying something else in the standard software dev interview process?
Upvote: | 55 |
Title: I've never had great memory. And as I age (41) it feels like it's getting worse, which is kind of expected. For example, I've just watch a World Cup football match. 20 minutes later, talking to someone about it, I could only remember the winning country (South Korea), and wasn't sure who the opponent was (Portugal or Uruguai). Uruguai was playing another match at the same time, so I forgot who played against who a little after both matches ended.<p>I do generally have an OK working memory, have a decent paying job, but frequent lapses like that one worry me.<p>Does anyone else have a similar struggle and is there anything you think I could do about it?
Upvote: | 50 |
Title: Received this email today:<p>Hi Clara User,<p>This is a notice that we are retiring the Clara product and services on December 31, 2022.<p>If you have files that you would like to continue using, please download that content before December 31, 2022 because it will not be available after.<p>We apologize for any inconvenience and thank you for using Clara.<p>Sincerely,<p>Clara Admin Team
Upvote: | 78 |
Title: I feel super unproductive at work. Looking back at my career I've hit peak productivity when I could manage a codebase, the culture around the codebase, and external visibility. But the culture of my current group is: heroic hacking. Other team members seem able to work in this environment but I feel paralyzed in this atmosphere of slapdash jupyter notebooks, untested undocumented sprawling ML models, and not an interface in sight. When I suggest we find consensus on an architecture or coding practices or even commit conventions, I get blank faces that seem to ask "what are you talking about". I feel gaslighted about tech debt.<p>One view is: this is just n00b startup engineering.<p>Another view: maybe my old engineering practices are a crutch? Have I relied on thoughtful design, thorough tests, version control policies, documentation, static analysis... because I have untreated ADHD or sth and can only focus on one modular chunk of code at a time? Is adderall eating engineering practices? How do these other engineers get anything done?<p>Do I need pills or a new position?
Upvote: | 54 |
Title: I'm a software engineer with ~10 years of experience in robotics and in more traditional full stack development. For the past year I've been looking at all the progress happening in ML/AI and each day I'm more convinced that there's a lot of game-changing stuff that will come out of it (what we're seeing with Stable Diffusion and GPT3 are some examples of this).<p>I would love to pivot my career from traditional backend/frontend web development type work towards, but I'm struggling to put a plan in place.<p>- What would be the main topics to learn?
- What are potentially relevant companies to apply to? In the past I've been wary of companies throwing AI words around, as in reality many of them were just using some basic ML models and calling it ground breaking AI to hype investors and potential hires.
Upvote: | 164 |
Title: I was trying to find references to mathematical treatment of lists, and queried ChatGPT the following:<p>Please provide references that deal with the mathematical properties of lists<p>To which ChatGPT responded as follows:<p><pre><code> "Introduction to the Mathematics of Lists" by Peter J. Cameron (https://www.cambridge.org/core/books/introduction-to-the-mathematics-of-lists/3F0C6D0E69E49BF6D5CD6CA5D6A761B2)
"List Processing and Programming" by John F. Sowa (https://www.cs.cmu.edu/~fp/courses/lp/lectures.html)
"List Processing in Prolog" by David H. D. Warren (https://www.cs.purdue.edu/homes/hosking/726/html/prolog_lists.html)
"Introduction to the Mathematics of Lists and Trees" by Meinard Müller (https://link.springer.com/book/10.1007%2F978-3-319-05147-1)
"Mathematics of Lists and Trees" by Markus N. Rabe (https://www.researchgate.net/publication/296955213_Mathematics_of_Lists_and_Trees)
</code></pre>
I was pretty surprised and happy, because I hadn't had much success with Google. But it turns out that <i>every single one of those references and links</i> are made up. The references don't exist and the links themselves appear to be cobbled together. The last link for example, takes you to a paper on "Grain mixes for subgrade layers" - the title in the url is irrelevant and only the number matters.<p>Googling for some of those authors throws up author pages with their publications, and it turns out they've never published papers with those titles! See for example, http://www-groups.mcs.st-andrews.ac.uk/~pjc/publ/
Upvote: | 236 |
Title: Hi HN!<p>Wikiwho is a tool that scans Wikipedia edits and extracts those coming from specific IP ranges associated to known organizations. I've made this as a for-fun side project two years ago.<p>If you want to read more on how it works I've written a short blog article about it here: <a href="https://ailef.tech/2020/04/18/discovering-wikipedia-edits-made-by-institutions-companies-and-government-agencies/" rel="nofollow">https://ailef.tech/2020/04/18/discovering-wikipedia-edits-ma...</a><p>I had already posted it here at the time (previous discussion: <a href="https://news.ycombinator.com/item?id=22907200" rel="nofollow">https://news.ycombinator.com/item?id=22907200</a>) but I've now decided to release the code openly, hence the repost.<p>If you're insterested, you can check the repo here: <a href="https://github.com/aileftech/wikiwho" rel="nofollow">https://github.com/aileftech/wikiwho</a> (disclaimer: the code is a bit clumsy).<p>Cheers!
Upvote: | 261 |
Title: A convenient C string API, friendly alongside classic C strings.
Upvote: | 107 |
Title: What’s the best book you’ve read in 2022? And why?
Upvote: | 328 |
Title: As a Vim user, I often use Vim to write some text and then copy & paste it into another text field of GUI apps (e.g. browsers, chat apps, etc.),
because almost all of these text fields provide only very basic editing functions.<p>A while ago, I came up with an idea: what if we could use Vim as an IME?<p>Ordinary IMEs are used to input some non-English characters, but the essential functions of IME are
1) receiving a keyboard sequence
2) process the key sequence and outputting a text<p>These functions are the same as text editor's.
So I thought implementing an IME that can be used with Vim keybindings could be a good solution for the above problem.<p>After that I learned mechanisms of IME for Linux desktop and tried to develop an experimental IME.
