BYOMesh – New LoRa mesh radio offers 100x the bandwidth
3 by nullagent | 1 comments on Hacker News.
Sunday, May 3, 2026
Saturday, May 2, 2026
Friday, May 1, 2026
Thursday, April 30, 2026
Wednesday, April 29, 2026
Tuesday, April 28, 2026
Monday, April 27, 2026
New top story on Hacker News: China blocks Meta's acquisition of AI startup Manus
China blocks Meta's acquisition of AI startup Manus
33 by yakkomajuri | 7 comments on Hacker News.
https://ift.tt/iBFlkr2... https://ift.tt/IApTbhR
33 by yakkomajuri | 7 comments on Hacker News.
https://ift.tt/iBFlkr2... https://ift.tt/IApTbhR
Sunday, April 26, 2026
Saturday, April 25, 2026
Friday, April 24, 2026
Thursday, April 23, 2026
Wednesday, April 22, 2026
Tuesday, April 21, 2026
Monday, April 20, 2026
Sunday, April 19, 2026
Saturday, April 18, 2026
New top story on Hacker News: Show HN: AI Subroutines – Run automation scripts inside your browser tab
Show HN: AI Subroutines – Run automation scripts inside your browser tab
7 by arjunchint | 0 comments on Hacker News.
We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decision: the script executes inside the webpage itself, not through a proxy, not in a headless worker, not out of process. The script dispatches requests from the tab's execution context, so auth, CSRF, TLS session, and signed headers get added to all requests and propagate for free. No certificate installation, no TLS fingerprint modification, no separate auth stack to maintain. During recording, the extension intercepts network requests (MAIN-world fetch/XHR patch + webRequest fallback). We score and trim ~300 requests down to ~5 based on method, timing relative to DOM events, and origin. Volatile GraphQL operation IDs are detected and force a DOM-only fallback before they break silently on the next run. The generated code combines network calls with DOM actions (click, type, find) in the same function via an rtrvr.* helper namespace. Point the agent at a spreadsheet of 500 rows and with just one LLM call parameters are assigned and 500 Subroutines kicked off. Key use cases: - record sending IG DM, then have reusable and callable routine to send DMs at zero token cost - create routine getting latest products in site catalog, call it to get thousands of products via direct graphql queries - setup routine to file EHR form based on parameters to the tool, AI infers parameters from current page context and calls tool - reuse routine daily to sync outbound messages on LinkedIn/Slack/Gmail to a CRM using a MCP server We see the fundamental reason that browser agents haven't taken off is that for repetitive tasks going through the inference loop is unnecessary. Better to just record once, and get the LLM to generate a script leveraging all the possible ways to interact with a site and the wider web like directly calling backed API's, interacting with the DOM, and calling 3P tools/APIs/MCP servers.
7 by arjunchint | 0 comments on Hacker News.
We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decision: the script executes inside the webpage itself, not through a proxy, not in a headless worker, not out of process. The script dispatches requests from the tab's execution context, so auth, CSRF, TLS session, and signed headers get added to all requests and propagate for free. No certificate installation, no TLS fingerprint modification, no separate auth stack to maintain. During recording, the extension intercepts network requests (MAIN-world fetch/XHR patch + webRequest fallback). We score and trim ~300 requests down to ~5 based on method, timing relative to DOM events, and origin. Volatile GraphQL operation IDs are detected and force a DOM-only fallback before they break silently on the next run. The generated code combines network calls with DOM actions (click, type, find) in the same function via an rtrvr.* helper namespace. Point the agent at a spreadsheet of 500 rows and with just one LLM call parameters are assigned and 500 Subroutines kicked off. Key use cases: - record sending IG DM, then have reusable and callable routine to send DMs at zero token cost - create routine getting latest products in site catalog, call it to get thousands of products via direct graphql queries - setup routine to file EHR form based on parameters to the tool, AI infers parameters from current page context and calls tool - reuse routine daily to sync outbound messages on LinkedIn/Slack/Gmail to a CRM using a MCP server We see the fundamental reason that browser agents haven't taken off is that for repetitive tasks going through the inference loop is unnecessary. Better to just record once, and get the LLM to generate a script leveraging all the possible ways to interact with a site and the wider web like directly calling backed API's, interacting with the DOM, and calling 3P tools/APIs/MCP servers.
