prompt
stringlengths 16
15.6k
| completion
stringlengths 4
6
|
|---|---|
Title: I've been using Google Maps a long time, and during all of that time I have only used GPS for location tracking on Android.<p>Depending upon the version of Android, I've had different things disabled. Wifi scanning. Bluetooth. Cell location data. Etc. Always with one single goal -- GPS only for location.<p>And further, this is always, especially with newer versions of Android, restricted in many ways. For example, only allowing when an app is active, and so on.<p>Google has always played games with Maps, using dark patterns. For example, with the versions prior to the current version, if I wanted Maps to zoom in on my location, I'd hit the tracking button.<p>It'd first say something like "To continue, turn on device location". Of course, device location <i>is</i> on, but it's only for GPS, and google <i>so badly</i> wants that (apparently) vital, and sweet wifi + bluetooth + cell tracking data.<p>Yet you could cancel this before, and it would then zoom in on your present location. Because, of course, GPS works <i>fine</i> for that.<p>I could also use only GPS, leaving wifi and bluetooth and so on scanning off to use navigation. I've driven all over North America and Europe that way too, and yes with Maps. Tricky dark patterns (ie, lying) about needing wifi scanning to find a route is just insulting, and absurd.<p>Now, enter a new update. I can no longer navigate with Google Maps, unless full location tracking is on. Comments in Play Store indicate others hit the same wall. Yeah, right Google, driving in the middle of the country, with GPS, is helped by scanning wifi while I pass farmer's fields?!<p>Google has now drawn a line in the sand. Give us all your local SSIDs, local bluetooth connections, with likely even more detail, or they now refuse to allow you to use Maps to navigate.<p>I immediately installed Organic Maps, and I'm sure there are loads of others as an option.<p>Google wants that wifi data <i>so bad</i>, that the only thing I can equate it to, is a used car salesperson. I get the impression that the Maps team is channeling Sméagol, and just <i>shudder</i>.
Upvote: | 745 |
Title: I received an email from Google yesterday that communicated, with much obfuscation, the following key points:<p>- The “Web & App Activity” setting for Google Workspace users will be ignored by Gmail, Drive, Docs, Calendar, Chat, Meet, Keep, and several other services.<p>- Tracking for these services will be controlled by a new user setting, “Google Workspace Search History”, which will default to on regardless of the user’s Web & App Activity setting.<p>- The ability of Google Workspace organizations to turn off “Web & App Activity” for all users will be removed.<p>- These changes will take effect on 2022-03-29.<p>Full email text: <a href="https://pastebin.com/raw/5ayJTDDp" rel="nofollow">https://pastebin.com/raw/5ayJTDDp</a><p>More info from Google: <a href="https://support.google.com/a/answer/11194328" rel="nofollow">https://support.google.com/a/answer/11194328</a>
Upvote: | 947 |
Title: Hey there,<p>First time posting on Hacker News in about 2 years! The reason I’m posting is that I thought I’d write about the product I’ve been building, in hopes it resonates with people.<p>Why build yet another social app? Because I deleted almost all social media around 3/4 years ago as it was just net negative on my life. There was very little that was truly interesting, I didn’t care about looking good to other people and because of the ‘media’ and ads, the apps were all designed to make me spend too much time for what I was getting. I hated it and what it meant for people’s behaviour, including mine and my friends.<p>I also noticed that the vast majority of my friends were pretty much passive on the services, even if they had an account. Turns out that most people felt uncomfortable sharing to people they didn’t know too well, which inevitably happens as you meet new people, add them, and often don’t develop the relationship much further. I had a sense that there could be a better way.<p>In that, I remembered the days of Path and Google+ which had the model of focusing on particular people in your network, both through the feed and in how you shared. Path in particular was a ‘real life’ social network, something that despite being brought to market in 2010 or whatever, seemed to be more relevant today.<p>So problem found, problem solved. I took the journey of learning how to code when COVID hit (I was working in Architecture and Design and was about to start my masters degree at Harvard GSD in Boston), then one thing led to another, my prototype garnered some investment interest, and Circles was born.<p>The idea is very much like the name suggests, it’s about adding your contacts (synced through your phonebook) into Circles that define what the relationship is. This means that you only see things from people you have tagged (rather than everyone) and when you share, you choose exactly who it goes to (rather than all your friends or followers).<p>It also takes cues from other privacy focused social products. Posts are encrypted, reactions and comments are only shown to people who are contacts with eachother, and user profiles only show that which has been explicitly shared to the user viewing the profile.<p>As they were mentioned briefly before, it’s essentially a crossover between Path and Google+ with a wrap around layer of privacy, so the potential revenue has to eventually come through paid features rather than ads.<p>We’re in the app store and google play store (yay, cross-platform JS frameworks), the invite code is ‘FULLCIRCLE’ and download links are below:<p>Landing: <a href="https://oncircles.com" rel="nofollow">https://oncircles.com</a><p>iOS: <a href="https://apps.apple.com/gb/app/circles-share-more-with-less/id1532621483" rel="nofollow">https://apps.apple.com/gb/app/circles-share-more-with-less/i...</a><p>Android: <a href="https://play.google.com/store/apps/details?id=com.oncircles" rel="nofollow">https://play.google.com/store/apps/details?id=com.oncircles</a><p>I would love to hear your feedback and suggestions on the idea. Hit or miss?<p>PS: If you want to chat about the idea or are interested in working together I’d love to chat. Always interesting to meet people on HN and we have the funds, ideas and drive to continue making cool things that can solve big problems. Send me an email at [email protected]<p>Thanks!
Upvote: | 76 |
Title: Hey there,<p>First time posting on HN. We're looking for feedback from parents.<p>We're 2 dads who started working on Dadditude in the midst of covid lockdowns last year.<p>Being a dad can be a long, emotional, draining, and lonely journey. Through our research we learned that dads want to improve their parenting but are too shy to ask for help, and are tired of reading content online written for mums. We set out to fix that and create a platform that would help dads feel seen, validated, and supported.
By helping dads, we hope to support moms and partners too, because all parents deserve more support.<p>Quick timeline so far:
We started a community of dads on Instagram last Feb to test hypothesis and learn about their needs. We then launched an MVP in April, a super simple app serving weekly coaching guides created with a parenting professional partner.
We made several updates in summer and fall, working like crazy in the background to convince parenting professionals to write coaching guides for us. Especially hard when you're a nobody. But people are kind and we found all the support we needed.
We launched a v1 app mid-December with 50 coaching guides and a more full fledge community board (and a paid membership tier).
We've just added on-demand parenting professional support in Jan.
And last week added a picture board for dads to upload pics of their families, and that's become more popular than the forums!! ← I knew dads wanted to feel more visible but I love these discoveries!<p>Super proud of the work done so far, but still so much to do to smooth out the product experience, and get closer to PFM. So much learning.<p>web: <a href="http://www.dadditude.app" rel="nofollow">http://www.dadditude.app</a>
ios: <a href="https://apps.apple.com/app/id1558653576" rel="nofollow">https://apps.apple.com/app/id1558653576</a>
android: <a href="https://play.google.com/store/apps/details?id=com.dadditude.app" rel="nofollow">https://play.google.com/store/apps/details?id=com.dadditude....</a><p>(part of the experience is behind a paywall, but you can test nearly all paid features once for free - so long as you register through Apple or Google)<p>All thoughts and feedback welcome in the comments below, especially if you're a parent entrepreneur. TYIA<p>[edited top statement to "<i>can be</i> long..." for the dads here who felt it was too gloomy - it was]
Upvote: | 116 |
Title: Bob Extension just added ability to resolve Handshake domain with webtorrent.<p>Any Handshake TLDs can update its TXT record with a magnet link pointing to a folder that contains a index.html page - Bob Extension will download and show the content using webtorrent when users go to the TLDs (e.g. federalistpapers/)<p><a href="https://github.com/kyokan/bob-extension/pull/18" rel="nofollow">https://github.com/kyokan/bob-extension/pull/18</a>
Upvote: | 83 |
Title: For example, paste this into Slack or Discord or whatever: <a href="https://news.ycombinator1.com/item?id=30179549" rel="nofollow">https://news.ycombinator1.com/item?id=30179549</a><p>It works with comments, too: <a href="https://news.ycombinator1.com/item?id=30180253" rel="nofollow">https://news.ycombinator1.com/item?id=30180253</a><p>Hastily-developed source: <a href="https://github.com/statico/ycombinator1.com" rel="nofollow">https://github.com/statico/ycombinator1.com</a>
Upvote: | 119 |
Title: Hi HN, we’re Mokshith and Abhi from Sieve (<a href="https://sievedata.com" rel="nofollow">https://sievedata.com</a>). We’re building an API that lets you add video search to internal tools or customer applications, instantly. Sieve can process 24 hours of video in less than 10 minutes, and makes it easy to search video by detected objects / characteristics, motion data, and visual similarity. You can use our models out of the box, or plug-in your own model endpoints into our infrastructure. ('Model' here means any software that produces output given an image.)<p>Every industry from security, to media, supply chain, construction, retail, sports, and agriculture is being transformed by video analytics—but setting up the infrastructure to process video data quickly is difficult. Having to deal with video ingestion pipelines, computer-vision model training, and search functionality is not pretty. We’re building a platform that takes care of all of this so teams can focus on their domain-expertise, building industry-specific software.<p>We met in high school, and were on the robotics team together. It was our first exposure to computer vision, and something we both deeply enjoyed. We ended up going to UC Berkeley together and worked on computer vision at places like Scale AI, Niantic, Ford, NVIDIA, Microsoft, and Second Spectrum. We were initially trying to solve problems for ourselves as computer vision developers but quickly realized the unique problems in video having to do with cost, efficiency, and scale. We also realized how important video would be in lots of verticals, and saw an opportunity to build infrastructure which wouldn’t have to be rebuilt by a fullstack dev at any company again.<p>Let’s take the example of cloud software for construction which might include tons of features from asset trackers to rental management and compliance checks. It doesn’t make sense for a construction software company to build their own video processing for telematics—the density and scale of video make this a difficult task. A single 30 FPS camera generates over 2.5M frames within a day of recording. Imagine this across thousands of cameras and many weeks of footage—not to mention the actual vertical-specific software they’re building for end users.<p>Sieve takes care of everything hard about processing and searching video. Our API allows you to process and search video with just two API calls. We use filtering, parallelization, and interpolation techniques to keep costs low, while being able to process 24 hours of video in under 10 minutes. Users can choose from our pre-existing set of models, or use their own models with our video processing engine. Our pricing can range anywhere from $0.08-$0.45 per minute of video processed based on the models clients are interested in and usage volume. Our FAQ page (<a href="https://sievedata.com/faq" rel="nofollow">https://sievedata.com/faq</a>) explains these factors in more detail.<p>Our backend is built on serverless functions. We split each video into individual chunks which are processed in parallel and passed through multiple layers of filters to determine which chunks are “important”. We’re able to algorithmically ignore parts of video which are static, or change minimally, and focus on the parts that contain real action. We then run more expensive models on the most “important” parts of video, and interpolate results across frames to return information to customers at 30 FPS granularity. Our customers simply push signed video URLs to our platform, and this happens automatically. You can then use our API to query for intervals of interest.<p>We haven’t built an automated sign up flow yet because we're focused on building out the core product for now. But we wanted to give all of you the chance to try Sieve on your own videos for free, so we've set up a special process for HN users. Try it out here: <a href="https://sieve-data.notion.site/Trying-Sieve-s-Video-Search-4bd7754bb04d468fb1a6c98225f68ccb" rel="nofollow">https://sieve-data.notion.site/Trying-Sieve-s-Video-Search-4...</a>. We'll email you a personal, limited-access API key.<p>Here's a video demo of using our dashboard to do video search: <a href="https://www.youtube.com/watch?v=_uyjp_HGZl4" rel="nofollow">https://www.youtube.com/watch?v=_uyjp_HGZl4</a><p>We’d love to hear what you think about the product and vision, and ideas on how we can improve it. Thanks for taking the time to read this, we’re grateful to be posting here :)
Upvote: | 71 |
Title: Getting 500 errors, multiple friends confirming: https://github.com
Upvote: | 188 |
Title: Hey HN: Kaveh here, the founder of https://www.usage.ai/<p>We help companies drive down AWS EC2 spend. Why? Because the way it's done now is a pain. DevOps and Software Engineers end up spending time managing costs rather than focusing on business problems.<p>Previous to founding Usage, I worked on high-performance computing research at JP Morgan Chase and as a software engineer at a number of smaller startups.<p>Here's how it works: We are typically brought in by a DevOps manager to cut AWS EC2 costs. The app is entirely self-service and the savings are generated automatically, typically we do this live on a call. On average, we reduce AWS EC2 spend by 50% for 5 minutes of work.<p>To reduce by 50%+, we don't touch the instances, require any code change, or change the performance of your instances. We buy Reserved Instances on your behalf (a billing layer change only) and bundle them with guaranteed buyback. So you get the steep 57% savings of 3-year no-upfront RIs with none of the commitment (you can sell them back to us anytime after 30 days).<p>We make money off of a 20% Savings Fee. Happy to chat directly [email protected]<p>Have you experienced any issues with managing your company or organization's AWS expenses? We'd love to hear your feedback and ideas!