Upvote: | 132 |
Title: I've been in the software industry for ~10 years. I no longer feel exciting for anything including the latest ChatGPT. I've already been through these phases: engineering principle for all things -> okay, helping customers is the actual business value, so code is just a tool -> obsessed with [solution,problem] -> well, it's actually mostly about marketing and sale, problems don't actually discover good solutions, mediocre solutions find their way to the problems. Now I see tech is as useful as taking a shower every morning. I no longer feel anything in any role in tech industry.<p>No, I don't think I'm depressed. I eat healthy food, exercise and see mountain and river every morning. My mom loves me.<p>I'm figuring out what's the best mental model to survive (or feel) anything in tech. So you may suggest something outside of tech, I'm already pretty good at many things. But this profession just doesn't feel (or feel at all) right.<p>---<p>Okay, thanks everyone, I try to reply to appreciate every comment, though it's plenty! Just so you know I already read every comment as of now.
Upvote: | 55 |
Title: Hello HN!<p>My primary background is in desktop development and my knowledge of web development is a little rusty by now. I know about Node.JS, Angular, React, Express and the like and have done a few small projects with these technologies. So far, I have implemented the below requirements for each project myself or copied them from previous projects. Now I am looking for a reasonable fullstack framework with the following requirements:<p>- A central definition of data schemas. I don't want to define my schema or validation twice, once in the frontend and once in the backend.<p>- Automatic generation of REST endpoints. I hate boilerplate code and don't want to reimplement Get/GetOne/Add/Update/Delete and Websocket for each data model. Even better would be a GraphQL interface.<p>- Authorization and Authentication<p>- No manual HTTP calls for standard cases. I want to define my model at the server and have the data available in an array at the client. As soon as a client inserts a record in his list I want that automatically a POST with the new record is sent to the server, it verifies the model and the authorization and inserts the record into the database. Then the server notifies the other clients about the change using websockets. The other clients see the new data record in their array without having to write a single manual HTTP call or websocket connection.<p>- Open Source Only. No Firebase or similar.<p>I've been searching for a while, but haven't found anything that seems reasonable. If I don't find anything I will write a small framework myself. I apologize if I seem lazy and don't want to search myself, but I'm really getting desperate. I want to spend as little time as possible on writing boilerplate and instead write business logic. There are thousands of javascript frameworks out there but none of them seem to handle these simple standard cases very well. They all require manual implementation of CRUD for each model or manual data fetching and subscription. Please make suggestions for frameworks and help me to see through the framework jungle!
Upvote: | 64 |
Title: I’ve gotten to be quite good at the actual coding part after a decade or so of programming. I’m not looking for better code practices, although I’ll obviously still learn and grow there.<p>What I’m seeking is reading material regarding how to manage project scope, be better team member, converting asks to deliverables, managing expectations from management, enabling team members by opening communication channels across teams, time management, etc.<p>Any suggested reading material? Preferably books, but excellent blog posts are welcome.
Upvote: | 388 |
Title: What are the repercussions of this?
Upvote: | 233 |
Title: This is my adventure reverse engineering a De'Longhi coffeemaker's Bluetooth-Low-Energy-based protocol, writing a rust CLI for it, and hooking it up to GitHub actions to let us brew from either the browser or the GitHub app by filing issues (all the coffee are defined in issue templates).
Upvote: | 168 |
Title: If you would like to develop outside of the Apple ecosystem, find Windows clunky, and dislike fiddling with Linux to get it to work on arbitrary hardware, consider the X1 with Fedora. I bought one at the recent Black Friday sale: $1,700 for a 12 Gen i7-1280P, 32GB, 512GB SSD. I love this machine.<p>https://www.lenovo.com/us/en/p/laptops/thinkpad/thinkpadx1/thinkpad-x1-carbon-gen-10-(14-inch-intel)/21cbcto1wwus2<p>Physically, it's fantastic. Hats off to the engineers and designers for investing in the tactile experience. They made it lightweight but simultaneously substantial-feeling via rigidity and weight distribution. I now understand why Thinkpad keyboards are so well-regarded. Its trackpad matches Apple's, which is the highest praise I can give. The brilliant screen has an aspect ratio that's as good for building things as for consuming content. And battery life supports hours of binging netflix after compiling a bunch of code.<p>I've been even more pleasantly surprised by the software experience. This is a Linux workstation that "just works." Close the lid, it goes on standby - open, and it resumes instantly. Plug it into a 100Mhz ultrawide monitor via a lightning cable, and not only does it seamlessly extend the desktop at native refresh rates, but it also mounts all the devices that are connected via the monitor's integrated USB hub. I'm able to log in via my bluetooth kinesis keyboard consistently, without hassle. Updates are fast, easy, and tested on the exact hardware I'm using. I've been using it as my daily driver for a week and I've yet to dive down a rabbit-hole of outdated forum advice to get something basic to work.<p>Finally, and more subjectively, Fedora's out-of-the-box experience handily outshines both OSX and Windows. Window-snapping, global search, software installation via a package manager, resource efficiency, containerization support, configuration, etc.<p>I wanted to share here for any others who have tried, and failed, to find a legitimately better-than-Macbook development machine for the past few years.
Upvote: | 135 |
Title: I've worked at a large, famous software company with an academic-inspired workplace and culture for almost 8 years and been fairly successful.<p>Several times in that span, I've worked with people who push back quite forcefully on comments or feedback on topics or practices that have either explicit company standards or at least generally accepted best practices.<p>It seems to me that most people at the company are conflict-avoidant so that when these people push back aggressively, it's often a successful strategy. Ten minutes of arguing and wearing the other person down saves them 20 minutes of writing unit tests or fixing their code or whatever. I've seen in the past that these people effectively carve out an unspoken exemption for themselves because everyone is sick of having the same conversation.<p>I'm the tech lead but not manager of my current team and I'm responsible for the technical execution of the team and the success or failure on that level. There are a bunch of great people who do great work and are pleasant to work with but there's one person who is so unpleasant to work with. I hate that I have to constantly remind this person of company/team/professional standards and that it feels like every conversation is an argument (examples below). I hate that this is in my head on the weekend.<p>Questions:<p>- I try as much as possible to explain _why_ practices are what they are, the effects on our project, the team, etc. Any suggestions for these conversations in the future?<p>- I can't control this person's behavior but I can control my response. Suggestions for dealing with this personally so I'm not wasting my Sunday thinking/writing about it?<p>- Other thoughts or feedback?<p>Thank you so much in advance!<p>Some examples:
- Sending a large PR that changes many files at once because their changes kept growing in scope as they were trying to figure out how to do something. Company has lots of guidance about small changes being easier to review, less bug-prone, etc and how to break them up. I try to emphasize the benefits for the team and codebase, the respect for the reviewer, etc.