Friday, April 17, 2026
Thursday, April 16, 2026
Wednesday, April 15, 2026
Tuesday, April 14, 2026
New top story on Hacker News: Show HN: A memory database that forgets, consolidates, and detects contradiction
Show HN: A memory database that forgets, consolidates, and detects contradiction
9 by pranabsarkar | 2 comments on Hacker News.
Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier. YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does. Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA cluster via Docker Compose or Kubernetes. Chaos-tested failover, runtime deadlock detection (parking_lot), per-tenant quotas, Prometheus metrics. Ran a 42-task hardening sprint last week — 1178 core tests, cargo-fuzz targets, CRDT property tests, 5 ops runbooks. Live on a 3-node Proxmox homelab cluster with multiple tenants. Alpha — primary user is me, looking for the second one.
9 by pranabsarkar | 2 comments on Hacker News.
Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier. YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does. Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA cluster via Docker Compose or Kubernetes. Chaos-tested failover, runtime deadlock detection (parking_lot), per-tenant quotas, Prometheus metrics. Ran a 42-task hardening sprint last week — 1178 core tests, cargo-fuzz targets, CRDT property tests, 5 ops runbooks. Live on a 3-node Proxmox homelab cluster with multiple tenants. Alpha — primary user is me, looking for the second one.
Monday, April 13, 2026
Sunday, April 12, 2026
Saturday, April 11, 2026
Friday, April 10, 2026
Thursday, April 9, 2026
Wednesday, April 8, 2026
Tuesday, April 7, 2026
Monday, April 6, 2026
New top story on Hacker News: Show HN: GovAuctions lets you browse government auctions at once
Show HN: GovAuctions lets you browse government auctions at once
20 by player_piano | 13 comments on Hacker News.
I've long been into finding deals on government auction sites (seizures, surplus sales etc.) - right now for example San Diego DHS is selling 26 tons of lead shot, with bidding starting at $1,000 ¯\_(ツ)_/¯ It has historically been extremely tedious though: scanning dozens of janky sites which have interminable page loading times; back buttons take you all the way back to the homepage etc. The site I built - GovAuctions - lets you search every government surplus auction at once. You can filter by location, category, and price, save items to a watchlist, and get alerts when new auctions match what you're looking for. Let me know what you think, if you have any suggestions, and if you find any deals in your area!
20 by player_piano | 13 comments on Hacker News.
I've long been into finding deals on government auction sites (seizures, surplus sales etc.) - right now for example San Diego DHS is selling 26 tons of lead shot, with bidding starting at $1,000 ¯\_(ツ)_/¯ It has historically been extremely tedious though: scanning dozens of janky sites which have interminable page loading times; back buttons take you all the way back to the homepage etc. The site I built - GovAuctions - lets you search every government surplus auction at once. You can filter by location, category, and price, save items to a watchlist, and get alerts when new auctions match what you're looking for. Let me know what you think, if you have any suggestions, and if you find any deals in your area!
Sunday, April 5, 2026
Saturday, April 4, 2026
Friday, April 3, 2026
Thursday, April 2, 2026
Wednesday, April 1, 2026
Tuesday, March 31, 2026
Monday, March 30, 2026
Sunday, March 29, 2026
New top story on Hacker News: Pretext: TypeScript library for multiline text measurement and layout
Pretext: TypeScript library for multiline text measurement and layout
41 by emersonmacro | 2 comments on Hacker News.
https://ift.tt/ARZV30X , https://ift.tt/APVevja Demos: https://ift.tt/8GlSmNn , https://somnai-dreams.github.io/pretext-demos/
41 by emersonmacro | 2 comments on Hacker News.
https://ift.tt/ARZV30X , https://ift.tt/APVevja Demos: https://ift.tt/8GlSmNn , https://somnai-dreams.github.io/pretext-demos/
Saturday, March 28, 2026
Friday, March 27, 2026
New top story on Hacker News: Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam)
Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam)
15 by supai | 9 comments on Hacker News.
Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the outputs by weighting segments based on confidence. Low entropy in the output token probability distributions correlates with accuracy. High entropy is often where hallucinations begin. My dad Scott (AI Research Scientist at TRI) is my research partner on this. He sends me papers at all hours, we argue about whether they actually apply and what modifications make sense, and then I build and test things. The entropy-weighting approach came out of one of those conversations. In our eval on Humanity's Last Exam, Sup scored 52.15%. The best individual model in the same evaluation run got 44.74%. The relative gap is statistically significant (p < 0.001). Methodology, eval code, data, and raw results: - https://sup.ai/research/hle-white-paper-jan-9-2026 - https://github.com/supaihq/hle Limitations: - We evaluated 1,369 of the 2,500 HLE questions (details in the above links) - Not all APIs expose token logprobs; we use several methods to estimate confidence when they don't We tried offering free access and it got abused so badly it nearly killed us. Right now the sustainable option is a $5 starter credit with card verification (no auto-charge). If you don't want to sign up, drop a prompt in the comments and I'll run it myself and post the result. Try it at https://sup.ai . My dad Scott (@scottmu) is in the thread too. Would love blunt feedback, especially where this really works for you and where it falls short. Here's a short demo video: https://www.youtube.com/watch?v=DRcns0rRhsg
15 by supai | 9 comments on Hacker News.
Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the outputs by weighting segments based on confidence. Low entropy in the output token probability distributions correlates with accuracy. High entropy is often where hallucinations begin. My dad Scott (AI Research Scientist at TRI) is my research partner on this. He sends me papers at all hours, we argue about whether they actually apply and what modifications make sense, and then I build and test things. The entropy-weighting approach came out of one of those conversations. In our eval on Humanity's Last Exam, Sup scored 52.15%. The best individual model in the same evaluation run got 44.74%. The relative gap is statistically significant (p < 0.001). Methodology, eval code, data, and raw results: - https://sup.ai/research/hle-white-paper-jan-9-2026 - https://github.com/supaihq/hle Limitations: - We evaluated 1,369 of the 2,500 HLE questions (details in the above links) - Not all APIs expose token logprobs; we use several methods to estimate confidence when they don't We tried offering free access and it got abused so badly it nearly killed us. Right now the sustainable option is a $5 starter credit with card verification (no auto-charge). If you don't want to sign up, drop a prompt in the comments and I'll run it myself and post the result. Try it at https://sup.ai . My dad Scott (@scottmu) is in the thread too. Would love blunt feedback, especially where this really works for you and where it falls short. Here's a short demo video: https://www.youtube.com/watch?v=DRcns0rRhsg
Thursday, March 26, 2026
Wednesday, March 25, 2026
Tuesday, March 24, 2026
Monday, March 23, 2026
Sunday, March 22, 2026
Saturday, March 21, 2026
New top story on Hacker News: Show HN: Joonote – A note-taking app on your lock screen and notification panel
Show HN: Joonote – A note-taking app on your lock screen and notification panel
7 by kilgarenone | 0 comments on Hacker News.
I finally built this app after many years of being sick of unlocking my phone every goddamn time I need to take or view my notes. It particularly sucks when I'm doing my grocery and going down the list. I started building last year June. This is a native app written in Kotlin. And since I'm a 100% Web dev guy, I gotta say this wouldn't have been possible without this AI to assist me. So this isn't "vibe-coded". I simply used the chat interface in Gemini website, manually copy paste codes to build and integrate every single thing in the app! I used gemini to build it just because I was piggybacking on my last company's enterprise subscription. I personally didn't subscribe to any AI (and still don't cuz the free quota seems enough for me :) So I certainly have learnt alot about Android development, architecture patterns, Kotlin syntax, and obeying Google's whims. Can't say I love it all, but for the sake of this app, I will :) Anyway, I finally have the app I wish existed, and I'm using it everyday. It not only does the main thing I needed it to do, but there's also all this stuff: - Make your notes private if you don't want to show them on lock screen. - Create check/to-do lists. - Set one time or recurring reminders. - Full-text search your notes in the app. - Speech-to-text. - Organize your notes with custom or color labels. - Pin the app as a widget on your home screen. - You can auto backup and restore your notes on new install or Android device. - Works offline. - And no funny business happening in the background https://ift.tt/0on3IWz It's 30-day trial, then a one-time $9.99 to go Pro forever. I would love you all to check it out, FWIW. Ok thanks!
7 by kilgarenone | 0 comments on Hacker News.
