3,186 results for been

news.ycombinator.com
Ask HN: Do you hide your AI behind a curtain?https://news.ycombinator.com/item?id=49074416I used AI to build a music recommender system that itself uses no AI in its operation.I have been promoting the system in communities that can sometimes be considerably anti-AI. But people usually assume that it is AI because, well, it's a recommender system.Anyways, after a 30-year break, I rebuilt it and got it working the way I always wanted! It basically uses the same 10 lines of code, (for which I was granted now-expired US patent #5749081), but with a good interface around it instead of a lousy 1990s one.You tell it your 5 favorite albums, and it recommends other albums to try.It uses collaborative filtering (CF) to generate the music recommendations. It's just now exiting the "cold start" phase that all CF systems have to get through.The tagline I use is: "No sign-up needed, instant results, takes 2 minutes to try. Not AI."Try it here:[https://SimilaritiesEngine.com](https://similaritiesengine.com/)If you're curious, here's a New York Times article from way back then. (But the U
Jul 27, 2026 7:20 PM
science.nasa.gov
NASA’s Swift Sees ‘Wandering’ Mega Black Hole Shredding Starhttps://science.nasa.gov/missions/swift/nasas-swift-sees-wandering-mega-black-hole-shredding-star/NASA’s Neil Gehrels Swift Observatory captured an “orphan” black hole lighting up as it devoured a star on the outskirts of a faraway galaxy. These phenomena are rare to begin with, and none had ever before been seen so far outside of a galaxy’s core. “We were looking for these star-shredding events as a way […]
Jul 27, 2026 4:06 PM
github.com
Show HN: Otlet – Local LLM inference "inside" Postgreshttps://github.com/joshmeek/otletI’ve been working on Otlet, a Postgres extension for running local LLM inference “inside” Postgres (inference runs in a background worker, while Postgres stores the jobs, inputs, outputs, and receipts)I started it while working on an entity resolution problem (determining which rows in a table refer to the same entity). The data was already in Postgres, but using a model meant pulling rows into another process and then writing the results back. I wanted to see whether I could keep more of that workflow in the database right next to where the data livesRight now Otlet lets you start model work from SQL, require structured output, keep a record of each run, review proposed writes before they touch source data, etc. The example in the repo uses a small model for the first pass and a stronger model for uncertain casesThis is just something I've been hacking on, not something I would recommend attempting to use in production yet. There’s a Docker demo if anyone wants to try it. I’m mostly p
Jul 27, 2026 2:56 PM
news.ycombinator.com
Robotics development made dead simple (open source)https://news.ycombinator.com/item?id=49058956Hey everyone,My team and I have been working hard on this project: https://peppy.botIt's a direct replacement for ROS 2. We already have the OpenArm robot (https://openarm.dev) working on the platform, both v1.0 and v2.0, plus Isaac Sim and MuJoCo integration.If you're in a hurry, head over to https://docs.peppy.bot/quickstart/ and get started in 5min.Our long term vision is to allow anyone (even non-devs) to go from a prompt to real humanoid robot actions, first in simulation, then on the physical robot.Happy to answer any question.