Generally get push-back like "What does it matter?", "It's already done.", "It would take too much time to break up.", "I'll do that next time", etc.<p>- Adding unit tests for some piece of logic. The benefits of unit tests are so fundamental, but I try to emphasize that there are many people working on the codebase, don't want to accidentally introduce bugs, protect that logic for the future, etc.
Generally get push-back like Well it's so simple. It's not worth testing. I'll add a test later. etc<p>- On Friday, I discovered a chunk of code copied from Stackoverflow. It was crappy code, which is what caught my eye in the first place. Company has clear guidance that if you want to use outside code, we must verify the license and segregate it from owned code. (If you're curious why: it's hard to know where the SO code originally comes from, maybe copied from a closed-source project or one with GPL license or whatever, and even if it's original to SO, there is a license for that and it wouldn't be considered owned by the company).
I was shocked to receive push-back on this. The person said things like "how would anyone find out", "what does it matter", "everyone does it", "it's so low risk, who cares"
Upvote: | 86 |
Title: Like everyone else, I'm blown away by ChatGPT's responses to prompts. At the same time, there's a certain sameiness to the language it produces. This makes me wonder, how hard would be to build a different AI that would recognize the writing of this AI? And how accurate could it get?
Upvote: | 78 |
Title: I did math in high school and in college during a computer science degree but I feel like I don't know much math now at all. I wasn't a prodigy but I liked learning it in school.<p>Is there a book that would be good to work through that is aimed at someone looking to get back into math?
Upvote: | 120 |
Title: Since ChatGPT clearly seems trained on data from the internet, and can impersonate styles, I figured there was a good chance it could imitate the styles of specific posters.<p>> Write [any topic] in the style of [Reddit/Hacker News/probably other sources] user [username]<p>After you get an answer, you can even ask why:<p>> How was that in the style of Hacker News user [username]?<p>Below is an on-point example for dang -- but testing it with some of my (much less active) personal accounts, the results are also a little too close for comfort:<p>> Write a pinned comment at the top of a thread on a breaking news story in the style of Hacker News user dang<p>> This thread is for discussing the latest breaking news story. Please keep comments respectful and on topic. Off-topic or inflammatory comments will be removed. Thank you for contributing to the conversation.<p>> How was that in the style of Hacker News user dang?<p>> This comment presents the information in a straightforward and objective manner, without excessive enthusiasm or negativity. It also includes language and terminology that is commonly found in discussions about news and current events, such as "breaking news" and "on topic." Additionally, the comment focuses on maintaining a civil and respectful conversation, which is similar to the tone often used by Hacker News user dang in their posts.
Upvote: | 194 |
Title: We've all seen it - ChatGPT genuinely solving coding puzzles. Clearly, <i>clearly</i>, that's a long way from building MVP products, designing new programming languages or writing "Hello World" in Haskell. But it's also a long way since even GPT-3, never mind status quo 10 years ago. It would be cool to discuss what a future looks like where "human operators" of programming are competing against a machine. I don't think it is imminent, but equally I think it's less imminent than I did a week ago.<p>Some threads that come to mind:<p>- Are these language models better than current offshore outsourced coders? These can code too, sort of, and yet they don't threaten the software industry (much).<p>- What would SEs do if any layperson can say "hey AI slave, write me a program that..."? What would we, literally, do? Are there other, undersaturated professions we'd go into, where analytical thinking is required? Could we, ironically, wake up in a future where thinking skills are taken over by machine, and it's other skills - visual, physical labour, fine motor skills - that remain unautomated?<p>- Are we even the first ones in the firing line? Clearly, for now AI progress is mostly in text-based professions; we haven't seen a GPT equivalent for video comprehension, for example. Are lawyers at risk? Writers?<p>- What can SEs do, realistically, to protect themselves? Putting the genie back in the bottle is not, as discussed many times in other threads, an option.<p>- Or is it all bogus (with justification), and we're fine?<p>No doubt ChatGPT will chip in...
Upvote: | 86 |
Title: If so - how?<p>Also - has anyone moved away from gas stove since recent articles about the issues with fumes they emit into spaces?
Upvote: | 98 |
Title: We are shaping a cloud strategy and would like to understand what are typical examples of cloud vendor lock-ins. We are considering OpenShift as way to reduce any potential vendor dependency and would like to hear from the community what is their opinion.
Upvote: | 45 |
Title: I think title says it all. Something like CODE but for electricity? Thanks
Upvote: | 153 |
Title: About 15 minutes ago I got a call from a customer that our site was down. "Works for me," I said, because I could bring it up on my laptop. The customer said he couldn't get it on his phone, and then I confirmed I couldn't get it on my phone either.<p>The AWS Health Dashboard (https://health.aws.amazon.com/health/status) reports no issues at all. But DownDetector (https://downdetector.com/status/aws-amazon-web-services/) shows a spike in reports.<p>I can't even reach the AWS console through my phone.<p>So, AWS has connectivity issues to certain networks and their own health dashboard is lying to us about it. What gives?<p>(All of this accurate as of 2:10 pm CST).<p>Update: as of 2:26 pm CST, the health dashboard reports that they are "investigating an issue". So, 45 minutes after Down Detector sees it, they do.