I finally built this app after many years of being sick of unlocking my phone every goddamn time I need to take or view my notes. It particularly sucks when I'm doing my grocery and going down the list. I started building last year June. This is a native app written in Kotlin. And since I'm a 100% Web dev guy, I gotta say this wouldn't have been possible without this AI to assist me. So this isn't "vibe-coded". I simply used the chat interface in Gemini website, manually copy paste codes to build and integrate every single thing in the app! I used gemini to build it just because I was piggybacking on my last company's enterprise subscription. I personally didn't subscribe to any AI (and still don't cuz the free quota seems enough for me :) So I certainly have learnt alot about Android development, architecture patterns, Kotlin syntax, and obeying Google's whims. Can't say I love it all, but for the sake of this app, I will :) Anyway, I finally have the app I wish existed, and I'm using it everyday. It not only does the main thing I needed it to do, but there's also all this stuff: - Make your notes private if you don't want to show them on lock screen. - Create check/to-do lists. - Set one time or recurring reminders. - Full-text search your notes in the app. - Speech-to-text. - Organize your notes with custom or color labels. - Pin the app as a widget on your home screen. - You can auto backup and restore your notes on new install or Android device. - Works offline. - And no funny business happening in the background https://ift.tt/0on3IWz It's 30-day trial, then a one-time $9.99 to go Pro forever. I would love you all to check it out, FWIW. Ok thanks!
Friday, March 20, 2026
Thursday, March 19, 2026
New top story on Hacker News: Show HN: Dumped Wix for an AI Edge agent so I never have to hire junior staff
Show HN: Dumped Wix for an AI Edge agent so I never have to hire junior staff
5 by axotopia | 2 comments on Hacker News.
I run a building design consultancy. I got tired of paying Wix $40/month for a brochure that couldn’t answer simple service questions, and me wasting hours on the same FAQs. So I killed it all and spent 4 months building a 'talker': https://axoworks.com The stack is completely duct-taped: Netlify’s 10s serverless timeout forced me to split the agent into three pieces: Brain (Edge), Hands (Browser), and Voice (Edge). I haven’t coded in 30 years. This was 3 steps forward, 2 steps back, heavily guided by AI. The fight that proved it worked: 2 weeks ago, a licensed architect attacked the bot, trying to prove my business model harms the profession. The AI (DeepSeek-R3) completely dismantled his arguments. It was hilariously caustic. Log: https://ift.tt/82iQkYn... A few battle scars: * Web Speech API works fine, right up until someone speaks Chinese without toggling the language mode. Then it forcefully spits out English phonetic gibberish. Still a headache. * Liability is the killer. Hallucinate a building code clause? We’re dead. Insurance won’t touch us. * We publish the audit logs to keep ourselves honest and make sure the system stays hardened. Audit: https://ift.tt/4sTxpUE The hardest part was getting the intent right: making one LLM pivot seamlessly from a warm principal’s tone with a homeowner, to a defensive bulldog when attacked by a peer. That took 2.5 months of tuning. We burn through tokens with an 'Eager RAG' hack (pre-fetching guesses) just to improve responsiveness. I also ripped out the “essential” persistent DBs—less than 5% of visitors ever return, so why bother? If a client drops mid-query, their session vanishes. No server-side queues. The point: To let me operate with a network of seasoned pros, and trim the fat. Try to break it. I’ll be in the comments. Kee
5 by axotopia | 2 comments on Hacker News.
I run a building design consultancy. I got tired of paying Wix $40/month for a brochure that couldn’t answer simple service questions, and me wasting hours on the same FAQs. So I killed it all and spent 4 months building a 'talker': https://axoworks.com The stack is completely duct-taped: Netlify’s 10s serverless timeout forced me to split the agent into three pieces: Brain (Edge), Hands (Browser), and Voice (Edge). I haven’t coded in 30 years. This was 3 steps forward, 2 steps back, heavily guided by AI. The fight that proved it worked: 2 weeks ago, a licensed architect attacked the bot, trying to prove my business model harms the profession. The AI (DeepSeek-R3) completely dismantled his arguments. It was hilariously caustic. Log: https://ift.tt/82iQkYn... A few battle scars: * Web Speech API works fine, right up until someone speaks Chinese without toggling the language mode. Then it forcefully spits out English phonetic gibberish. Still a headache. * Liability is the killer. Hallucinate a building code clause? We’re dead. Insurance won’t touch us. * We publish the audit logs to keep ourselves honest and make sure the system stays hardened. Audit: https://ift.tt/4sTxpUE The hardest part was getting the intent right: making one LLM pivot seamlessly from a warm principal’s tone with a homeowner, to a defensive bulldog when attacked by a peer. That took 2.5 months of tuning. We burn through tokens with an 'Eager RAG' hack (pre-fetching guesses) just to improve responsiveness. I also ripped out the “essential” persistent DBs—less than 5% of visitors ever return, so why bother? If a client drops mid-query, their session vanishes. No server-side queues. The point: To let me operate with a network of seasoned pros, and trim the fat. Try to break it. I’ll be in the comments. Kee
Wednesday, March 18, 2026
New top story on Hacker News: 2025 Turing award given for quantum information science
2025 Turing award given for quantum information science
21 by srvmshr | 4 comments on Hacker News.