Jul 26, 2026 3:13 PM
news.ycombinator.com
ASK HN: Why has technology become so unreliable?https://news.ycombinator.com/item?id=49056900Even though I'm a software engineer with long experience with serious projects, I'm become so disillusioned with the whole thing nowadays.Forget the ridiculous AI hype, forget about the lack of ethics and a moral compass; What's getting to me right now is the unreliability of it all. It seems like everything is held together with duct tape, and the tape is falling off.Just in the last few months, all these have happened:- My Macbook Air M1 has been acting up, refusing to charge in a stable manner. The audio jack is dead because apparently it is linked to the charging circuit. The screen sometimes shows a tint on a whim. Now it is dead and not charging at all. Granted, it has otherwise been a fine machine so far, and I've knocked it over a few times, but still. Even my old trusty 2014 Macbook Pro is still going strong, and I've abused that one much more.- I also can't use my old Macbook Pro well, because the replacement Transcend 256GB SSD I put in it around 2020 is now failing, causing
Jul 26, 2026 11:13 AM
glossarypage.com
Show HN: GlossaryPage – Turn customer questions into knowledge pageshttps://glossarypage.com/Hey HN, I built GlossaryPage after noticing companies have long-tail content opportunities that never get created because they fall between blog posts and documentation.The primary use case is marketing teams building glossaries and learning hubs around these topics. The same workflow also works for support teams creating help centers.GlossaryPage helps teams identify unanswered topics, generate drafts with AI, review content, and publish structured knowledge pages.Here is a demo site: https://glossary.glossarypage.comSome things I have been thinking about while building this:1. How to avoid creating more low-quality content?This is a challenge for anyone building AI content tools, and is something I'm working on. The product is focused on generating drafts, but users are responsible for reviewing and approving what gets published. My guess is that as AI systems improve at evaluating quality, there will be less value in publishing low-quality content.2. Why not just use an existing CMS
Jul 24, 2026 3:44 AM
news.ycombinator.com
Launch HN: Screenpipe (YC S26) – Record how you work and turn that into agentshttps://news.ycombinator.com/item?id=49024620Hi Hacker News, I'm Louis. I built Screenpipe (https://screenpipe.com), an app that records your screen and audio locally (only!), and gives AI agents a searchable memory of what you've seen, said, and heard. This makes it easier to automate your repetitive tasks, turn them into SOPs (Standard Operating Procedure) and so on.I made a HN-style demo video at https://www.tella.tv/video/build-your-ai-second-brain-with-s... and there’s a marketing video at https://www.youtube.com/watch?v=c1jV6E9pyug.I’ve been obsessed with this for a long time. I’ve been maintaining a “second brain” since 2020, in which I would store journals, handwritten notes, music I listen to, projects I'm working on, conversations I have with people, personal CRM etc. I experimented a lot of RAG in the early days with ParlAI, hundreds of fine-tuned GPT2 models, and GPT3 (https://forum.obsidian.md/t/fine-tuning-openai-api-gpt3-on-y...). Later I built Ava, the first Obsidian AI plugin, which grew to a few thousands of use
Jul 23, 2026 4:48 PM
github.com
Show HN: Rendi, an agent harness on Trigger.dev without spinning up a VMhttps://github.com/mcheemaa/rendiHi all,Rendi is a full agent harness that runs background jobs, schedules, a real browser, and email without you needing to spin up a virtual machine. I built it for the ClickHouse and Trigger.dev hackathon but honestly super excited on how it came out.If you look at my github I have been working on deploying agents for a decent time now but mainly by spinning up VMs on Hetzner or AWS. The one thing I still wasn't able to crack was how to make these agents per tenant yourself without buying a huge bare metal machine to create micro VMs or use third party VM providers, but I think with Trigger.dev and this work on Rendi I can easily provision these agents per tenant without having to deal with all things VMs and also cost is so low.I also spent a lot of time on the UI and the component library. I literally came up with a brand for my project before starting it up hehe. I have also been thinking a lot more towards accessible UIs specially since it makes an agents life a lot easier when b
Jul 23, 2026 1:44 PM
github.com
Show HN: Mwe-MCP – self-hosted memory for AI agents that knows who may know whathttps://github.com/Fr4nZ82/mwe-mcpHi HN, for about a year now I've been experimenting with AI agents and building my own home ecosystem; from the start I set out with the idea of an agent that behaves like a member of the family, not as a personal agent, and this made me clash very early first with OpenClaw's builtin memory, then I tested dozens of memory plugins without ever finding one that fit my purpose, so like any good builder I made my own. First on OpenClaw, as a plugin, then the idea matured and since the beginning of this year the memory plugin has evolved into an agent agnostic MCP server. It has been running my household since spring, 4 people and 3 agents on the same memory.The core idea that sets this project apart is the addition of inline ACLs on the prose of the wiki pages; the inspiration came to me, in all honesty, when social media was full of the redacted documents from the Epstein files; the wikis are written like that, every paragraph, every item of a list, every sensitive piece of data has its o
Jul 23, 2026 12:38 PM
kalvir.life
Show HN: Kalvir Clockhttps://kalvir.life/clockI've been working on new mind psychology visualizations of time and have created a unique clock to work in the background of my iterm2 transparent vim that has been really helping me focus my mind on complex code, notes, thinking. So have published it for free, it's a one page app, so you can easily copy the HTML code and host it yourself. It's your unique clock for your minds eye.