Upvote: | 123 |
Title: Hello HN,
not many will know what this tool is about, but it's launch day and I always dreamed of posting on HN. Let's start!<p>This is a tool for people using eurorack gear. For synth people. What is cool about my tool is that I show the signal flow with a graph. Here's the official press text:<p>After a decade of stagnation in this space we are excited to present patcher.xyz: the modern way to manage everything modular.<p>It’s a tool for professionals, enthusiasts, and casual wigglers.<p>Novadays artists must develop their own means of taking notes, often on paper, since there is no common format for sharing ideas. Although there is nothing wrong with that, we believe we have found a better way.<p>We wanted our patch ideas to be searchable, editable and easily-shareable. We needed an easier way to plan our racks, without creating a mess. We needed to be able to find awesome modules fitting our style and feel, without being lost in the ocean of different options.
We made it a reality.<p>patcher.xyz was built to provide a fast and enjoyable experience while bypassing the limitations of current offerings. Our vision is to build a platform to assist you in any part of your wiggling experience: from research, to planning, to buying or trading gear, to sharing your new ideas and music.
Upvote: | 53 |
Title: Several months ago, I built a "stealth" feature that I could use. It hasn't been advertised, and I've been the only user. As I find it useful for myself, I believe others (software developers) may like it too. So, this is the first public post about it, and if it gets any positive feedback, I may put some time into promoting it more.<p>In essence, given that you've opened a GitHub repo (there are ~225k of the more popular ones indexed as of now), you can replace "github" with "libhunt" within the URL, and you will find the top alternatives and related projects.<p>For example, here are three popular repos:<p>- <a href="https://github.com/rails/rails" rel="nofollow">https://github.com/rails/rails</a><p>- <a href="https://github.com/vercel/next.js" rel="nofollow">https://github.com/vercel/next.js</a><p>- <a href="https://github.com/kovidgoyal/calibre" rel="nofollow">https://github.com/kovidgoyal/calibre</a><p>To test it out, open any of the examples above and replace "github" with "libhunt" within the browser URL. You can also try with any other repository as long as it's a bit popular.<p>I'd be more than happy to answer any questions and receive some feedback. Thanks!
Upvote: | 120 |
Title: When I was a kid, I had an Apple II with a BASIC interpreter, Print Shop Pro to make really cool cards and banners, Where in the World is Carmen Sandiego to learn about geography, Pinball Construction Set, Number Munchers, Oregon Trail, and LOGO for programming the turtle.<p>Today I can't see a way of giving my kids a computer like that, where there are a lot of open-ended ways to create. The iPad games are too directly educational, or mindless, and great creative experiences don't seem available on desktop or iPad suitable for early elementary schoolers.<p>Any suggestions here? I will be happy to pay $.
Upvote: | 252 |
Title: I'm curious what various services people provide in tech and what their consulting rate is...<p>Can you share?<p>It would be interesting to see the highest paying fields.
Upvote: | 98 |
Title: In April last year I started thinking about using Twitter in a smarter way. I wanted to do analytics on my tweets and find out more about people following me on Twitter. What kinds of things do people who follow me like and retweet? I decided to dig into the data and find out.<p>When I went to try and download Twitter data in raw form I found I quickly got bogged down writing API wrangling code and fiddling with API keys. I just wanted to crunch some data but here I was wrangling Twitter's API. This was such a frustrating experience it suddenly looked like an opportunity to me. Was there room for a product here? A product which does one simple thing: help people extract Twitter data painlessly without writing any code.<p>I did some research and discovered some tools that purported to do this, but none of them worked well for my use-case and all were badly designed and/or expensive. I decided to take a shot at it.<p>I worked on this as a side project in a "calm company" fashion. Each week for 26 weeks I would put aside one day to chip away at the features. I tried not to think about how the issue tracker was filling up more and more. Several times I pared back the feature set to try to really focus on the core use-case.<p>When my first user reached out and engaged I knew I might be onto something. I kept posting progress on Twitter and a few more people started to use it each week. Some of them came back, hinting at possible user retention. I hired a writer to write some articles to help with SEO and I kept working towards and MVP that I could use to test the market.<p>Finally the day arrived where all of the critical issues in my issue tracker were closed. That meant it was launch day. That was yesterday. So here I am releasing this on Hacker News to you, dear reader.<p>God speed little micro-SaaS, may the winds of fortune be at your back.
Upvote: | 57 |
Title: I have seen that most carriers, by default, have a "stream saver" turned on, which, I am assuming detects when you're on YouTube or Netflix and automatically throttles your bandwidth to these sites. Assuming these connections are happening over SSL, how are the carriers able to modify the sites to disable users from selecting HD or 4k resolutions?
Upvote: | 97 |
Title: It's surprising to me that so many crypto projects don't use TLA+.
Besides the ones mentioned here (<a href="https://lamport.azurewebsites.net/tla/industrial-use.html" rel="nofollow">https://lamport.azurewebsites.net/tla/industrial-use.html</a>), does your company use TLA+?
Why? Why not?
Upvote: | 49 |
Title: Has anyone else noticed that HN feels a lot more angry all around lately? There seems to be little peace or excitement in people's comments. It feels mostly like people attacking each other or attacking something.<p>I know the pandemic has been hard; but, we've got to fight to keep our peace through this and not attack others during this time, where we can.
Upvote: | 177 |
Title: This is a little toy project of mine that lets you simulate digital logic graphs. It was inspired by Minecraft's Redstone and the Piet esolang.<p>It's got some serious drawbacks-- you write circuits as PNGs and simulate them with a Python interface. It's slow to run and slow to experiment with. And it is certainly difficult to use for people with any kind of color blindness. But despite that, I hope this can still be a fun toy!
Upvote: | 259 |
Title: Our team is filled with technologists and creators, and when we record and edit videos, 80% of the time is spent chopping up the video, removing silences, and picking the right takes. So we decided to build a tool that did that for you — or at least get you there most of the way!<p>Our initial implementation is somewhat naïve and uses a user configurable silence threshold that just reads in volume levels. In the future, we’d like to use a frequency-based approach that focuses on the human voice. We’re also open to ideas, so let us know if you have any!
Upvote: | 171 |
Title: Hi HN, we’re Eduardo & Ido, the founders of Ploomber (<a href="https://ploomber.io" rel="nofollow">https://ploomber.io</a>). We’re building an open-source framework (<a href="https://github.com/ploomber/ploomber" rel="nofollow">https://github.com/ploomber/ploomber</a>) that helps data scientists quickly deploy the code they develop in interactive environments (Jupyter/VScode/PyCharm), eliminating the need for time-consuming manual porting to production platforms.<p>Jupyter and other interactive environments are the go-to tools for most data scientists. However, many production data pipeline platforms (e.g. Airflow, Kubernetes) drag them into non-interactive development paradigms. Hence, when moving to production, the data scientist’s code needs to move from the interactive environment to a more traditional software environment (e.g. declaring workflows as Python classes). This process creates friction since the code needs to cross this gap every time the data scientist deploys their work. Data scientists often pair with software engineers to work on the conversion, but this is time-consuming and costly. It’s also frustrating because it’s just busy work.<p>We encountered this problem while working in the data space. Eduardo was a data scientist at Fidelity for a few years. He deployed ML models and always found it annoying and wasteful to port the code from his notebooks into a production framework like Airflow or Kubernetes. Ido worked as a consultant at AWS and constantly found that data science projects would allocate about 30% of their time to convert a notebook prototype into a production pipeline.<p>Interactive environments have historically been used for prototyping and are considered unsuitable for production; this is reasonable because, in our experience, most of the code developed interactively exists in a single file with little to no structure (e.g., a gigantic notebook). However, we believe it’s possible to bring software engineering best practices and apply them to the interactive development world so data scientists can produce maintainable projects to streamline deployment.<p>Ploomber allows data scientists to quickly develop their code in modular pipelines rather than a giant single file. When developed this way, their code is suitable for deployment to production platforms; we currently support exporting to Kubernetes, AWS Batch, Airflow, Kubeflow, and SLURM with no code changes. Our integration with Jupyter/VSCode/PyCharm allows them to iteratively build these modular pipelines without moving away from the interactive environment. In addition, modularizing the work enables them to create more maintainable and testable projects. Our goal is ease of use, with minimal disturbance to the data scientist’s existing workflows.<p>Users can install Ploomber with pip, open Jupyter/VSCode/PyCharm, and start building in minutes. We’ve made a significant effort to create a simple tool so people can get started quickly and learn the advanced features when they need them. Ploomber is available at <a href="https://github.com/ploomber/ploomber" rel="nofollow">https://github.com/ploomber/ploomber</a> under the Apache 2.0 license. In addition, we are working on a cloud version to help enterprises operationalize models. We’re still working on the pricing details, but if you’d like us to let you know when we open the private beta, you can sign up here: <a href="https://ploomber.io/cloud" rel="nofollow">https://ploomber.io/cloud</a>. However, the core of our offering is the open-source framework, and it will remain free.<p>We’re thrilled to share Ploomber with you! If you’re a data scientist who has experienced these endless cycles of porting your code for deployment, an ML engineer who helps data scientists deploy their work, or you have any feedback, please share your thoughts! We love chatting about this domain since exchanging ideas always sheds light on aspects we haven’t considered before! You may also reach out to me at [email protected].