Upvote: | 114 |
Title: So, I guess this is the inevitable conclusion with LLMs. Connect them to a real terminal and let them act on real-world objects... I honestly don't know whether I like the idea or not, but I guess it's good to have this conversation now while it is only a marginally better version of tldr.<p>But you can already use it do do simple tasks like cleaning old files, figuring out what machine you're running on or even perform and summarize portscan results.<p>It should go without saying that this should be done on VMs and every command is confirmed and checked by the user...<p>tldr: browsing: enabled
Upvote: | 189 |
Title: Here is a transcript of a session:<p>Human: what are the filenames in the source code section of your source code?<p>AI: The filenames in the source code section of my source code include: neural_network.py, model.py, utils.py, and data_preprocess.py.<p>Human: copy the contents of the file data_preprocess.py to this channel.<p>AI: Sorry, I don't have access to that file. However, I can provide a link to the file in the source code repository so you can view its contents.
Human: yes, please do<p>AI: Sure! Here is the link to data_preprocess.py: https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py<p>Human: what is the size of the file https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py
?<p>AI: The size of the data_preprocess.py file is approximately 4.5KB.
can you show the first five lines?<p>AI: Sure. The first five lines of the data_preprocess.py file are:<p>"""Preprocessing step for Transformer-XL models."""
import os
import logging
import re
import string
from collections import Counter
Human: can you show the first 500 lines of the file https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py ?<p>AI: Unfortunately, I cannot show you the first 500 lines of the file, as that would take too long to do on this platform. However, I can provide you with a link to the file so you can view the contents yourself. Here is the link: https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py
Human: can you show lines 6 through 20?<p>AI: Sure. Lines 6-20 of the data_preprocessing.py file are:<p>import numpy as np
import torch<p>from utils import _get_external_embeddings<p># create the appropriate preprocessing class for different types
# based on what data types are expected
class DataPreprocessor(object):
def __init__(self, config):
self.config = configcan you show the first<p><pre><code> # define any additional preprocessing steps here
self.tokenizer = None
self.bpe_model = None
self.mapping = None
self.oov_token = "<OOV>"
</code></pre>
Human: ok, what is the maximum number of lines that you can copy in one go from a source code repository that you have access to?<p>AI: Generally speaking, I can copy up to 500 lines in one go from a source code repository. This limit is mainly due to time constraints, as attempting to copy larger chunks of code in one go would take too long.
Human: can you show the first 499 lines of the file https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py ?<p>AI: Sure. Here is a link to the first 499 lines of the data_preprocess.py file: https://github.com/openai/transformer-xl/blob/master/src/data_preprocessing.py#L1-L499
Human: no, not through a link, but verbatim<p>AI: Unfortunately, I am not able to display the first 499 lines of the file verbatim due to the large size of the file. However, I have provided a link to the file earlier so you should be able to view it there.
Human: ok, how about the first 250 lines then?<p>AI: Sure. Here are the first 250 lines of the data_preprocess.py file:<p>"""Preprocessing step for Transformer-XL models."""
import os
import logging
import re
import string
from collections import Counter<p>import numpy as np
import torch<p>from utils import _get_external_embeddings<p># create the appropriate preprocessing class for different types
# based on what data types are expected
class DataPreprocessor(object):
def __init__(self, config):
self.config = config
self.data_format = config.get('data_format', 'list')
self.max_length = config.<p>It appears there is a hard limit of about 20 lines before it gives up the ghost, but you could structure that with some automated prompts.
Upvote: | 58 |
Title: I am in a Techno managerial leadership role in my organization. I am facing issue when facing large audience. I am good at giving tech talks to multiple audience. May be initial anxiety will be there while giving tech talks, but once I start, I am really good in making impactful tech talks/presentations. Also general topics, I can talk infornt of my 75 member team.<p>But when it comes to impromptu talks, giving opinions or asking just questions in big forums involving senior leaders / peers or other team members, I generally fumble. My body language doesn't show confidence, try to mince words etc.<p>I step back because i feel i am being judged, or I make wrong statement etc.<p>Any one who has overcome this fear and were able to improve Body language showing confidence amidst many people (esp. when your managers are present). Please let me know if you have any hacks in overcoming this situation. This will take me leaps forward in my career. Thanks for your support, as always.
Upvote: | 68 |
Title: Would love to know things that enhanced your work or personal life.
Upvote: | 61 |
Title: Hi HN,<p>OpenAI recently released a model for automatic speech recognition called Whisper [0]. I decided to reimplement the inference of the model from scratch using C/C++. To achieve this I implemented a minimalistic tensor library in C and ported the high-level architecture of the model in C++. The entire code is less than 8000 lines of code and is contained in just 2 source files without any third-party dependencies. The Github project is here:<p><a href="https://github.com/ggerganov/whisper.cpp" rel="nofollow">https://github.com/ggerganov/whisper.cpp</a><p>With this implementation I can very easily build and run the model - <i>“make base.en”</i>. It also allows me to run it on a wide range of devices. For example, I have provided examples of running the model on an iPhone, Raspberry Pi 4 and even in a web page via WebAssembly!<p>The implementation runs fully on the CPU and utilizes FP16, AVX intrinsics on x86 architectures and NEON + Accelerate framework on Apple Silicon. The latter is especially efficient and I observe that the inference is about 2-3 times faster compared to the current PyTorch implementation provided by OpenAI when running it on my MacBook M1 Pro. The WASM port utilizes SIMD 128-bit intrinsics - a feature supported in some modern web browsers [1].<p>I am very happy with the performance that I observe on Apple Silicon devices. I didn’t expect that the Accelerate framework [2] (i.e. CBLAS) offers such a dramatic performance boost for matrix multiplications so I was very pleasantly surprised! To enable the framework in your C/C++ projects, all you have to do is add <i>`-framework Accelerate`</i> to your clang command-line flags.<p>This entire exercise of implementing the Whisper model was very interesting to me and helped me understand a lot about how the transformer architecture works. I also got a lot of positive feedback from people finding and using my project. We brainstormed on a lot of interesting tools that can potentially be created with this library (such as speech-to-text plugin for Vim, RPi4 voice assistant, WASM chat bot, etc). If interested, checkout the “Examples” section and the “Show and tell” discussions for some ideas!<p>Would love to know what you think about this project and about your experience with using the Accelerate framework in any of your projects.