Jul 22, 2026 8:17 PM
nkorai.github.io
Show HN: An open source schema definition for datasheetshttps://nkorai.github.io/datasheet-schema/Not the first person to do this but all the other examples I've seen are either dead or miss the point. Why: I was designing a Eurorack compatible instrument and I did not want to brush up on now 10 years old college electrical engineering knowledge and I just want Claude to make me a PCB board. I realized that all of the sources for electrical component information are PDFs and not very nicely machine readable. That led me to ask why not and one of the gaps I see is a lack of an agreed upon easy to use schema for both extraction and consumption of datasheet information.So I've been building datasheet-schema. It's an open JSON Schema for the electrical specs in a component datasheet. One of the core idea's is that a number by itself is useless. "VOUT = 3.3V" tells you nothing until know it was measured at 1mA load, 25C, 4.3V in. So every value in the schema carries its test conditions and a pointer back to the page it came from. That last part matters to me because if a model extracts
Jul 22, 2026 6:12 PM
orate.to
Show HN: Orate – On-device neural text-to-speech queue for Machttps://orate.to/Hey friends! Brad here - long time HN user, founder, engineer (Coinbase, Soothe, Jeevz, Release, Hired, GrowthX, etc)...I have been struggling recently with too many tabs, emails, articles, etc sitting unread while I swap between Claude code sessions all day. So I decided to build Orate to help me work through the backlog by listening to it all like I would a podcast.Orate allows you to select any text on your screen and keyboard shortcut it to a listening queue where it gets processed using the latest + greatest TTS AI models, and then read back to you in a mostly-natural sounding voice. Orate works fully on-device and offline. Whatever you pass to it stays yours. It's native, lives in your menu bar, and supports things like tagging, system playback controls, speed adjustment, and more. There's also an optional HD-voice tier that uses Chatterbox instead of Kokoro which ships with it for more expressive TTS.I'm also burnt out on being chipped away at little by little with a subscriptio
Jul 21, 2026 8:38 PM
github.com
Show HN: PMG, open source package firewallhttps://github.com/safedep/pmgHi HNI am the founder of SafeDep. We have been detecting malicious packages for a while. Coming from DevSecOps background, I always considered malicious package detection & protection to be a build stage problem. But I was wrong since the S1ngularity and early Shai-Hulud days.In 2026, we pretty much started worrying more about our own dev machines than CI/CD environment. Depending only on threat intelligence data (OSV / SafeDep / Socket / any other source) to protect our own dev machines did not feel right. We wanted to build a multi-layered protection that can get 100% visibility of OSS packages coming in, and can protect against known and “hopefully” unknown threats. That’s how Package Manager Guard (PMG) started. Core idea was simple:- Start a local proxy (localhost)- Make sure supported package managers like npm, pnpm, pip etc. goes through it- Use threat intelligence data to fail fast on known malicious packages- Apply policies like dependency cooldown as additional guardrails- Ad
Jul 21, 2026 4:58 PM
nasa.gov
Establishing Crew Exposure Limits of Martian Dusthttps://www.nasa.gov/general/establishing-crew-exposure-limits-of-martian-dust/Background Human exploration of Mars will expose crews to a persistent, fine particulate environment whose physicochemical properties and health implications remain only partly understood. Because no samples of authentic Martian airborne dust have been returned to Earth, NASA must rely on lunar dust toxicology, Martian regolith simulants, and extensive rover/lander geochemical and mineralogical datasets to […]
Jul 21, 2026 2:03 PM
github.com