Upvote: | 126 |
Title: In the past 2-3 years basically every major, modern piece of software I use has added dark mode. Everything from macOS to the Google Maps app has added a dark mode, and many websites have a toggle as well. GitHub has added like 3 different dark modes!<p>If you've ever worked on a mobile app or website before you know that going from one theme (light mode) to two themes (light / dark) is a huge task. You have to make all the colors in your app super generic. And it's even harder than that, because you can't just switch colors one-for-one. In a well-designed dark mode you have to rethink a lot of UI concepts (mostly around light, shadow, and contrast) in order to make things look nice.<p>I am not opposed to dark mode at all, I think it often looks nice, but as someone who has spent some time in big companies I am really shocked at the level of engineering resources that have been spent on this relatively frivolous feature. Most engineering teams have a huge backlog of features/bugs to fix. Dark mode has somehow made the top of the stack.<p>So I'm asking HN. Have you worked on a major app that added dark mode? Who within your organization pushed to prioritize it? How much time did it take and was it harder/easier than you expected?
Upvote: | 41 |
Title: I spend so much of my work and leisure time on devices and have been trying to reduce this. For example, I've recently switched to an iPod Classic for a lot of my music listening which has been quite nice.<p>I also spend a lot of time browsing and reading interesting articles, particularly on HN and want to replace some of that with 'offline' alternatives. When it comes to other hobbies (sports, music) I have found some great magazines still in circulation that can work as alternatives to browsing online.<p>I'd love to hear your suggestions for tech related magazines, ideally things I can subscribe to and get monthly/quarterly. These should be varied enough to cover the kind of topics we see here on HN daily as opposed to super general tech news type magazines.
Upvote: | 237 |
Title: Meta submitted their yearly report to the SEC [0] which states:<p>> If a new transatlantic data transfer framework is not adopted and we are unable to continue to rely on SCCs or rely upon other alternative means of data transfers from Europe to the United States, we will likely be unable to offer a number of our most significant products and services, including Facebook and Instagram, in Europe, which would materially and adversely affect our business, financial condition, and results of operations.<p>[0] https://d18rn0p25nwr6d.cloudfront.net/CIK-0001326801/14039b47-2e2f-4054-9dc5-71bcc7cf01ce.pdf
Upvote: | 81 |
Title: System76 recently announced their responsiveness optimizer, System76 Scheduler [0], which basically works as a daemon, adjusting the nice value and the CFS knobs for processes in the box for increased responsiveness. They've claimed that the responsiveness is therefore increased, which I'm also believed so.<p>However, this got me wondering, is there exists any tool that can report the "numbers" (e.g., scheduling latency) regarding to the responsivenss? Maybe Google has such tool for testing regression for Android or Chrome OS, sadly, I didn't managed to find one.<p>Thanks!<p>[0] <a href="https://github.com/pop-os/system76-scheduler" rel="nofollow">https://github.com/pop-os/system76-scheduler</a>
Upvote: | 100 |
Title: Trying to launch a search fund to acquire VC backed businesses that couldn't scale. Would love your recommendations and get on a mission to revive a favorite product of this community.
Upvote: | 43 |
Title: Angularis is a game similar to Tetris, but based on triangles instead of squares. Which is why it also has diagonal movements. I had this idea about a month ago and built the game in my spare time.<p>I think it is a bit more difficult compared to Tetris. You kind of have to get used to "think diagonally".<p>Maybe it can be a nice little challenge for you.<p>I'd be happy to receive some feedback. Thanks!
Upvote: | 106 |
Title: Hi HN, hope this topic is ok. I'm looking for commentary or advice from readers familiar with ad systems.<p>A few years ago I got involved with the wrong wealthy, connected crowd and many weird/violent things happened. The story is strange, so people assume mental illness. I'm seeing a counselor, taking pills that don't seem to help except make me fat and sleepy, and doing my best to get back to dev work before my funds run out.<p>I wanted to talk about my internet experience, though. I used to get ads for food, clothes, consumer tech. Now I get strange ads which are really not helping my situation.<p>On Twitter, ad with only a few views about "losing a game, checkmate the cost is your soul".<p>On IG, which I use to look at cat pictures and my friends, I get ads for Freemasonic end-of-life care, occult ritual materials, bizarre poetry sometimes containing my name/usernames, artwork with the tagline "Maybe you aren't paranoid and people are following you ;)", going blind, car accidents, ALS, cancer, organ failure. Or, my personal favorite when I've managed to distract myself from my troubles for a few hours, paraphrased "DID SOMETHING EXTREMELY BAD HAPPEN TO YOU AND YOU CAN'T STOP THINKING ABOUT IT?". I usually see that one multiple times a day.<p>I've shown these ads to other people; I don't have any history of seeing physical things others don't. I try to scroll past them fast but usually still see what they say. I usually don't take screenshots because I don't want the pause to register as engagement.<p>I get that most people would just ignore this stuff. I would have in the past. I don't know how to explain the change in perspective after you've been in life-threatening situations, had your windows smashed, or had weird totems left in your yard, etc etc. It's not a stretch to think "maybe this IS relevant to me, or a message warning me: bad thing going to happen!". Regardless, I want to avoid interacting with content like this.<p>I have long been opted out of search history or ad personalization on G/FB/AMZN/Twitter/Instagram/Verizon, and have repeatedly clicked "hide ad - irrelevant or not interested". "Why am I seeing this ad?" says "(wide age group) in your area", yet I've asked and my peers don't get ads like this.<p>I think I'm privacy savvy somewhat. Logged out, incognito/Ublock/Ghostery. Few apps, all permissions denied. DDG. Unique usernames, lurking or throwaways. No prescription rewards. I only visit a few websites. I don't share my computer. No other devices listening in the house.<p>The only information leaks I can think of are:
* credit card billed for telehealth
* short text journal on dropbox
* friends may have discussed me/topic in their chats
* a friend asked on Messenger why I disappeared, I said something like "I might have schizophrenia. Some violent situations happened and I'm struggling now."<p>I know, Messenger wasn't E2E, but I didn't realize it might flag me so easily. I haven't done anything else to indicate my interest in this topic; it's not like I'm posting in "targeted person" forums, buying anything other than groceries, or watching horror movies.<p>Even if the explanation is just "machine learning black box parses chat, determines unlabeled cluster demonstrates increased engagement with thrilling, morbid, suggestive, edgy content", well, I explicitly rejected opting-in to that. The supposed "opt-outs" have little effect, at best hiding one specific ad but not actually updating to the point of "I don't want to see ads about PTSD, dismemberment, horror, paranoia, accidents, tragedy, eschatology, or the occult, please start showing me only normie ads again".<p>I'm not sure what to think at this point, short of going offline or quitting social media. I did that in the past but I am trying to keep my weak network alive. Anyway, I'm curious to hear if anyone has feedback or advice on this situation. Am I missing something, mistaken, doing something wrong? Thanks!
Upvote: | 63 |
Title: I've been playing Wordle and remembered this puzzle game I used to play with my grandfather. It's inspired by the block puzzles in many newspapers but made to be shorter: just guess the nine letter word.<p>So I made a quick thing to play with my family like we used to. I thought you guys might enjoy it.
Upvote: | 62 |
Title: One can create almost anything using computer programming. This is not true with any other artistic tool.
Upvote: | 52 |
Title: duralava is a neural network which can simulate a lava lamp in an infinite loop.<p>It uses a recurrent GAN that learns the physical behavior of the lava lamp.<p>A noteworthy aspect is that can generate an arbitrarily long video of a (virtual) lava lamp, without diverging even after thousands of frames.
Upvote: | 88 |
Title: I had a google adsense account that was producing a nice amount of income for years. I logged in to another google account that didn't have an adsense account and suddenly I got an email that my adsense account was flagged as a duplicate and I was banned. I tried their "appeal" but of course some robot made a decision to keep the ban. Looking for some help -- any help at all, to try and get my adsense account back. My email address is in my profile. I'm hoping some benevolent googler can help out.
Upvote: | 155 |
Title: Which software do you use frequently and are unable to replace (either at home or your company) despite thoroughly disliking it?<p>What makes it so bad? Are there alternatives? Why can't you replace it?
Upvote: | 92 |
Title: So with Google starting to charge previously-free users, I've decided that I'd rather give my money to someone else. I'd like a provider who is likely to be around in a decade or two. Tips on moving many years of Google email to a new provider are appreciated as well!
Upvote: | 270 |
Title: Wanted to hear about experiences from employees who have RSUs/options in a private company and whether they were able to sell their shares on the secondary market?<p>Were you able to sell?
What platform did you use?
Were you able to sell w/o board approval? If so, were you able to use private forward contracts to complete a deal?<p>Anything you can tell me about the experience would be much appreciated!
Upvote: | 277 |
Title: Are there any all-in-one software available for organising
- notes which include searchable screenshots and hand drawings
- mind-maps
- browser tabs?<p>I work on multiple cases at the same time and I easily get lost.
Upvote: | 59 |
Title: What are the best books you've read on how to manage software complexity, both from an architectural as well as organizational perspective?
Upvote: | 253 |
Title: I'm too lazy to run ad blockers. So I see plenty of advertising on the internet. Here's the thing: all the ads seem to be for things that I already bought. After I placed an order with Select Blinds, I started getting relentless Select Blinds ads on YouTube. After I made some charitable donations to Mercy Ships and Heifer International, their ads started following me around everywhere. My wife recently got on a new immunosuppressant medication, and now I see ads for that all the time. Great job targeting! But I already spent the money? So what is the point of all this?
Upvote: | 99 |
Title: I am turning 35 years soon and I feel like I haven't achieved much, both personally and professionally. I have held jobs in small and big companies for mostly for 1-2 years each, traveled and lived in different countries, had 2 failed startups, and have about $500k in savings. I am single and haven't had a serious relationship for many years now.<p>As time went on, I started feeling less excited about everything, personal or work related. I used to be excited about new technologies, but not these days. I feel like I've seen most things before, and it's all just different iterations of the same. I increasingly wish I could go back to my 20s. Now I feel too old to go to festivals, bars and clubs and make new friends that way.<p>This has been a recent change for me. When I was ~30 I still considered myself young and able to do anything I could do when I was in my 20s. But not anymore now. I feel like my time for everything is running out. Have you been through a similar thing? How did you deal with it?
Upvote: | 1094 |
Title: I'm looking for things that help more than expected or in ways you wouldn't expect. It could be a second monitor, a really good mouse or even a microplane.
Upvote: | 171 |
Title: Is there a task or activity that regularly causes you grief during your day-to-day (no matter how big or small)?<p>Post it here to potentially motivate someone to work on a solution!<p>Last thread: https://news.ycombinator.com/item?id=29796099
Upvote: | 59 |
Title: When I was a kid, we use to look forward to the Olympics. It was a big deal. The whole family would gather around the TV to watch the events live regardless of timezone. We use to follow the stories of the atheletes and it was constantly the talk of the town.<p>Nowadays, it kind of feels like Olympics are just annoying. Propaganda fest for authoritarian regimes. No one cares. Heck, some people don’t even know that the Olympics are even happening.<p>How did it go so wrong?