https://ift.tt/OMNQTDs... https://ift.tt/6teoTNQ... https://ift.tt/ylDX3pF... https://ift.tt/gJCjOBQ...
21 by srvmshr | 4 comments on Hacker News.
https://ift.tt/OMNQTDs... https://ift.tt/6teoTNQ... https://ift.tt/ylDX3pF... https://ift.tt/gJCjOBQ...
Tuesday, March 17, 2026
Monday, March 16, 2026
Sunday, March 15, 2026
New top story on Hacker News: Ask HN: How is AI-assisted coding going for you professionally?
Ask HN: How is AI-assisted coding going for you professionally?
18 by svara | 6 comments on Hacker News.
Comment sections on AI threads tend to split into "we're all cooked" and "AI is useless." I'd like to cut through the noise and learn what's actually working and what isn't, from concrete experience. If you've recently used AI tools for professional coding work, tell us about it. What tools did you use? What worked well and why? What challenges did you hit, and how (if at all) did you solve them? Please share enough context (stack, project type, team size, experience level) for others to learn from your experience. The goal is to build a grounded picture of where AI-assisted development actually stands in March 2026, without the hot air.
18 by svara | 6 comments on Hacker News.
Comment sections on AI threads tend to split into "we're all cooked" and "AI is useless." I'd like to cut through the noise and learn what's actually working and what isn't, from concrete experience. If you've recently used AI tools for professional coding work, tell us about it. What tools did you use? What worked well and why? What challenges did you hit, and how (if at all) did you solve them? Please share enough context (stack, project type, team size, experience level) for others to learn from your experience. The goal is to build a grounded picture of where AI-assisted development actually stands in March 2026, without the hot air.
Saturday, March 14, 2026
New top story on Hacker News: Show HN: Learn Arabic with spaced repetition and comprehensible input
Show HN: Learn Arabic with spaced repetition and comprehensible input
11 by adangit | 2 comments on Hacker News.
Sharing a friends first-ever Rails application, dedicated to Arabic learning, from 0 to 1. Pulls language learning methods from Anki, comprehensible input and more.
11 by adangit | 2 comments on Hacker News.
Sharing a friends first-ever Rails application, dedicated to Arabic learning, from 0 to 1. Pulls language learning methods from Anki, comprehensible input and more.
Friday, March 13, 2026
Thursday, March 12, 2026
Wednesday, March 11, 2026
Tuesday, March 10, 2026
Monday, March 9, 2026
Sunday, March 8, 2026
New top story on Hacker News: Show HN: Skir – like Protocol Buffer but better
Show HN: Skir – like Protocol Buffer but better
6 by gepheum | 1 comments on Hacker News.
Why I built Skir: https://ift.tt/JtT8yro... Quick start: npx skir init All the config lives in one YML file. Website: https://skir.build GitHub: https://ift.tt/6jspZtY Would love feedback especially from teams running mixed-language stacks.
6 by gepheum | 1 comments on Hacker News.
Why I built Skir: https://ift.tt/JtT8yro... Quick start: npx skir init All the config lives in one YML file. Website: https://skir.build GitHub: https://ift.tt/6jspZtY Would love feedback especially from teams running mixed-language stacks.
Saturday, March 7, 2026
Friday, March 6, 2026
New top story on Hacker News: Show HN: Claude-replay – A video-like player for Claude Code sessions
Show HN: Claude-replay – A video-like player for Claude Code sessions
13 by es617 | 7 comments on Hacker News.