Show HN: A chess game you play with Claude as your wing-bot in the CLIhttps://github.com/goawaygeek/ground-controlHey HN!Wanted to show off a thing I built in case it interests anyone.I wanted to build a game you play inside the claude code CLI and back when they launched the channels feature I started investigating ways to use that to do so. I started with a multiplayer comedy battle game where you would collaborate with Claude to write jokes based on a theme in a timeframe and then post them to an audience and compete against other folks (with the audience voting for the funniest joke), it was OK but I didn't have anyone to really test it with so I moved on. My son has been learning chess so instead I tweaked it to let you play chess with Claude suggesting three possible move options for you to choose from and submit as your move (you choose what you actually want to do not Claude). It was much more fun and allowed me to actually learn a thing or two about chess (my chess isn't great, it didn't need to do much to help me learn but I could go back and forth with it on why a certain move was bette
Jul 20, 2026 11:40 PM
news.ycombinator.com
A B2B marketing agency grew to $1.5M ARR in 6 months by betting on AIhttps://news.ycombinator.com/item?id=48980665I run GrowthSpree, a B2B SaaS marketing agency, selling into the US and Europe. Six months ago we made a bet that the agency model itself was broken for the AI era, so we tore ours down and rebuilt it. This is what we did and what actually happened. The bet: become the first truly AI-native marketing agency. Not an agency that "uses AI tools" by bolting ChatGPT onto a 2015 workflow, but one where AI is wired into how we find demand, win clients, and run delivery. We rebuilt the operating model, not just the toolbar.The context that matters: we have worked with 300+ B2B SaaS companies, but we'd been stuck between $500K and $800K ARR for two years. Plateaued. Then in the six months since the rebuild we went to $1.5M, almost entirely in the US and Europe, where we had no brand. Clients now include Datahub, PriceLabs, Hasura, Rocketlane, Proton AG, Spoke and more.What changed:1. We bet on AEO over SEO. Buyers now ask an LLM before they ask Google. So we built our own Answer Engine Optimiza
Jul 20, 2026 3:58 PM
voxthermic.jbri.workers.dev
Show HN: VoxThermic – A macOS journaling app that uses Apple's Foundation Modelshttps://voxthermic.jbri.workers.dev/TL;DR version: I made a macOS journaling app that use Foundation Models to analyze entries for mood + written themes, and also has voice transcription, because I couldn't find any other journaling app that does those things.OK, now for the longer, I-rambled-too-much version:For the past few weeks I've been working on a macOS journaling app called VoxThermic.The idea for it came from my own journaling habits, where my mood tends to shift a lot depending on whatever I'm dealing with. I've tried some journaling apps, but I've never found one that can analyze mood or see how my mood changes depending on what I'm writing about.So I just figured I'd build it myself. I've been experimenting a lot with Apple's Foundation Models and Natural Language frameworks, and those all work on-device and offline (which is good because there's no way I'm sending journal entries to some AI company's data centers!)But there's one problem with using Foundation Models: they're tiny. About 3 billion parameters,
Jul 20, 2026 2:40 PM
readthetape.cc
Show HN: Read the Tape – Wordle for daytrading, five blind S&P 500 charts a dayhttps://readthetape.cc/Read the Tape gives players the same 5 S&P500 stock charts per day to predict. You select low, medium or high confidence and then call the chart UP or DOWN. It's a 1d chart which then resolves over 5 days. Alpha is scored against the Monkey Index, a basket of 11 random coin flips at low confidence which provides a tangible win/lose condition.We're two weeks in and some interesting data is being kicked up. Players like to call tops even though stonks go up- 60% of the 70 charts so far resolve higher, players' down calls have only been right 31% of the time. There's a full stats dive at https://readthetape.cc/notes/tape-report-1Your feedback and thoughts is most welcome.
Jul 20, 2026 12:07 PM