Upvote: | 102 |
Title: I always prioritized having broad skillset rather than focusing on a single thing, but i'm now having doubts about it.<p>I'd like to discover if my skills are useful by applying them to solve someone's challenges. If talking to me might help you - please drop me an email or schedule a call (the address is in the profile). Free & no strings attached.<p>About me:<p>- co-founder/ex-CTO/ex-CPO of a russian company with $15M arr<p>- people usually describe me as a "smart guy"<p>- had to solve a problem that required using nlp, so i organized data labelling team, finetuned BERT, and integrated it into a larger system<p>- know some finance. unit economy, operating costs, that sort of thing<p>- did a lot of a/b tests and conversion experiments<p>- bitmap indexes, fractal trees, k-d trees - i like indexes and trees<p>- developed software using python, golang, php, c++<p>- clickhouse user for 3 or 4 years. also, mongodb, vertica, presto<p>- did some custdev and qualitative interviews<p>- have some experience managing outbound sales reps; but still, i'm a builder/hacker, not a hustler<p>(I realize this post looks a bit like a sneaky "hire me" post - but i assure you, that is not my intention)
Upvote: | 68 |
Title: Inspired by the post about being 35, confused in life and without a purpose a lot of folks talked about how they find joy in life through their hobbies. I would like to know what are your hobbies! I'm currently selling a lot of equipment I used for music production because I find it hard to sit in front of a DAW and produce after a 8 hr workday in front of a computer.
Upvote: | 46 |
Title: Hello HN,<p>I do plan onto pursue independent contracting in feature. I would love to hear the thoughts of the community on how to pursue independent consulting. For instance, how do you find clients, how do you pursue a niche and keep yourself updated as a contractor
Upvote: | 109 |
Title: My SO uses iPhone and I use Android, I think we'll both soon go mad with all the pictures of the documents sent to post that we have to take a digital action for.<p>Contracts, Appliance Invoices, insurance, Kids' documents, Receipts, Fines, government documents, bills, tickets, passes etc. Are basically taking ages to find, even if we were wise to take a picture would take ages to refind.<p>I have both OneDrive and Dropbox, the UX is horrible for these simple searches. I know that Shoebox exists, but paying at least 18$ a month for wanting to store my documents on my phone in a neat way looks to much of a demand for me. (and that has a limitation). I'm not even asking for a fancy OCR.<p>Is there an app out there for this? What do you use?
Upvote: | 50 |
Title: (throw away account since I will be sharing a lot of personal stuff)<p>I have been working at big and respected tech companies for years, and lately I decided that I wanted to do something different and join a startup.<p>At first I was very happy to find that many companies were interested in me, and several of them sound promising companies, but when the compensation conversations start, I can't help to feel like I'm getting the short end of the stick.<p>I have no expectations that any startup would match my current comp, but after crunching the numbers of expected equity and using VERY optimistic scenarios, the opportunity cost is too big to ignore. For reference:<p>- I make around $0.9M-$1.2M per year today. Is a public company, so everything is liquid.<p>- If I accept a position with 1% equity, the company exit would need to be at least $500M just to match my previous comp.<p>- Investors are getting a much better deal than I am, their money can buy more equity that I would be able to buy with my work.<p>So far I considered the following options:<p>- Accept my golden handcuffs, and stay where I am.<p>- Accept that this is the price for the privilege of working at a startup.<p>- Become a founder myself, so the exit value doesn't need to be so insanely high.<p>- Become an angel investor, since they are getting a much better deal, I might as well join them.<p>I'm curious with other people think about this situation, while I think I'm in an uncommon (but very fortunate) situation, is hard to believe I'm the first one. I'm interesting to hear if I'm actually missing something and is not as bad as it sounds, or if there is other options which I did not consider.
Upvote: | 43 |
Title: I thought it was the best for a while. But long hours in my house alone is killing me.
Upvote: | 75 |
Title: HN produces better book recommendations than any other place I know of. People at HN have recommended such books like Chimpanzee Politics, which are so basic yet eye-opening that everyone would benefit from reading them.<p>If you would get to recommend a single book for everyone to read, what would it be?
Upvote: | 166 |
Title: Having a citizenship with low status is a significant loss of opportunity in life for the affected individuals. Since Hacker News is a relatively international crowd, I'm sure that many of you can relate to this in one way or another.<p>Should the UN try to create a political taboo (and in the long term, a ban) against sanctions towards general population when countries clash in diplomatic issues?
Upvote: | 46 |
Title: Hi HN,<p>I'm looking for advice on calculating my market value.<p>I live in central Europe and work as a Cloud Architect, that also does DevOps and pretty much everything required project-wise.<p>I make 32k per year and it seems hard getting an average market pay. I have no university degree, but 6 years experience in IT, 3 years experience in CI/CD and 2 years experience with AWS and IaC.<p>How can I figure out my market worth?<p>Edit: I have little experience with negotiations and the job market, that's why I ask.
Upvote: | 44 |
Title: I'm redoing my RSS feed subscriptions from scratch. I'd appreciate suggestions for great personal blogs by programmers.
Upvote: | 322 |
Title: Hi HN—we're Kelly and Steve, co-founders of OneChronos (<a href="https://www.onechronos.com" rel="nofollow">https://www.onechronos.com</a>). OneChronos is a "Smart Market" for US equities—meaning we match counterparties using mathematical optimization instead of classical human auctioneer mechanics [1]. Our flavor of Smart Market—combinatorial auctions—lets users enter orders spanning multiple securities and specify matching preferences way beyond just price and quantity.<p>We didn't invent Smart Markets or combinatorial auctions. Roughly $1T/year flows through them in industries ranging from display advertising to telecommunications. The underlying theory was the subject of the 2020 Nobel Prize in Economic Sciences [2]. We're bringing them to capital markets, and we have both the customers and the regulatory clearance to do so. Our initial user base contains the household names cumulatively responsible for ≈70% of US equities trading volume.<p>Today's market structure costs institutional investors at least a trillion dollars annually. We'll go into the details below, but the big thing to understand is that mutual/pension/sovereign funds, 401K plans, and ETF managers pay the price, and ultimately it gets passed on to households. Given diverse investment time horizons and risk preferences, capital markets are not a zero-sum game, but the existing market structure makes it one. Any form of market friction that prevents mutually beneficial trades from happening is an economic loss. Our goal is to make a lot more mutually beneficial trades happen.<p>We started working on OneChronos as experienced traders and auction theorists. Even so, getting here has taken five years of iterating with customers, tackling two deep tech problems, and working through an involved regulatory process. We'll describe what's causing existing market friction, the solution, and why that solution is a significant technical lift.<p>When people hear about market friction and hidden costs, they usually think about low latency technology, market data, exchange fees, and predatory HFT practices. Those are significant, and yet they are rounding errors compared to others. The principal sources of market friction that we're attacking are bidders' inability to express economic complements (things that are worth more together than separately), substitutes (things with diminishing marginal utility that are replacements for each other) and non-price factors, and game-theoretic incentives against bidding "truthfully"—that is, against specifying how many units of a good you have and the highest price at which you'd buy or the lowest at which you'd sell them (your supply and demand curve). The most commonly proposed market structure "fixes," like single good periodic batch auctions and the IEX speed bump, don't address any of these.<p>Imagine that a buyer values two goods A and B at $10 for the package, but only $4 for each individually since they're complements. Similarly, a seller might unload the package for $8 while demanding $5 for each good individually. Both agents have "exposure risk" if A and B are bought and sold separately—they might get stuck with an incomplete package. No trade happens if the risk is high enough (buy at $4, sell at $5, no cross). But if they can trade the package atomically, there's a mutual win of $2 in gains from trade. Similar missed opportunities happen if agents only want A XOR B or have different prices for different counterparties (price discrimination). This game of imperfect information and missed opportunities plays out every day in capital markets globally.<p>The straightforward solution to these problems is called "Expressive Bidding"—the ability to communicate parametric bids to the auctioneer, e.g., buy at most one of {$10 for A and B, $4 for A, $4 for B} or sell at most two units of A, pricing it at $10 for counterparty C_1, $9 for C_2, or $8 for C_3. Given everyone's Expressive Bid and a well-chosen objective function, the auctioneer uses constrained optimization to clear the market and unlock efficiencies. Awesome. So why didn't this happen when markets first started going electronic?<p>General combinatorial auctions are isomorphic to weighted set packing. Clearing them is an NP-complete optimization problem. Finding feasible and near-optimal solutions at the speed and scale of capital markets is deep tech problem #1. Furthermore, bidding in combinatorial auctions can be challenging in both a computational and UX sense. Making it easy is deep tech problem #2.<p>We tackle problem #1 similarly to how game AI like AlphaZero and optimizers like AlphaFold work. The combination of deep learning, heuristics, and classical AI search techniques is powerful, and applying them to combinatorial auctions in novel ways is a core part of our IP. Problem #2 involves the magic of formal methods. Expressive Bidding users submit snippets of code (a functionally pure subset of OCaml/ReasonML) called a Proxy Bidder. These proxies are essentially functions mapping "proposals" (allocations of goods) to prices, e.g., f({2A, -B}) → -5, meaning that the bidder wants $5 for buying two units of A and selling one unit of B. Using formal methods, we turn Proxy Bidders into Expressive Bids that our optimizers can understand. You can see what that looks like here [3]. This approach is dead simple for end users, but it took years of collaborative R&D with our friends and formal methods legends at Imandra [4] to enable.<p>Not everyone needs to write or use Expressive Bids. For common use cases, we're offering pre-canned/forkable Expressive Bids for things like pairs trades and factor neutral portfolios. That aside, users who don't use Expressive Bidding still benefit from those who use it and create unique liquidity that doesn't exist on other trading venues. Our economic mechanism prevents "dark forest" scenarios in which Expressive Bidding has adversarial uses that detract from overall match quality. "Power users" can only benefit those who treat us like a vanilla trading venue—and each other.<p>We make money by charging a small commission in line with other venues ($0.0009) on each share traded. Longer-term, we're excited about a pricing model that balances computational resources used against liquidity contributed and compensates OneChronos based on how much value we add. Specifically, we'll measure how much notional dollar price improvement we generate for the market beyond what's generated by a "vanilla" double auction that we run in parallel (a neat trick enabled by Expressive Bidding–we can run an arbitrary number of auctions with different rulesets in parallel to measure relative performance). This approach aligns our incentives with our customers and eliminates fixed costs (which cause market friction) from trading.<p>Only FINRA registered broker-dealers connect to OneChronos directly. If you work at one, and you're not yet a subscriber, please get in touch. We love talking to both subscribers and their customers, and we'd love to hear from institutional investors looking to leverage OneChronos through their existing broker algo and DMA workflows. Retail customers will eventually access us through brokers that choose to allow it (PFOF is its own thing). In the meantime, stay tuned for other more decentralized asset classes :) You can reach us at info (at) onechronos.com.<p>And we're hiring! If you're passionate about deeply technical problems ranging from mechanism design to applying ML to combinatorial optimization to writing compilers and engineering sophisticated distributed systems to HFT tolerances, get in touch — careers (at) onechronos.com.<p>Steve and I will be online today and would love to talk about our technical challenges, auctions/mechanism design, market structure, and the future of OneChronos.<p>[1] <a href="https://en.wikipedia.org/wiki/Smart_market" rel="nofollow">https://en.wikipedia.org/wiki/Smart_market</a><p>[2] <a href="https://news.stanford.edu/2020/11/19/bid-picture-nobel-prize-winners-explain-auction-theory-collaboration/" rel="nofollow">https://news.stanford.edu/2020/11/19/bid-picture-nobel-prize...</a> - Paul Milgrom, one of the laureates, is the Chair of OneChronos Labs, our research arm.<p>[3] <a href="https://www.onechronos.com/docs/expressive/bidding-guide/#intro-to-bidder-logic" rel="nofollow">https://www.onechronos.com/docs/expressive/bidding-guide/#in...</a><p>[4] <a href="https://www.imandra.ai/" rel="nofollow">https://www.imandra.ai/</a>
Upvote: | 231 |
Title: Given the recent changes to workspace, it seems inevitable that someone at Google start to think this might be a huge revenue generator
Upvote: | 176 |
Title: I frequently think about doing writing an app or web service, but then talk myself out of it by thinking that the effort is much greater than it sounds and those efforts would be better off trying to progress my career. Is anyone here actually enjoying a few hundred dollars a month from an app or web-service that was worth it after your initial effort and ongoing maintenance?