I got tired of sharing AI demos with terminal screenshots or screen recordings. Claude Code already stores full session transcripts locally as JSONL files. Those logs contain everything: prompts, tool calls, thinking blocks, and timestamps. I built a small CLI tool that converts those logs into an interactive HTML replay. You can step through the session, jump through the timeline, expand tool calls, and inspect the full conversation. The output is a single self-contained HTML file — no dependencies. You can email it, host it anywhere, embed it in a blog post, and it works on mobile. Repo: https://ift.tt/kVc30Zt Example replay: https://es617.github.io/assets/demos/peripheral-uart-demo.ht...
13 by es617 | 7 comments on Hacker News.
I got tired of sharing AI demos with terminal screenshots or screen recordings. Claude Code already stores full session transcripts locally as JSONL files. Those logs contain everything: prompts, tool calls, thinking blocks, and timestamps. I built a small CLI tool that converts those logs into an interactive HTML replay. You can step through the session, jump through the timeline, expand tool calls, and inspect the full conversation. The output is a single self-contained HTML file — no dependencies. You can email it, host it anywhere, embed it in a blog post, and it works on mobile. Repo: https://ift.tt/kVc30Zt Example replay: https://es617.github.io/assets/demos/peripheral-uart-demo.ht...
Thursday, March 5, 2026
Wednesday, March 4, 2026
Tuesday, March 3, 2026
New top story on Hacker News: Show HN: Open-Source Article 12 Logging Infrastructure for the EU AI Act
Show HN: Open-Source Article 12 Logging Infrastructure for the EU AI Act
12 by systima | 0 comments on Hacker News.
EU legislation (which affects UK and US companies in many cases) requires being able to truly reconstruct agentic events. I've worked in a number of regulated industries off & on for years, and recently hit this gap. We already had strong observability, but if someone asked me to prove exactly what happened for a specific AI decision X months ago (and demonstrate that the log trail had not been altered), I could not. The EU AI Act has already entered force, and its Article 12 kicks-in in August this year, requiring automatic event recording and six-month retention for high-risk systems, which many legal commentators have suggested reads more like an append-only ledger requirement than standard application logging. With this in mind, we built a small free, open-source TypeScript library for Node apps using the Vercel AI SDK that captures inference as an append-only log. It wraps the model in middleware, automatically logs every inference call to structured JSONL in your own S3 bucket, chains entries with SHA-256 hashes for tamper detection, enforces a 180-day retention floor, and provides a CLI to reconstruct a decision and verify integrity. There is also a coverage command that flags likely gaps (in practice omissions are a bigger risk than edits). The library is deliberately simple: TS, targeting Vercel AI SDK middleware, S3 or local fs, linear hash chaining. It also works with Mastra (agentic framework), and I am happy to expand its integrations via PRs. Blog post with link to repo: https://ift.tt/X2v3YSm I'd value feedback, thoughts, and any critique.
12 by systima | 0 comments on Hacker News.
EU legislation (which affects UK and US companies in many cases) requires being able to truly reconstruct agentic events. I've worked in a number of regulated industries off & on for years, and recently hit this gap. We already had strong observability, but if someone asked me to prove exactly what happened for a specific AI decision X months ago (and demonstrate that the log trail had not been altered), I could not. The EU AI Act has already entered force, and its Article 12 kicks-in in August this year, requiring automatic event recording and six-month retention for high-risk systems, which many legal commentators have suggested reads more like an append-only ledger requirement than standard application logging. With this in mind, we built a small free, open-source TypeScript library for Node apps using the Vercel AI SDK that captures inference as an append-only log. It wraps the model in middleware, automatically logs every inference call to structured JSONL in your own S3 bucket, chains entries with SHA-256 hashes for tamper detection, enforces a 180-day retention floor, and provides a CLI to reconstruct a decision and verify integrity. There is also a coverage command that flags likely gaps (in practice omissions are a bigger risk than edits). The library is deliberately simple: TS, targeting Vercel AI SDK middleware, S3 or local fs, linear hash chaining. It also works with Mastra (agentic framework), and I am happy to expand its integrations via PRs. Blog post with link to repo: https://ift.tt/X2v3YSm I'd value feedback, thoughts, and any critique.