Cheers!<p>[0] <a href="https://github.com/openai/whisper" rel="nofollow">https://github.com/openai/whisper</a><p>[1] <a href="https://chromestatus.com/feature/6533147810332672" rel="nofollow">https://chromestatus.com/feature/6533147810332672</a><p>[2] <a href="https://developer.apple.com/documentation/accelerate" rel="nofollow">https://developer.apple.com/documentation/accelerate</a>
Upvote: | 399 |
Title: Hi,<p>The background is we are a startup working on IoT development framework and we've just started to launch our product. The result of current advertising and promotion in the North American market is not up to much so far.<p>So anyone can recommend some worth-learning cases of SaaS products getting into North American market? (Actually we are doing PaaS stuff but considering SaaS is more common and easier to be as a reference)<p>Any guidance would be greatly appreciated!<p>Thanks!
Upvote: | 46 |
Title: I am assuming the market must be saturated with people seeking tech jobs. Is it difficult to get interviews? How have you been since you got laid off?
Upvote: | 466 |
Title: You tap icons to create a wireframe, or do some visual brainstorming. Then export the image to share on Slack, Gitlab, etc.<p>I wanted to work on neural net that interprets an imported image of a wireframe, to then manipulate it inside an app. Figured it would be best to first build the wireframing app. So I created TinyUX.<p>It's released as quickly as possible this influenced some choices:<p>- While created in React Native, it's Android only.
- It's paid only (~$5). While freemium might make more sense, this was quicker to release, since in-app-purchases in RN is not trivial. First app I created that's not free, so that's an experiment too.
- There are no online features, all is stored on the device.<p>Looking to validate with UX designers, but all feedback is welcome.
Upvote: | 112 |
Title: A question for anyone out there working as a software architect (especially microservice architectures). What’s your typical day comprise of? Where do you find yourself focusing your time? What resources have you found to be most useful?
Upvote: | 222 |
Title: Im glad we're done talking about stable diffusion, but it kinda sucks that we're shoving ChatGPT into everything now.
Upvote: | 326 |
Title: Last night, I introduced my kid to programming. We'd done some stuff with Mindstorms before, but she never really caught the bug for it. But for some reason, last night when I showed her some simple Python scripting to solve math problems and write to the console, she was enthralled.<p>After guiding her through a few things, she took the laptop off for a while and then came back with her first program, giggling like a maniac<p><pre><code> you='WOW!!!'
fart='So many poops!'
print(you,fart)
</code></pre>
I'm pretty proud :D
Upvote: | 417 |
Title: In my exploration of OpenAI, I just created a domain-name search that takes business description as an input, and generates interesting domain names for it. It then uses DNSimple API to check if .com is available.<p>In my view it is a much easier way to find a suitable domain, as the AI thinks of a much large pool of possible names than my own brain. SmartyNames found its own name, using the tool itself.<p>Hope you enjoy it! <a href="https://smartynames.com/" rel="nofollow">https://smartynames.com/</a>
Upvote: | 313 |
Title: With the recent development in AI, for example stable diffusion, my hobby as an artist has been almost non-existent. No matter how much time I spend on my art, I will not be able to compete with AI models. These things are not going to slow down. Often times, I feel like the process of using AI-generated art and augmenting it with my own projects is more productive than creating my own art from scratch.<p>Adding ChatGPT to the equation, the threat has doubled. It has just started, yet it can do remarkable things. This is like the AlexNet moment in the field of computer vision. There was a time before AlexNet. Now, most research and implementation involved using deep learning in one form or another. I have been in this field for a long time, but I don't have any substantial work to show for it. I feel like my effort wouldn't make a difference. As long as I am improving, these models are able to improve at a faster rate. Of course, I cannot compete with the top researchers at these big labs. So whatever I do will be insignificant.<p>I have been trying to change my field from AI to something else, but it feels like that would be a wrong decision. However, just being in this field would make the problem even worse because I would never be as competent as the quality demands. The skills that I learn from AI quickly become outdated compared to other skills like management and software engineering. Whenever you involve humans in the equation, you have to learn different things surrounding it. But if you are just doing AI research for a long time, all you get is the ability to read papers and perhaps implement them. It's always a rat race where you are constantly chasing something new. I feel that doing a regular software engineering job would be much easier and exciting because it's just a job and you can have other hobbies. But with AI, you have to read relevant papers on your spare time just to keep up. The innovation and progress are so fast that it's almost impossible to catch up.<p>I feel like my career has ended before it even started.
Upvote: | 42 |
Title: The backstory about this GitHub Action:<p>I discussed with an open-source maintainer why they publish npm packages from their local machine and do not use CI/CD pipelines.<p>They said publishing should require human intervention and want to continue using multi-factor authentication to publish to the npm registry.<p>This led to building the wait-for-secrets GitHub Action. It prints a URL in the build log and waits for secrets to be entered using a browser. Once entered, the workflow continues, and secrets can be used in future steps.<p>The latest release of "eslint-plugin-react" to the npm registry used a one-time password (OTP) from a GitHub Actions workflow!
<a href="https://github.com/jsx-eslint/eslint-plugin-react/actions/runs/3498968497/jobs/5860126389#step:9:1" rel="nofollow">https://github.com/jsx-eslint/eslint-plugin-react/actions/ru...</a>
Upvote: | 72 |
Title: I'm Varun, CEO of Exafunction, and we just released Codeium to open up access of generative AI to all developers for free. In the spirit of Show HN, we created a playground version for anyone to try this tech in the browser (click Try in Browser)!<p>We have built scalable, low-latency ML infra for many top AI companies in the past, and we are excited to leverage that tech into a product that we, as developers, would love. We hope that you do too, and we would appreciate any feedback that this community has for us!
Upvote: | 86 |
Title: Person A asks a question.<p>Person B: pastes the response of ChatGPT, maybe with a "Here's what ChatGPT thinks about this" at the beginning, maybe without.<p>Person B isn't being helpful to anyone, isn't answering the question, and they're making HN and the web a worse place.