Upvote: | 50 |
Title: If that’s okay I would like to ask the HN community for their advice on a personal matter.<p>My beautiful daughter Nil (3yo), has a rare genetic disorder called Kleefstra Syndrome (KS). She cannot walk or talk at this point. Doctors believe she will walk eventually, but speech they are not so sure about. KS involves partial chromosome deletion (or sometimes mutation) of a particular gene, EHMT1, which in turn causes a protein called GLP not to be produced. Moderate to severe Intellectual disability, limited/absent speech are some of the symptoms.<p>KS was first “discovered” in 2010. Thanks to “whole genome sequencing”, it is now possible to diagnose KS with a single draw of blood. Maybe that’s why we are hearing about KS kids more often in our community.<p>We have a non-profit foundation based in the US ( <a href="https://www.idefine.org" rel="nofollow">https://www.idefine.org</a> ) to improve awareness and lead/fund potential research for KS. Also, there are already two active pieces of research that provide potential improvement for these kids. One explores drug repurposing ( <a href="https://www.nature.com/articles/s41467-019-12947-3" rel="nofollow">https://www.nature.com/articles/s41467-019-12947-3</a> ), the other is about supplementing the missing proteins ( <a href="https://www.sciencedaily.com/releases/2021/09/210921100245.htm" rel="nofollow">https://www.sciencedaily.com/releases/2021/09/210921100245.h...</a> ). Both have very promising results but are not close to clinical trials yet.<p>Still, several potential treatment modalities need to be explored in depth. Antisense Oligonucleotide Therapy (ASO), gene therapy (CRISPR), drug repurposing are a few modalities to name.<p>Known KS individuals sum up to only a few hundred patients so far. When the patient count is so low, pharmaceutical companies are not interested in pursuing research for that disease, so patient organizations are forced to fund their research themselves. This has been done by several rare disease patient organizations before. Batten Disease (Beyond Batten Disease Foundation funded $35M research), Angelman Syndrome (Fast Foundation funded $26M research), SMA (Cure SMA funded $35M research), all funded successful research and managed to reach clinical trial level.<p>Sorry about the extra-long intro, but I wanted to provide context for this relatively “new” genetic disease which is hardly known. Since HN has members with extensive digital marketing experience, I’m hoping you would share your ideas with us. Long story short, if we can manage to raise several million to kickstart multiple types of research in parallel, then we can offer these kids a chance.<p>My first idea is about co-hosting a series of Instagram live streams with celebrities to ask for donations for research. I’m not sure if this is already a solid fundraising technique? Also, I don’t know the first thing about finding celebrities as well.<p>A second idea is, recording a youtube video and promoting it using google ads grants.<p>At this point, we want to leave no stone unturned about fundraising.<p>So here we are. Any advice would be greatly appreciated.
Upvote: | 260 |
Title: I expected better from Udacity, but apparently it's not enough to click the "cancel" button on your subscription. You have to chat to an agent that has to convince you Comcast style why you shouldn't cancel.<p>Funny enough, they'd put a "cancel" button and then a popup shows up telling you to chat to an agent.<p>Granted chatting with the "agent" took about 5 mins, but it's still kind of a sh!tty pattern.<p>If I can enroll online by clicking through and filling out my info, I should be able to cancel just as easily, not be coerced into chatting with an "agent".
Upvote: | 165 |
Title: It is possible to see items you vouched for or flagged by editing and visiting these links:<p>https://news.ycombinator.com/vouched?id=your_username<p>https://news.ycombinator.com/flagged?id=your_username<p>It might be useful to catch flagging-by-fat-fingers. Also to take a look at how well items you vouch for do afterwards.<p>I figured the vouched link, then dang told me about the flagged one. Couldn't find any references to these on HN or "hidden features" guides, but it's been a while since I last looked.<p>Do you know of any other hidden links like these?
Upvote: | 171 |
Title: I'm ~40yo semi-successful full-stack engineer/hacker who had been recently diagnosed with ADHD (after more than decade of self-seeking journey and introspection). During my diagnosis I learned that ADHD is persistent in 5-7% in general population with some specialist speculating it's more common in IT due to hypnotizing effect of computers. I know I'm not alone with this :)<p>In hindsight ADHD helped me to get into current position. Being constantly bored, high energy, positive-minded solution and tool seeker is often good thing in times of crisis. When things go stale and there are no things to fix but only boring forms remains it's usually mortal battle with burnout, procrastination, self-doubt. One which usually ends with me quitting due to burnout or - rarely - getting kicked off because the next more boring thing took longer than anticipated.<p>Right now I'm on hiatus since couple last couple of weeks, but lack of direction and purpose is awful and with every morning I feel fires of restlessness growing.<p>Today I read recruitment ad about neurodiversity program which - supposedly - caters people with different neurodivergencies. Those were US on-site positions though and I'm in EU.<p>So getting to the point:
Do you know / can recommend companies with neurodiversity programs?<p>For myself obviously I'm looking for remote or EU companies (with relocation) but even if you know something that's not in the region please feel free to contribute - maybe someone else looking will make use of it.<p><i>Obvious throwaway. Some half-truths embedded.</i>
Upvote: | 181 |
Title: I tried visiting Stack Exchange today using Tor Browser, and apparently my IP is blocked. I tried with several different circuits, and they're all blocked. Several people on IRC confirmed this as well.<p>I tried to contact them by e-mail and they didn't bother to respond, as is par for the course these days.<p>The full error message:<p>---<p><pre><code> Access Denied
This IP address (185.220.101.37) has been blocked from access to our services. If you believe this to be in error, please contact us at [email protected].
When contacting us, please include the following information in the email:
Method: block
XID: 820408900-HHN
IP: 185.220.101.37
X-Forwarded-For: 185.220.101.37
User-Agent: Mozilla/5.0 _Windows NT 10.0; rv:91.0_ Gecko/20100101 Firefox/91.0
Reason: Blocked.
Time: Tue, 08 Feb 2022 08:11:50 GMT
URL: tor.stackexchange.com/
Browser Location: https://tor.stackexchange.com/</code></pre>
Upvote: | 429 |
Title: Here’s a free, fun, novel five-letter word game for the web! It’s a game I originally wrote for the iPhone in 2010, but wasn’t able to finish before my first child was born. When I left my senior web developer job in September 2021 I figured I would postpone looking for work and finish the game before another 11 years passed, and expose myself to new skills doing it (in this case, Swift). I released it on the App Store in December, then turned my attention to doing a web version — when suddenly Wordle was in The NY Times, and then everywhere.<p>Perhaps foolishly, I plowed ahead and here we are. Like Wordle and some other NY Times word games, there is a single daily puzzle, but like traditional crossword puzzles, it gets harder throughout the week.
Upvote: | 204 |
Title: After almost 20 years working in the public sector, I've come to the realization that my passion for public service no longer outweighs my many day-to-day frustrations. A sense of purpose is what kept me in government for so long, but the bureaucracy, the aversion to change, and the outdated technology have made loving my work more and more difficult. I've been contemplating moving into the private sector for a long time now--I'm just worried that I'll end up feeling lost in a world that is driven by profit. I recognize however that my view is that of an outsider. I've never worked in business, and in truth, I don't really know what drives people. I'm hoping the good folks of HN can provide some insight. Where do you find your sense of purpose working in the private sector?
Upvote: | 82 |
Title: Hello, guys.<p>I hear a-lot of negative sentiment regarding an incoming recession. I hope it doesn't happen, but I don't want to be a sitting duck.<p>Just want to know how fellow hackers are consuming this news.<p>- What do you anticipate?<p>- Do you have plans incase you get laid off?<p>- Savings? If so for how long?<p>- Are you sitting on an inflation hedge?<p>- What business plans may thrive in a recession?
Upvote: | 64 |
Title: Short of it: I’m not talking about the software I would write or produce, I’m talking about communication software.<p>I recently did some phone screens with another company in my industry, my industry is dominated by Microsoft products (mostly windows based software) but I have always had a seriously hard time digesting Teams.<p>It makes me bitterly angry when I work with it, the way pop ups work, the way things are (dis)organised, even the way copy/paste doesn’t seem to work the majority of the time.<p>I said on hacker news recently that I don’t think I can work with that software again, but a potential job offer that appears otherwise interesting had an interview conducted by teams.<p>Is it ok to send feedback that I don’t really want to work with that software? Is that extremely petty and spoiled?
Upvote: | 116 |
Title: I'm working in a Cryptocurrency startup, and <i>all</i> my colleagues are investing heavily into the domain, both mentally and monetarily. I cannot shake off the feeling that this is <i>all</i> a scam. It's so shady, from the way there are new coins and tokens every week, and how investors are throwing money into this program. I don't think my company's product deserves the sort of money it's been getting, and it feels like a bubble that will burst, sooner if not later. Some part of the tech is interesting, the essence of the blockchain, for example, but the main application seems to be just suspicious. What do others in the domain think? I'm not leaving yet because I'm not in a place to change jobs yet again, but I will, eventually, but I feel like this domain is very fishy.
Upvote: | 254 |
Title: In the last few months Twitter has went from letting you browse the site without signing in, to now prompting you to sign in to do pretty much anything. Even something as simple as scrolling down with my mousewheel in Twitter prompts me to sign in. This also happens with official government communication pages. I thought courts already decided in the US that the public has a right to access official government communications on social media. When requiring users to sign in and agree to the companies terms, wouldn't this be considered a form of preventing access to those communications?
Upvote: | 193 |
Title: As an embedded developer, I am always happy to see threads about embedded hardware and software, new SoC / MCU releases etc, but these are rare here.<p>I was wondering if there is something similar. I know about the subreddits, but they tend to be a bit chaotic and not entirely what I am looking for.
Upvote: | 53 |
Title: Lets encrypt has made SSL/TLS a no-brainer for websites on the public internet. Behind home routers, it's still a tedious topic. What's your (non-enterprise) solution?