Monday, March 2, 2026
Sunday, March 1, 2026
Saturday, February 28, 2026
New top story on Hacker News: Show HN: Tomoshibi – A writing app where your words fade by firelight
Show HN: Tomoshibi – A writing app where your words fade by firelight
11 by hakumei | 5 comments on Hacker News.
I spent ten years trying to write a novel. Every time I sat down, I'd write a sentence, decide it wasn't good enough, and rewrite it. The problem wasn't discipline — it was that I could always see what I'd written and go back to change it. I tried other approaches. Apps that delete your words when you stop typing — they fight fear with fear. That just made me panic. I wanted the opposite: not punishment, but permission. "Tomoshibi" is Japanese for a small light in the dark — just enough to see what's in front of you. You write on a dark screen. Older lines fade, but not when you hit return. They fade when you start writing again. If you pause, they wait. You can edit the current line and one line back — enough to fix a typo, not enough to spiral. The one-line-back rule also catches my own practical issue: Japanese IME often fires an accidental newline on kanji confirmation. Everything is saved. There's a separate reader view for going back through what you've written. Tomoshibi is for writing over months, not just one session. When you come back, your last sentence appears as an epigraph — as if it always belonged there. No account, no server, no build step. Your writing stays in your browser's local storage — export anytime as .txt. Vanilla HTML/CSS/ES modules. Try it in your browser. A native Mac app (built with Tauri) with file system integration is coming to the store. I've been writing on it for two months. https://ift.tt/Cx54l1w
11 by hakumei | 5 comments on Hacker News.
I spent ten years trying to write a novel. Every time I sat down, I'd write a sentence, decide it wasn't good enough, and rewrite it. The problem wasn't discipline — it was that I could always see what I'd written and go back to change it. I tried other approaches. Apps that delete your words when you stop typing — they fight fear with fear. That just made me panic. I wanted the opposite: not punishment, but permission. "Tomoshibi" is Japanese for a small light in the dark — just enough to see what's in front of you. You write on a dark screen. Older lines fade, but not when you hit return. They fade when you start writing again. If you pause, they wait. You can edit the current line and one line back — enough to fix a typo, not enough to spiral. The one-line-back rule also catches my own practical issue: Japanese IME often fires an accidental newline on kanji confirmation. Everything is saved. There's a separate reader view for going back through what you've written. Tomoshibi is for writing over months, not just one session. When you come back, your last sentence appears as an epigraph — as if it always belonged there. No account, no server, no build step. Your writing stays in your browser's local storage — export anytime as .txt. Vanilla HTML/CSS/ES modules. Try it in your browser. A native Mac app (built with Tauri) with file system integration is coming to the store. I've been writing on it for two months. https://ift.tt/Cx54l1w
Friday, February 27, 2026
New top story on Hacker News: Show HN: Unfudged – version control without commits
Show HN: Unfudged – version control without commits
8 by cyrusradfar | 4 comments on Hacker News.
I built unf after I pasted a prompt into the wrong agent terminal and it overwrote hours of hand-edits across a handful of files. Git couldn't help because I hadn't finished/committed my in progress work. I wanted something that recorded every save automatically so I could rewind to any point in time. I wanted to make it difficult for an agent to permanently screw anything up, even with an errant rm -rf unf is a background daemon that watches directories you choose (via CLI) and snapshots every text file on save. It stores file contents in an object store, tracks metadata in SQLite, and gives you a CLI to query and restore any version. The install includes a UI, as well to explore the history through time. The tool skips binaries and respects `.gitignore` if one exists. The interface borrows from git so it should feel familiar: unf log , unf diff , unf restore . I say "UN-EF" vs U.N.F, but that's for y'all to decide: I started by calling the project Unfucked and got unfucked.ai, which if you know me and the messes I get myself into, is a fitting purchase. The CLI command is `unf` and the Tauri desktop app is called "Unfudged" — the clean version. Didn’t want to force folks to have it in their apps, windows headers, etc. You can rag on me for my dad vibes. How it works: https://ift.tt/bBxI5vV (summary below) The daemon uses FSEvents on macOS and inotify on Linux. When a file changes, `unf` hashes the content with BLAKE3 and checks whether that hash already exists in the object store — if it