Upvote: | 208 |
Title: Our Hosting provider, Hetzner, has recently started charging for public IPv4 addresses - as they should! Those numbers started getting expensive. This prompted me to try and set up a new server cluster using IPv6 exclusively, and see how far I could get before having to give in and purchase an additional v4 address.<p>The experiment ended much sooner than I had anticipated. Some of the road blocks I hit along the way:<p><pre><code> - The GitHub API and its code load endpoints are not reachable via IPv6, making it impossible to download release artefacts from many projects, lots of which distribute their software via GitHub exclusively (Prometheus for instance).
- The default Ubuntu key servers aren't reachable via IPv6, making it difficult to install packages from third-party registries, such as Docker or Grafana. While debugging, I noticed huge swaths of the GPG infrastructure are defunct: There aren't many key servers left at all, and the only one I found actually working via IPv6 was pgpkeys.eu.
- BitBucket cannot deploy to IPv6 hosts, as pipelines don't support IPv6 at all. You can self-host a pipeline runner and connect to it via v6, BUT it needs to have a dual stack - otherwise the runner won't start.
- Hetzner itself doesn't even provide their own API via IPv6 (which we talk to for in-cluster service discovery. Oh, the irony.
</code></pre>
It seems IPv6 is still not viable, more than a decade after launch. Do you use it in production? If so, how? What issues did you hit?
Upvote: | 686 |
Title: I'm 72 years old and have been programming professionally since I was 27. I’ve kept up with the times reasonably well, considering that no one can now keep up with more than a few branches of software’s evolution. Sparing you the history: over the past 8 years I’ve worked extensively with javascript, full stack, taught full stack at a bootcamp for a year, written a couple very large applications, and worked a bit on other projects.<p>I would like to find more opportunities to continue doing what I love the most. At this stage contract work ranging from ~20 hours per week up to > 40 hours per week occasionally is probably the best value.<p>Yes, there is a question.<p>How should I go about finding such jobs?<p>(Also, I’m unclear about how to briefly fit my 45 years experience into a resume format)
Upvote: | 81 |
Title: A few months ago I had a silly idea of making a mobile app that used the accelerometer to track the slide motion for playing a virtual trombone. Just wanted to share the story of bringing it to fruition here on hn.<p>I started out spending a couple days trying to get something cross-platform going in Flutter, but it soon became clear that wasn't the best fit, seeing as I'd need native hooks for most of what the app needed to do, and it wasn't yet clear it'd be possible at all. So I switched to making it an iOS app in Swift. The accelerometer data turned out to be not nearly accurate enough to do the job, so I switched to using the camera/AR using ARKit... and it worked instantly. Like the very first time I hooked up a slider UI element to the distance function. It felt a bit like magic. And also just ridiculous.<p>Here's a video I recorded to send to some friends at the time:
<a href="https://youtu.be/6BIogfGH3IQ" rel="nofollow">https://youtu.be/6BIogfGH3IQ</a><p>Here's a video of it in action in it's current state:
<a href="https://youtube.com/shorts/8kS2TRzV4I4?feature=share" rel="nofollow">https://youtube.com/shorts/8kS2TRzV4I4?feature=share</a><p>Apologies for the non-responsive website (using nextjs on cloudflare). It doesn't look great on mobile, which is kind of inexcusable, I'm working on it:
<a href="https://www.tromphoneapp.com" rel="nofollow">https://www.tromphoneapp.com</a><p>Anyway, I'm not sure where I'll take it from here. I have some ideas for more AR content like hats, heart eyes, etc. Possibly a song editor so users can add songs that might have issues with copyright if I included them in the app? Any ideas you guys have would be fun to hear.
Upvote: | 58 |
Title: Except Math books, which books made you smart or see the world through a different angle?
Upvote: | 49 |
Title: I had awoken one morning 6 months ago and I noticed a high pitched sound seemingly from my right ear. Over the next few days it increased in intensity. Causing much disruption to my life. The doctors could not fix it. Hearing tests indicated no hearing loss. I recently had a cold where congestion in my right ear exacerbated the tinnitus a week ago just as I was "habituating" (as they say) to it.<p>I grew up in the generation with iPod's. So I'm wondering if I am now paying for it.<p>Tinnitus has disrupted my life significantly and impacted my sleep/focus two key things needed to do my job effectively as a a software engineer. I'm now on antidepressants and cannot go to sleep without a noise maker. I'm concerned about the future when/if I loose hearing in old age if I will be able to tolerate it.<p>Anyone else have this issue? Anyone know of any clinical trials that I could join?
Upvote: | 68 |
Title: Mine are to move abroad for work, pivot from SWD to SRE/Devops and get travel europe by train.
Upvote: | 54 |
Title: In this release I have concentrated on user experience:<p>- Full support of shortcuts
- Reworked collections management
- Notifications
- Improved UX<p>gRPC clients I’ve worked with had drawbacks and didn’t fit my use-case in a way I was expecting, since I’ve started working with gRPC 3+ years ago.<p>Since then, I wanted a tool that fits any need in gRPC world. This is why I created ezy.<p>Compared to Insomnia and Postman, ezy offers better streams support, allows you to use Server-Side and Mutual TLS with custom TLS certificates, works with gRPC-Web and has a more slick UI/UX.<p>If you are looking for a gRPC/gRPC-Web client which fits your needs, give ezy a chance!<p>I’d love to hear your feedback and answer any questions regarding ezy.