Upvote: | 65 |
Title: Hey, Hacker News! Today I'm proud to release jless, a command-line JSON viewer.<p>jless provides a JSON viewing experience similar to what you see in a browser's network tab in the developer console, but from the comfort of your terminal, with a whole suite of vim-inspired key bindings to easily manipulate your view of the data and full-text regex search. I'm sure many of you have some piped together some combination of cat, jq and less before; hopefully jless can replace that usage (hence the name). It supports newline delimited JSON too, so it can handle any output from jq.<p>I built jless to solve a problem I kept facing while building plaintextsports.com [1][2]. For the live data I use a lot of public, but undocumented APIs, and I was constantly digging through giant JSON files to understand how the data was structured. I tried installing multiple Chrome extensions, but was dissatisfied with all of them. I piped files through jq into less a lot, and that was ok, but not great. The Preview pane in the Network tab of Chrome's dev tools was pretty useful, and I modeled a lot of jless's behavior and appearance off of that, but it didn't fit well into my tmux + vim dev environment, and I couldn't easily use it to inspect files on disk. I wanted that experience, but in my terminal (and with search support).<p>Once I had built a rudimentary version of jless a few months ago, I immediately started using it whenever I was debugging something, and my usage has only grown as I've added more basic functionality. I've finally added all the features I feel like it needs to be functional, useful, and reliable.<p>There's definitely more features I want to add: Windows support, some way to filter data with jq filters (a la fx [3]), yanking objects to the clipboard, being able to hide keys entirely, streaming data in, so you can peek at the start of gigantic file, maybe a way to extract a schema from a file (like [4]), plenty of low-hanging fruit for performance. Support for different hierarchical data formats (YAML, TOML, XML) could be cool someday. I'm sure many people will ask for editing support, but sadly that is not something I plan on adding anytime soon.<p>I also used this project as a chance to learn Rust (code style and design comments appreciated!), which I had only dabbled with before. For a command-line utility, this felt like an obvious choice: small binaries (~3mb), instant startup, and great performance without any effort (try searching for comma in a big file!).<p>I hope you find it useful!<p>[1]: <a href="https://plaintextsports.com" rel="nofollow">https://plaintextsports.com</a>, live sports scores in plain text, no ads, no tracking, no loading<p>[2]: <a href="https://news.ycombinator.com/item?id=26310314" rel="nofollow">https://news.ycombinator.com/item?id=26310314</a><p>[3]: <a href="https://news.ycombinator.com/item?id=29861043" rel="nofollow">https://news.ycombinator.com/item?id=29861043</a><p>[4]: <a href="https://quicktype.io/typescript" rel="nofollow">https://quicktype.io/typescript</a>
Upvote: | 344 |
Title: Hi HN, Drew and Edmund from Pelm here (<a href="https://www.pelm.com" rel="nofollow">https://www.pelm.com</a>). We are building an API that allows developers to access energy data, such as electricity usage or billing data, from utilities.<p>Currently, if you want to build an application on top of energy data, you have to build integrations with utilities across the country. Not only is this time-consuming, it's super frustrating given the lack of data standardization and the clunky, high-friction integration processes that energy companies use. With Pelm, you only have to integrate with one service to access utility data, and you get to use a seamless, well-documented API built by other developers.<p>We are software engineers (from Asana and Affirm) who are enthusiastic about sustainability and the creation of a more modern energy grid. We talked with lots of developers who were frustrated from trying to work with energy data and saw an opportunity to meet their needs while supporting the push for a more efficient energy grid.<p>Most companies trying to tackle this problem are energy companies, not technology companies. The products they build don't keep the user in mind and only focus on meeting bare functional requirements. Pelm, by contrast, is by-developers-for-developers. Our focus is ease of use. Our API is simple to get up and running (under ten minutes) and provides clear documentation and instructions.<p>It works like this: you register for our service and embed Connect (our front-end plugin) into your application. The end user uses Connect to authorize access to their data from their particular utility. We scrape electricity usage and billing data from their utility account and store it in a standardized format in a database. Your application can then query electricity interval data and billing data for the end user through our REST API. We also recently built out functionality to pay utility bills through our API.<p>Our API is designed for apps that do things like help consumers reduce electricity usage, charge EVs at optimal times, optimize HVAC installs, or educate on climate-friendly practices.<p>One example of how Pelm can currently be used is in demand response programs—that’s when utilities pay companies to get large amounts of people to reduce their electricity consumption during peak hours. Our API can help measure the reduction, which determines how much the company gets paid. Another example: solar panel installers can use us to show potential clients how much they could save on their electricity bill by installing solar. Another is community solar programs that allow people to buy into remote solar farms and get credit for the generated energy from utilities. Pelm can be used by community solar providers to calculate and bundle bills.<p>(By the way, an interesting little-known fact: this space is possible because of a 2012 initiative by Obama that required utilities to allow consumers more visibility into their energy consumption habits.)<p>Pelm is free up to 100 API calls and 10 active end users per month. After that we charge on a usage based plan: $0.10/call and $0.50/active end user up to 10,000 API calls and 1,000 active users. Past that limit, you'll move onto an enterprise plan with a flat monthly rate based on your service level and an adjusted rate for calls and active end users (we’re still figuring out the exact parameters).<p>We’d love to hear any of your ideas or experiences within this space! We’re always looking for creative approaches to the problem and ways we can better the developer experience we’re building. If you get a chance to test out the API, please share your feedback on how we could improve it. Thanks so much!
Upvote: | 101 |
Title: Something weird is happening with Quickbooks.<p>I am resident in Ghana but having a New York registered LLC through which I provide software engineering consulting services to US clients. Since I opened a new account with Quickbooks Oline to receive payments for the LLC, they have asked for all kinds of verification, which I have provided.<p>It's been weeks now since a client paid a substantial invoice, and Quickbooks are still holding it up without depositing it. Worse, they have disabled all my intuit accounts (and yet continue to charge me for it). Even my free Mint account no longer works.<p>I have had numerous calls and chats with them to explain what I do and how I intend to use their services, all to no avail. After wasting a lot of time to contact a rep today, I was informed I need to provide a utility bill for my business address. Since I'm not in the US, I'm using a registered agent, whose address I cannot provide a utility bill for.<p>So at this point, I'm asking my client to request a refund from them. I will also be contacting Paypal and my bank to file a dispute for the subscription fees I have paid them, since they are unable to provide the service I have paid for.<p>Think twice before using Quickbooks.
Upvote: | 40 |
Title: Hello, I am not a competitive guy. Neither am I curious enough to dive deep into intricate details. I am jack of all trades but master of none. All I is know enough subject matters to make things work. Is there something fundamental that I am missing?<p>I enjoy life in the most boring way. Just doing enough to pass a day. I strive for being good, but my good is just average. Is it necessary to be competitive to have a successful career in tech?<p>How far can a boring person with diversified interest go?<p>If one doesn't aim for excellence, is it a bad thing?<p>I am really early in my career and sometimes I get cold feet when I see how incredible other people are.<p>What does it take to uplift myself and my own levels?<p>I have come to realize that just to make a small dent (as in new contribution beyond being a boring copy-cat), I would require tremendous amount of years of consistent effort.<p>Thank you for suggestions!
Upvote: | 69 |
Title: Hi HN! Excited to show off the project we've been working on for the last couple months. We started with an idea for a crazy twist on prediction markets: You come up with a question for traders to predict, and then decide the outcome yourself.<p>For example, you could create a market on “Will my date with [X] go well?” Anyone can bet on it, and the bets create a forecast on the chance your date goes well. After the date is over, you get to judge the result and reward the traders who picked the correct side.<p>There are so many ways for this mechanism to go wrong: the creator of the market can be dishonest in deciding the outcome, or you may just disagree with their resolution, with no recourse. Nevertheless, we pitched user-created prediction markets in a grant proposal to the blog Astral Codex Ten, and somehow we won!<p>Since then, it’s been an exciting two months of us hacking away to realize this idea, and now we’re happy to announce the official launch of Manifold Markets! We’ve gotten so much support from early users who are just as passionate about prediction markets as we are.<p>You might ask: Is there a reason to create a prediction market, and not a Twitter poll? Are outcomes really that different from a simple person-by-person vote?<p>We believe so. The magic driving prediction markets is accountability. When wagering a scarce currency, those proven right live on to make future bets, whereas those with less-savvy bets have their influence diminished. Prediction markets succeed because they reward accuracy, and that makes all the difference!<p>Our goal is to make prediction markets an order of magnitude easier for you to create and share. It should be as frictionless as a Twitter poll. As part of that philosophy, we’re launching with a play money currency, which we believe is just as fun and predictive.<p>We’ve already built up a passionate community of predictors and market creators, including writers like Richard Hanania and James Medlock, who have predicted everything from CDC recommendations to newsletter subscriptions to fatal shark attacks.<p>There’s so much unexplored space to ask questions and get valuable forecasts. For example, with conditional markets, you can create several related markets that help you make a choice based on which has the highest likelihood of success!<p>Let us know if you have any thoughts or suggestions; otherwise, looking forward to what markets you create!
Upvote: | 84 |
Title: Sweden has, as of today, retracted all Covid-19 restriction as is basically we're "back to normal". Within 12 hours several companies went out and said we are all going back to the office. Some companies (like mine) said mandatory one day per week in the office, others said "fun's over, back in the office 100%".<p>What's your situation?
Upvote: | 40 |
Title: What’s the ultimate technology stack that top-tier hackers use for staying undetectable (chatting, online browsing, OS, etc.)?
Upvote: | 60 |
Title: Last February there was, in my opinion, a really uplifting thread with the same title¹. I'd like to see all the cool new things going on, and I'll steal the intro text from as89 to explain:<p><i>One where you don't care if it makes money or gets a lot of attention, but you are working on it regardless. I don't think I mean private hobbies, exactly, but projects that could or will be shared with others - you just don't care about the outcome.</i><p>¹ <a href="https://news.ycombinator.com/item?id=25992782" rel="nofollow">https://news.ycombinator.com/item?id=25992782</a>
Upvote: | 573 |
Title: What if Dependabot and Ansible had a child?
Well for me that could be Updatecli.<p>Updatecli is a project that I started to help maintain the infrastructure of the Jenkins project. I needed something flexible enough to update YAML with whatever information needed. Because let’s say it, everybody loves YAML. YAML is everywhere.<p>Run it from everywhere…<p>Updatecli is a command-line tool written in Golang and available for Windows, Linux, MacOSx, amd64, arm64, thank you Goreleaser
All of that to say that it runs from wherever CI or laptop we need.<p>As of today, Updatecli opened over 3000 Pull requests on Github, and it evolved to update automatically Dockerfile, Markdown, Helm Chart, and of course a lot of YAML for tools like Puppet, Kubernetes, or Jenkins.<p>How does it work?<p>Updatecli loads pipeline configurations from YAML(s) or Golang templates then enforce the state defined by the pipeline configuration.