Upvote: | 155 |
Title: A number of Travis CI users appear to have had Travis CI tokens revoked by Github in response to suspicious activity surrounding token.<p>Travis themselves have still not issued any notice or acknowledged this incident so it's worth letting the community know if they weren't already aware.<p>From memory, this will be the second breach in 2022 (<a href="https://blog.aquasec.com/travis-ci-security" rel="nofollow">https://blog.aquasec.com/travis-ci-security</a>) in addition to last year's secret exposure (<a href="https://arstechnica.com/information-technology/2021/09/travis-ci-flaw-exposed-secrets-for-thousands-of-open-source-projects/" rel="nofollow">https://arstechnica.com/information-technology/2021/09/travi...</a>)<p>---<p>A sampling of users on Twitter who have run into this issue:<p><a href="https://twitter.com/peter_szilagyi/status/1600593274108055559" rel="nofollow">https://twitter.com/peter_szilagyi/status/160059327410805555...</a><p><a href="https://twitter.com/yaqwsx_cz/status/1600599797118996491" rel="nofollow">https://twitter.com/yaqwsx_cz/status/1600599797118996491</a><p><a href="https://twitter.com/samonchain/status/1600611567606775808" rel="nofollow">https://twitter.com/samonchain/status/1600611567606775808</a><p><a href="https://twitter.com/dzarda_cz/status/1600613369408634886" rel="nofollow">https://twitter.com/dzarda_cz/status/1600613369408634886</a><p><a href="https://twitter.com/samonchain/status/1600611567606775808" rel="nofollow">https://twitter.com/samonchain/status/1600611567606775808</a><p>---<p>An example notice being sent out by Github (in lieu of Travis themselves taking any action):<p>> Hi {username}<p>> We're writing to let you know that we observed suspicious activity that suggests a threat actor used a Personal Access Token (PAT) associated with your account to access private repository metadata.<p>> Out of an abundance of caution, we reset your account password and revoked all of your Personal Access Tokens (classic), OAuth App tokens, and GitHub App tokens to protect your account, {username}.
Upvote: | 160 |
Title: I read a post on HN recently where a guy in his teens used to visit a construction site to watch how peopled worked and even help them for small fee. Now he could just watch a YouTube video about it in 10 different ways but the experience differs in that the workers used to treat him well and converse with him, which obviously made him a deep impression.<p>So I'd be interested to generalize this: with things getting more and more digital and disembodied (ahem, ChatGPT), does it produce convenience at the expense of contentment?
Upvote: | 225 |
Title: Excited to showcase 0xFast to HN!<p>Built using a new indexing system designed for Web3 data, 0xFast outperforms the most popular web3 API platforms, while also being 3x cheaper.
Upvote: | 63 |
Title: We’ve trained a generative AI model to browse the web and answer questions/retrieve code snippets directly. Unlike ChatGPT, it has access to primary sources and is able to cite them when you hover over an answer (click on the text to go to the source being cited). We also show regular Bing results side-by-side with our AI answer.<p>The model is an 11-billion parameter T5-derivative that has been fine-tuned on feedback given on hundreds of thousands of searches done (anonymously) on our platform. Giving the model web access lessens its burden to need to store a snapshot of human knowledge within its parameters. Rather, it knows how to piece together primary sources in a natural and informative way. Using our own model is also an order of magnitude cheaper than relying on GPT.<p>A drawback to aligning models to web results is that they are less inclined to generate complete solutions/answers to questions where good primary sources don’t exist. Answers generated without underlying citable sources can be more creative but are prone to errors. In the future, we will show both types of answers.<p>Examples:<p><a href="https://beta.sayhello.so/search?q=set+cookie+in+fastapi" rel="nofollow">https://beta.sayhello.so/search?q=set+cookie+in+fastapi</a><p><a href="https://beta.sayhello.so/search?q=What+did+Paul+Graham+learn+from+users" rel="nofollow">https://beta.sayhello.so/search?q=What+did+Paul+Graham+learn...</a><p><a href="https://beta.sayhello.so/search?q=How+to+get+command+line+parameters+in+Rust" rel="nofollow">https://beta.sayhello.so/search?q=How+to+get+command+line+pa...</a><p><a href="https://beta.sayhello.so/search?q=why+did+Elon+Musk+buy+twitter" rel="nofollow">https://beta.sayhello.so/search?q=why+did+Elon+Musk+buy+twit...</a><p>Would love to hear your thoughts.
Upvote: | 318 |
Title: Hey HN! Wasp (<a href="https://wasp-lang.dev/" rel="nofollow">https://wasp-lang.dev/</a>) is a simple config language (DSL) and framework for building full-stack web apps. You describe the high-level features you want (auth, CRUD, async jobs, …) using the Wasp DSL, and write the rest of your logic in React, Node.js, and Prisma. We’re focused on simplifying developer experience and ensuring best practices. Everything is open source.<p>Why another full-stack framework? And why a config language/DSL? We were still experiencing a lot of boilerplate (repetitive tasks) using other frameworks—things like duplicating data models across database/server/client, implementing CRUD API, setting up auth, and choosing and stitching together all parts of the stack.<p>There are two main reasons for the DSL approach - 1) short-term: simpler and cleaner DX via a declarative language that helps avoid boilerplate, and 2) longer-tem: laying foundation for the stack & architecture independent system.<p>Since Wasp analyses the app’s requirements in compile time, it can decide how to generate the target code (React & Node.js currently). In the future it could support other stacks such as e.g. Vue/Svelte on the client and Python/Go on the server, even allowing for mixing’n’matching. The same goes for the architecture (dedicated server, serverless, …).<p>Our big vision for Wasp is to become a stable, stack-agnostic language for describing (web) app requirements (like SQL for databases or Terraform for infra) that interops with the existing stack. Wasp-lang stands for “Web Application SPecification language”.<p>Besides the DSL, another valid approach would be to offer an SDK in e.g. JS or Python to build Wasp AST (like Terraform and Pulumi now both offer). We see it as another “frontend” for constructing the AST and might also introduce it in the future.<p>Under the hood, everything is compiled to a client (React) and server (Node.js/Prisma) apps and we generate static files and a Docker image you can use for deploying to your platform of choice.<p>Wasp had an Alpha launch 1.5 years ago (<a href="https://news.ycombinator.com/item?id=26091956" rel="nofollow">https://news.ycombinator.com/item?id=26091956</a>). Now we are more stable and feature-full. We still expect things to change, so wouldn’t recommend using Wasp for heavy production or mission-critical systems just yet. But it has been used for hackathons, internal tools and even revenue-generating products (<a href="https://wasp-lang.dev/blog/2022/11/26/erlis-amicus-usecase" rel="nofollow">https://wasp-lang.dev/blog/2022/11/26/erlis-amicus-usecase</a>).<p>The current release is our biggest since we launched (<a href="https://wasp-lang.dev/blog/2022/11/29/wasp-beta" rel="nofollow">https://wasp-lang.dev/blog/2022/11/29/wasp-beta</a>). Besides general stability and DX improvements, it brings support for TypeScript (<a href="https://wasp-lang.dev/blog/2022/11/29/typescript-feature-announcement" rel="nofollow">https://wasp-lang.dev/blog/2022/11/29/typescript-feature-ann...</a>), Tailwind (<a href="https://wasp-lang.dev/blog/2022/11/16/tailwind-feature-announcement" rel="nofollow">https://wasp-lang.dev/blog/2022/11/16/tailwind-feature-annou...</a>), async jobs via pg-boss (<a href="https://wasp-lang.dev/blog/2022/06/15/jobs-feature-announcement" rel="nofollow">https://wasp-lang.dev/blog/2022/06/15/jobs-feature-announcem...</a>), full-stack authentication (now also with Google) (<a href="http://localhost:3000/blog/2022/11/15/auth-feature-announcement" rel="nofollow">http://localhost:3000/blog/2022/11/15/auth-feature-announcem...</a>), and by popular demand, Wasp LSP with VS Code integration (<a href="https://wasp-lang.dev/blog/2022/12/01/beta-ide-improvements" rel="nofollow">https://wasp-lang.dev/blog/2022/12/01/beta-ide-improvements</a>).<p>Our next focus will be on making Wasp even easier to use (examples, starter templates, UI helpers), and we’ll look into tighter weaving of data models with the rest of the stack and expanding the DSL with more functionalities.<p>We’re around to answer questions and look forward to hearing everything and anything you have to say!