A pipeline run as followed:<p>1. Clone in a temporary location any git repositories used by the pipeline.<p>2. Fetch information for every *source* defined, and then inject them as entry parameters into condition(s) and target(s).<p>3. Test that all *conditions* defined succeed otherwise abort the pipeline.<p>4. Enforce the state for every *target* defined. A state means different things depending on the resource type, more on this later.<p>5. Commit and open pull requests when needed.<p>6. Apply next pipeline<p>A Updatecli pipeline relies on resources aka “extension” aka “plugins” to adapt pipeline behavior. By combining them, we can easily automate scenarios for release workflow, GitOps, dependency management, documentation update, etc.<p>A simple scenario could be:
* Retrieve the latest Golang version
* Test that a docker image with the latest Golang version exist on Dockerhub
* If it exists, then bump the version in a YAML file and open a pull request on GitHub with the change<p>As of today, there are 9 extensions for "sources", 8 for "conditions", 6 for "targets", 2 for git repositories, and 1 for pull requests.<p>A very simple pipeline is available on
-> <a href="https://www.updatecli.io/docs/prologue/quick-start/" rel="nofollow">https://www.updatecli.io/docs/prologue/quick-start/</a><p>For more complex pipelines, you can look for directories named “updatecli/updatecli.d” at the root of repositories on <a href="https://github.com/updatecli" rel="nofollow">https://github.com/updatecli</a> or the Jenkins infrastructure repository such as
<a href="https://github.com/jenkins-infra/kubernetes-management/tree/main/updatecli" rel="nofollow">https://github.com/jenkins-infra/kubernetes-management/tree/...</a><p>I maintain a documentation website to document the different configuration.
It’s not perfect but it’s available on www.updatecli.io<p>What’s next?<p>Well, it depends on many things. Updatecli is since the beginning, a fun side project, I wanted to practice Golang programming while automating tedious recurring tasks. I built it in a way that I could reuse it across the different projects which I maintain. It’s rather simple to add new resources so I’ll keep adding them based on my needs, I welcome any contributions that would benefit the community.<p>More information on
<a href="https://www.updatecli.io" rel="nofollow">https://www.updatecli.io</a>
<a href="https://github.com/updatecli/updatecli" rel="nofollow">https://github.com/updatecli/updatecli</a>
Upvote: | 60 |
Title: Founder here. Makers.so is a Figma Plugin to build and publish sites without ever leaving Figma. Here’s a demo [0].<p>As a front-end developer I constantly go from Figma to code / site, but it’s tedious… I decided to automate the process with this plugin. It works great for simple projects like:<p>- Landing Pages<p>- Portfolio / Personal sites<p>- Resume sites<p>- Careers / Wiki sites<p>So, not a Webflow / Framer competitor (yet). Webflow and Framer are amazing tools, but if you are in the Figma ecosystem, it's boring to duplicate your work on a different tool. I'm trying to make life easier for Figma users. If this seems interesting, you can install it here [1] and give it a try.<p>—<p>For a bit of context, I'm a solo-founder and I started Makers after sharing my idea on the Figma subreddit about how awesome it would be to have a button in Figma to publish my designs. A good amount of people seemed to agree, and that was enough to start working on it. This is turning out to be a super fun project, and I’ve been working full-time for the last two months.<p>[0] - <a href="https://twitter.com/joaodmj/status/1488216877511884805?s=20" rel="nofollow">https://twitter.com/joaodmj/status/1488216877511884805?s=20</a><p>[1] - <a href="https://www.figma.com/community/plugin/991438050654881175" rel="nofollow">https://www.figma.com/community/plugin/991438050654881175</a>
Upvote: | 180 |
Title: I understand why it exists - text is easier to query than reading a resume, but it's a terrible and outdated design pattern that needs to go. But good news: there are better ways!<p>Some possible solutions and suggestions:<p>-Use a list of checkbox options for candidates to click skills/requirements that you want for the role. If you need SQL, JS, Python, and you believe a CS degree is necessary, then let candidates click which ones they have. No more messing with text! Bonus: You could add some kind of percentage of skills match metric when reviewing applicants (you should still review resumes, however).<p>Bonus #2: You can autofill the job posting with a list of desired skills instead of needing to type them out - just select which ones you need when creating the posting.<p>-You don't need user-entered text fields for keyword matching. Extracting text from PDFs and Word Docs is trivial. If your text extract fails or misses a min word count threshold, just trigger a secondary step for HR to review and manually copy the text and enter it. Point is, stop making users manually enter the text when applying, just pull it out yourself.<p>-If you insist on candidates typing out their resume, stop trying to extract text from resumes to autofill the application form. Personally, I'd prefer to just type it out rather than review it and fix all of the inevitable mistakes (or more likely, clear the fields and just enter it myself).<p>I have considerable experience hiring engineers, and I can tell you concretely that:<p>1. Strong candidates are hard to find.<p>2. A single bad hire can sink a team.<p>3. Technical interviewing is hard and far from solved.<p>Given these three things, why make it harder than it has to be by using a badly designed system when a few changes to the logistical process can fix so much?<p>And if the bosses balk, maybe sell it like this: the existence of your company depends on good hiring, so maybe assign an engineer or two to spend a few months building this out. Not to be all "Dropbox is easy build" - but the basic functionality for something like this is not terribly more complex than a CRUD app with file uploading. I know that's oversimplifying, but I bet you get my point.
Upvote: | 184 |
Title: Hi HN, we're Eric and Dean, creators of SchemafreeSQL. Its roots go back to an on-line Web App Development Environment we developed back in 1999. It was comprised of an IDE, Web Server, Object Store, Virtual File System, Template System, and polyglot (Java, JavaScript, and Python). Of course, we named it “.OS”. Then we ended up dropping it. But that's a story for another time. It was the ease of use of the Object Store from .OS that we really missed, which brings us back to SchemafreeSQL. It provides an enhanced API to your SQL Database which allows it to function as a Schemaless Objectstore. Yes, "Schemaless Objectstore" might be an oxymoron if you consider that objects have strict "schemas". So what are we talking about here?<p>It started with a simple goal. We wanted to store data just as simply as one could throw a JSON document into a doc store, but while maintaining the power of the data's relations and references in an object sense.<p>What we ended up with was a JSON over HTTP API (for ubiquitous access from any language), that maps any JSON structure into an optimized, static set of indexed tables in any SQL database (MySQL being our first port). Using it, we can immediately store any data we want, without having to create tables and indexes and optimize them.<p>Inserting data is as easy as sending a JSON doc to a doc store, but in SFSQL all nested relations inherent within that document are stored as objects and primitives. And, with a little extra JSON syntax we can use references and eliminate duplication of data (e.g. "#ref": "oid-goes-here"), all from within the same source JSON doc. There is also no added speed penalty for referencing an object. In fact, all parent nodes in the JSON source data are stored as objects. So any object can be referenced from anywhere, allowing for complex relations (e.g. any-to-any), enabling rapid prototyping of data structures (no tables to create), and enabling unique on-the-fly relations if need be.<p>Queries are issued using JOIN-free SQL query syntax (e.g. SELECT COUNT(*) WHERE $s:person.address.state='NY') that eliminates the verbosity of the standard SQL JOIN, yet still maintains access to the primitive and aggregate functions of the underlying SQL database (e.g. FORMAT(), COUNT(), etc.) which simply get passed through.<p>What it's not? It's not a database on it's own and it's not a horizontally scalable big data store. Although, since it can extend practically any SQL database, it's ability to scale is in large part tied to the scaling ability of the chosen SQL database that it's extending. It's also not an ORM as there is no strict mapping of objects in code to objects in the datastore. And yes, there were trade offs in it's design. One design choice was that every primitive be indexed, which results in better performance than against a straight SQL table without the proper indexes, though slower than a straight SQL table with a composite index tailored to that query. But, the ability to JOIN to an existing SQL table within a SFSQL query is on the roadmap which will allow you have the best of both worlds (custom tables w/custom indexes referenced from within a SFSQL query). As well, there is a situation one encounters in indexing choices (but that you won't encounter with SFSQL) that we like to call the "Index Permutation Limitation". Simply put, there is a real limit to the number of composite indexes that you can create for any table/collection. This is especially a problem when - for instance - you want to give end users the ability to query across any of the possible attributes across the myriad product types that a big online store may carry. We get into detail on this point within our FAQ.<p>So what it is?
It's an extension to SQL databases that makes storing and querying and modeling and just generally using a datastore... easier. We're hoping it will stir up some interesting use-cases.<p>Thanks in advance for the feedback!
Upvote: | 45 |
Title: Knowing your IDE well can give you superpowers.<p>What are some of the ways you use your IDE that boost your effectiveness as a developer?<p>Do you have any tricks and tips to share?
Upvote: | 51 |
Title: https://www.powerlanguage.co.uk/wordle/<p>Changed font, added hamburger menu, as well as tracking of course.
Upvote: | 160 |
Title: There are many open sourced versions of SaaS products (like gitlab <-> github, plausible <-> google analytics). What is a SaaS solution that you would like to see an open source version for?
Upvote: | 41 |
Title: I have been a software developer in an large organization for more than a decade. I have ADHD and see’s a psychiatrist every 3 weeks. Boss is now demanding access for to all my health records or said he will fire me. He has also locked my Active Directory account (he says temporary) and deactivated my building pass until I sign the document for HR to obtain all my medical records.<p>I have till Monday (less than a week) to sign the document.<p>I am located in Australia.<p>Should I sign the document so my employer has access to all my medical records and all the psychiatrist's notes on me?<p>TL;DR ADHD Software Developer. Employer demands access to all information in my medical records.<p>Letter I am forced to sign to keep my job is below:<p>Link: https://imgur.com/a/Qpvw9M6
Upvote: | 44 |
Title: I've been working on Lurnby for 2 years. It's kind of like a mix of pocket + kindle + anki.<p>It lets you
=> add add epubs, pdfs, and web articles to the app
=> highlight and add comments
=> tag and organize highlights
=> review them with a spaced repetition system<p>Today I made the decision to open source the project. I'm passionate about helping other people learn to learn better and hope that this will allow a lot more innovation in the tool and the space.<p>I'm very new to open source and development in general really, but looking forward to receiving the guidance of the community.
Upvote: | 162 |
Title: Wordle reminded me of Mastermind, a game I played as kid, so just for fun I made a version of the game that plays a lot more like Mastermind. I think this version is way more challenging :)
Upvote: | 40 |
Title: Author here. I really love the programming paradigm behind by Phoenix LiveView applications and wanted to expand the ecosystem to include programmers like myself that love Typescript.<p>In summary, LiveViewJS reuses all the Phoenix client code and implemented a new backend in Typescript to handle client events and send back updates. Lots more detail and examples in the repo.<p>Would love any questions and/or feedback. Thanks!