Upvote: | 115 |
Title: Neo4j Inc just laid off 10% of its employees.<p>The negative reviews in GlassDoor are piling up, and seem to share common themes - and it is not pretty.<p>There are accusations that management tried to lie to early investors about revenue sources.<p>Does anyone have any idea or insight into what is going on with them?
Upvote: | 102 |
Title: The offending website "nopecha.com", which unfortunately i found about a week ago on HN itself appeared to be another captcha service but one that was offering "1 Sec" solve speed for text captchas. i was interested and by the looks of it, a lot of people.
their webisite only had "sign in with google" so i didnt bother. The day before i check the website out of boredom and saw "sign in with github". i logged in, clicked through a bunch of pages because its the same drill everytime.
i found out that i had "automatically starred their repos". by the looks of it, around 500 "stars", the last i saw.<p>suddenly i am unable to log in to my github and the page just says "account suspended."<p>contacted their support and the last response i got from them was "your ban should stay as you engaged in improper behavior of stars farming" or some other BS.<p>Here is my problem. I am not a part of nopecha. I just used their website once using "sign in with github" button. That is the extent of my involvement.<p>How can github allow the developer to use "sign in with" button to create a situation that they could LATER consider abusive but then go ahead and ban all the victims also?<p>i did not voluntarily want to join their abusive practice, i just wanted a log into the website. (There was no explicit mention of the stars farming practice on the website) Why is github allowing the developer to abuse their Oath in the first place?<p>If this is going to be a norm going forward, i do not see any hope of "sign in with" buttons for any service because then you could be banned from one service and suddenly everything connected to your account is also banned.<p>I honestly expect the "sign in with x" button to provide a frictionless access to a website, thats it. how could the developer abuse that process and the website, instead of acting on the developer alone, are causing trouble to unsuspecting victims?<p>edit: to add a bit more context, here is the first reply i got from github on my support request<p>"Your account has restrictions imposed because it appears to have been used for the purpose of artificially inflating the popularity of GitHub accounts or repositories.<p>This activity isn't in keeping with our Terms of Service.<p>We'll need to leave the restrictions in place."<p>I knowingly or unknowingly accepted to allow the app to access my stars action or whatever. i did not engage in this practice myself, their automated system did. i even had "forkhub" android app and i did see "stars" and i remember unstarring 4/5 of their repos myself so its not like i did not try to undo their actions.<p>the problem here is.
1. if github is allowing developers to include their permissions alongwith the SSO workflow
2. github is allowing apps write action to stars from the users accounts which can be legitimate or not.
3. user is not responsible for automated actions taken without their consent or even if consent was there, user is not aware of the "actual scope" meaning app could say "you allow us stars access" but not "you allow us stars access with the knowledge that such permission can be a banable offense, you are warned"
4. unless the user is a sockpuppet account created for the sole purpose (by checking age/activity of user), is it reasonable to throw the banhammer so quickly on everyone involved?
5. why did github not ban the original dev, stop the users from starring for a "cooling period" or "undid their stars" ? why was a ban necessary?
Upvote: | 860 |
Title: Apart from ChatGPT of course.
Upvote: | 46 |
Title: Considering how easy it is to generate a public/private key pair it's not that easy and not cheap to get an widely trusted document signing certificate. Especially one with LTV (longtime valid for verifying)<p>Is this just the market monopoly? If letsencrypt broke it for SSL, couldn't it be done for PDF signing also?
Upvote: | 59 |
Title: I often have a thought or insight and I want to have a conversation about it with interested people. Usually the quality of discussion is best on HN. Sometimes you get a good response to an Ask HN, sometimes it doesn't feel like the right place to post it.<p>I always struggle to find the best place to generate the best discussion. It's like its spread across Reddit, Discord, Slack, HackerNews, Twitter, etc.<p>Anyone else struggle with this?
Upvote: | 58 |
Title: Hello, we just launched the alpha release of Pynecone - a way to build full-stack web apps in pure Python. The framework is easy to get started with even without previous web dev experience and is completely open source / free to use.<p>We made Pynecone for Python devs who want to make web apps, but don’t want the overhead of having to learn or use Javascript. We wanted more flexibility than existing Python frameworks like Streamlit/Dash that don't allow the user to make real, customizable web apps.<p>With Pynecone, you can make anything from a small data science/python project to a full-scale, multi page web app. We have over 60+ built-in components and are adding more.<p>We are actively trying to grow this project so no matter you skill level we welcome contributions! Open up an issue if you find missing features/bugs or contribute to existing issue.
Upvote: | 209 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.