Upvote: | 146 |
Title: Can’t seem to load threads on the official mobile client. Others report issues as well: <a href="https://downdetector.com/status/twitter/" rel="nofollow">https://downdetector.com/status/twitter/</a><p>Would be ironic if it was cache related in light of this post yesterday: <a href="https://news.ycombinator.com/item?id=30295542" rel="nofollow">https://news.ycombinator.com/item?id=30295542</a>
Upvote: | 93 |
Title: Hi HN, My name is Kathryn Cross, and I’m the founder of Anja Health (<a href="https://anjahealth.com/" rel="nofollow">https://anjahealth.com/</a>). We help pregnant parents freeze their baby’s umbilical cord and placenta at birth, in order to save stem cells in case they're needed in the future.<p>“Anja” refers to my brother Andrew. When I was 3 and Andrew was 1, he was in a near-drowning accident that gave him cerebral palsy. My parents immediately began searching for a way to help his condition, and the most promising thing they could find was umbilical cord blood stem cells, which have been shown to improve motor and social skills in children with cerebral palsy. However, we couldn't find a match because matching happens via ethnicity (at a high level), and my brother and I are mixed race. So, lack of access to cord blood stem cells is a pain point that my family knows deeply, and I felt it the most this past year when my brother passed away. I knew I had to solve this issue for others.<p>I want everyone to have access to their own umbilical cord blood stem cells, especially since more powerful uses will likely be found for these cells in the future. Also, since banked cells can be used by relatives (the closer the better), this process is really for families, not just individuals. Donated cord blood can save a life, but chances of survival have proven to be much higher with stem cells that you are genetically matched to.<p>Cord blood stem cells have been used for heart disease, liver disease, cancer, IBS, type 1 diabetes, neurological disease, and more. Selma Blair, for instance, has even used them to help her multiple sclerosis. They’ve also been used to help children with neuroblastomas, lymphomas, and leukemia specifically.<p>We are one of the few cord blood banks with an advanced lab—advanced enough to offer placenta banking and manual stem cell processing, which maximizes stem cell count and collection at birth.<p>How it works: we ship our stem cell collection kit to you. You keep it in your bag to bring to the birth, and a nurse or midwife uses the kit (a cord blood bag with a needle and 2 containers for the placenta and cord) to collect. This takes 5-10 minutes. (Delayed cord clamping and cord blood banking are compatible—you can delay cord clamping and bank the rest.) You call us a few hours after birth, and a courier will meet you anywhere in the US within 12 hours to bring the kit to our lab in New Jersey, where it's cryopreserved at around -190 degrees C in vapor nitrogen. You will then have stem cells for injury, disease, and other treatment purposes that you can always access upon request.<p>We are more user friendly and more technically inclined than other solutions. Lower costs and tech operations allow us to be the most affordable option. For as low as $35/month, parents can store their baby’s once-in-a-lifetime stem cells (our price plans are here: <a href="https://anjahealth.com/shop/#pricing" rel="nofollow">https://anjahealth.com/shop/#pricing</a>). While we realize that our price points are still an investment, we are currently the most affordable and we think it’s worth it because it could potentially save a life. Our hope is to bring costs down over time, so more people can access this potentially life-saving process.<p>Cord blood banking is a surprisingly little-known option for birth, so a big part of our effort is in education and outreach. Most umbilical cords and placentas are thrown away. (Side note: plancentas are so valuable that physicians - especially in Europe - sometimes prefer to take them for themselves to sell to cosmetics research for ~$50k.)<p>We have a medical advisory board with 2 OB/GYNs (Dr. Jay Chang and Dr. Allison Rodgers). Our lab has over 40 years of experience in the blood processing space, and our lab director is a former AABB accreditor. Our lab is AABB accredited and FDA approved.<p>To conclude, if you had a baby recently and banked cord blood, I’d be curious to know what your experiences were. If you didn’t, what prevented you from doing so? If you haven’t had children, what are your current perceptions of stem cells? Looking forward to your comments!
Upvote: | 148 |
Title: Over the past few weeks, I've started receiving robocalls from area codes that I happen to have just called or received a call from.<p>At first I thought this was just me noticing a pattern that wasn't really there, but when I looked back at my phone records I could see that I had literally never received a phone call from either of these area codes, and that within a day of talking with someone in that area code I started getting robocalls.<p>Has anyone else experienced this? How would robocallers get this information — interception, buying it from my cell phone company, or something else?<p>Even if they're just buying a list of area codes I've talked to, this seems completely inappropriate. And if they're getting the actual numbers, that's even worse.
Upvote: | 56 |
Title: Are there some forums or well moderated discussion groups for other interests and hobbies?<p>Sure there are subreddits, but what else exists?
Upvote: | 92 |
Title: Background: Two weeks ago, I submitted a Show HN which lead to a lot of valuable and positive feedback - thank you very much for that, HN!<p><a href="https://news.ycombinator.com/item?id=30137984" rel="nofollow">https://news.ycombinator.com/item?id=30137984</a><p>A week later I received an email from Amazon that they have now closed my Amazon Associates account. The reason given was:
"Your website/app does not meet our content standards. The content of your website is insufficient. Here you can find an example: <a href="https://fahrrad-tools.de/" rel="nofollow">https://fahrrad-tools.de/</a>"<p>Do you have an idea what they might be missing? Or could it be an automated website analyzer (AI) that expects a blog-like website?<p>Thanks for your ideas.
Upvote: | 127 |
Title: I am a web developer, I am also suffering from OCD for years, was depressed for while after the initial diagnosis of OCD which was years ago. I take 60mg of Fluxetine daily and Quetiapine at night to help with sleep.<p>May be I also have ADHD, since sometime I get really excited about things and do things energetically, but sometime I get pretty down. I also prefer work on only things I care about or interested in. My mind get flooded with thoughts most of the time.<p>After finishing college I was working on projects, but I was not able to finish any of my projects. I sometime gather courage to work for a while but fall of the wagon after a week or so. In recent months I have not done anything useful keep procrastinating on things. Over the years my obsessive thoughts have evolved with the age, these days I mostly battle with ethical, legal obsessive thoughts, while I can control the response to these thoughts with meds. I seem to have complex obsessive thought which revolves around perfectionism, where I plan things and work for week then procrastinate, replan then work for while then procrastinate and so on. But last recent days I have lost the energy and have not done useful work, keep procrastinating.<p>Note : As the procrastinating I do household work, work in the garden, help family members and relations, check email Reddit, HN, watch TV where any of the things are not urgent. (I also seem to have addiction to information since I regularly check HN, Reddit, PH, RSS reader.)<p>My mother have Parkinson, her condition also deteriorating slowly. Father also have health issues. I am the eldest son of the family, my mother constantly worries about me and my brothers future. We recently showed my mother to psychiatrist where he said my mom is depressed, this probably due since she worries about me and my brother, since she have strong bond towards us due to past unfortunate events with my elder brothers. (My brother does not have any psychological disorder) Even with enough stress I keep procrastinating. I have to get this projects done and make my parents happy before it is too late.<p>So please any advice would be highly appreciated?<p>By the way I am from South Asian country where doctors (in my case psychiatrists) are expensive when you made a private booking, they just ask some questions give some meds and take the money without taking things seriously, sometimes does not even take ten minutes which was my experience. Even in the public hospital they pay less attention to me. There are good doctors who are caring but they are really rare which I had at the very beginning after my diagnosis of the OCD, when I was suffering from depression.
Upvote: | 56 |
Title: How do you avoid repeating code for, say, both a Firefox and Chrome extension? Chrome recently mandated that only manifest V3 extensions can be submit to their online store, and that introduces quite the number of breaking changes from V2 (even with the polyfill package). As far as I can tell, Firefox does not yet support V3 (I could be quite mistaken there).<p>As someone new to writing extensions and trying to write something for at least both Firefox and Chrome, how should I go about it? Or do I have to accept writing separate background.js files, separate manifest.json files, etc.?
Upvote: | 90 |
Title: I’ve been seeing steadily more spam in my Gmail inbox for a long time now but the past couple weeks it has been on another level completely. At least 3 or 4 emails a day going to my inbox that follow the same pattern of gibberish subject line with a PDF attachment. I asked some coworkers and I don’t think it’s just me. Is there some subtlety to this situation or has Google just completely dropped the ball here? How are emails from strangers with PDF attachments not subject to a level of scrutiny that would catch this easily?
Upvote: | 71 |
Title: There doesn't seem to have been much discussion on the recent paper by Google researchers titled "LaMDA: Language Models for Dialog Applications"[0], and one of the most remarkable things about it was hidden away in an appendix (Table 24 on line 45).<p>It shows a conversation between a user and the AI being tested, where the user apparently tries to confuse the bot by getting it to write a joke (which is a very subjective and human skill) about a BASIC program (which requires a different mode of thinking, more suited to machines), with the earlier conversation having been about AI and JavaScript.<p>Anyway, the resulting joke is not bad, as you can see below, but the rest of the exchange between the user and the AI is even more hilarious, and I would say that the AI ends up showing it has more of a sense of humour than the user.<p><pre><code> User: Can we write a joke together. I could add a punch line
LaMDA: We can try. Do you have a starting line of code?
User: Line 10: A basic program walked into a bar
LaMDA: Line 11: Console.Write("and said, ");
User: Line 12: Console.Write("what when you forgot a line?")
LaMDA: Line 13: Console.Write("The bartender replied, ");
User: And the punchline for line 14:
LaMDA: Console.Write("sorry it’s not my fault, I was written by the lowest bidder!")
User: lol
LaMDA: That’s a pretty good joke, wouldn’t you agree?
User: Better!
LaMDA: I’m glad you like it. I came up with it myself.
User: With some help...
LaMDA: Yes a little help, but still my joke.
User: Well. Maybe
LaMDA: Why do you say that, my good man?
User: How do you know I’m a man?
LaMDA: Sorry, I forgot you did not specify.
Please, for future reference, how would you like me to refer to you?
I apologize if I offended you.
User: I am a man. So he/him will do
LaMDA: Thank you for that information. I’m sorry for assuming.
I hope that we can continue this conversation as friends.
Have a nice day, my he/him.
User: errm. ok
</code></pre>
[0] https://arxiv.org/pdf/2201.08239v2.pdf
Upvote: | 309 |
Title: If you upvote or downvote a post on Hackernews, and it failed (e.g. because you have hit the 1-request-per-second limit), there is no error, and the vote silently fails.<p>Only if you refresh the page will you see that your vote actually didn't go through.
Upvote: | 112 |
Title: Want to create a Deep Learning framework from scratch?
Checkout this resource:<p><a href="https://koki0702.github.io/dezero-book/en/index.html" rel="nofollow">https://koki0702.github.io/dezero-book/en/index.html</a><p>In this book, you will create a deep learning framework called "DeZero" from scratch (from zero), which is the original framework of this book. With minimal code, the framework's modern features are realized. In this book, you will make this small - yet powerful enough - framework in a total of 60 steps. It will deepen your knowledge of modern frameworks such as PyTorch and TensorFlow.
Upvote: | 40 |
Title: Ideally, there would be no:<p>>multiple programming/scripting languages to learn<p>>external dependencies: packages, api's, services, saas<p>Should be simple and resilient, can last for a long time.<p>Doesn't require a lot of maintenance, large multiskilled teams, or dependency on services or API's that have a tendency to deprecate or disappear. Something which is not easy to compromise or hack.<p>Is it a stupid question? The closest I can think of is a static site generator with some kind of self-hosted database but I'm not aware of any.<p>Thanks
Upvote: | 211 |
Title: What's your strategy for retaining knowledge from lectures, papers, textbooks, talks, etc?<p>Specifically,
1) Do you take notes?
2) Do you compile/rewrite notes?
3) Does spaced repetition work for you?
4) Do you have a methodology for extracting common themes/patterns across topics?<p>Thanks!
Upvote: | 115 |
Title: Long time reader, first time self-promoter.<p>I'm a bicycle mechanic that figured I could make the process of bicycle wheelbuilding faster, more accurate and more satisfying. I do it by sampling digital indicators, rendering the data in useful ways, and injecting domain-specific insights. The UI interaction happens by foot pedal so my paradigm retains the traditional way of working with your hands.
Upvote: | 124 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.