does, it just records a new metadata entry pointing to the existing blob. If not, it writes the blob and records the entry. Each snapshot is a row in SQLite. Restores read the blob back from the object store and overwrite the file, after taking a safety snapshot of the current state first (so restoring is itself reversible). There are two processes. The core daemon does the real work of managing FSEvents/inotify subscriptions across multiple watched directories and writing snapshots. A sentinel watchdog supervises it, kept alive and aligned by launchd on macOS and systemd on Linux. If the daemon crashes, the sentinel respawns it and reconciles any drift between what you asked to watch and what's actually being watched. It was hard to build the second daemon because it felt like conceding that the core wasn't solid enough, but I didn't want to ship a tool that demanded perfection to deliver on the product promise, so the sentinel is the safety net. Fingers crossed, I haven’t seen it crash in over a week of personal usage on my Mac. But, I don't want to trigger "works for me" trauma. The part I like most: On the UI, I enjoy viewing files through time. You can select a time section and filter your projects on a histogram of activity. That has been invaluable in seeing what the agent was doing. On the CLI, the commands are composable. Everything outputs to stdout so you can pipe it into whatever you want. I use these regularly and AI agents are better with the tool than I am: # What did my config look like before we broke it? unf cat nginx.conf --at 1h | nginx -t -c /dev/stdin # Grep through a deleted file unf cat old-routes.rs --at 2d | grep "pub fn" # Count how many lines changed in the last 10 minutes unf diff --at 10m | grep '^[+-]' | wc -l # Feed the last hour of changes to an AI for review unf diff --at 1h | pbcopy # Compare two points in time with your own diff tool diff <(unf cat app.tsx --at 1h) <(unf cat app.tsx --at 5m) # Restore just the .rs files that changed in the last 5 minutes unf diff --at 5m --json | jq -r '.changes[].file' | grep '\.rs$' | xargs -I{} unf restore {} --at 5m # Watch for changes in real time watch -n5 'unf diff --at 30s' What was new for me: I came to Rust in Nov. 2025 honestly because of HN enthusiasm and some FOMO. No regrets. I enjoy the language enough that I'm now working on custom clippy lints to enforce functional programming practices. This project was also my first Apple-notarized DMG, my first Homebrew tap, and my second Tauri app (first one I've shared). Install & Usage: > brew install cyrusradfar/unf/unfudged Then unf watch in a directory. unf help covers the details (or ask your agent to coach).
8 by cyrusradfar | 4 comments on Hacker News.
I built unf after I pasted a prompt into the wrong agent terminal and it overwrote hours of hand-edits across a handful of files. Git couldn't help because I hadn't finished/committed my in progress work. I wanted something that recorded every save automatically so I could rewind to any point in time. I wanted to make it difficult for an agent to permanently screw anything up, even with an errant rm -rf unf is a background daemon that watches directories you choose (via CLI) and snapshots every text file on save. It stores file contents in an object store, tracks metadata in SQLite, and gives you a CLI to query and restore any version. The install includes a UI, as well to explore the history through time. The tool skips binaries and respects `.gitignore` if one exists. The interface borrows from git so it should feel familiar: unf log , unf diff , unf restore . I say "UN-EF" vs U.N.F, but that's for y'all to decide: I started by calling the project Unfucked and got unfucked.ai, which if you know me and the messes I get myself into, is a fitting purchase. The CLI command is `unf` and the Tauri desktop app is called "Unfudged" — the clean version. Didn’t want to force folks to have it in their apps, windows headers, etc. You can rag on me for my dad vibes. How it works: https://ift.tt/bBxI5vV (summary below) The daemon uses FSEvents on macOS and inotify on Linux. When a file changes, `unf` hashes the content with BLAKE3 and checks whether that hash already exists in the object store — if it does, it just records a new metadata entry pointing to the existing blob. If not, it writes the blob and records the entry. Each snapshot is a row in SQLite. Restores read the blob back from the object store and overwrite the file, after taking a safety snapshot of the current state first (so restoring is itself reversible). There are two processes. The core daemon does the real work of managing FSEvents/inotify subscriptions across multiple watched directories and writing snapshots. A sentinel watchdog supervises it, kept alive and aligned by launchd on macOS and systemd on Linux. If the daemon crashes, the sentinel respawns it and reconciles any drift between what you asked to watch and what's actually being watched. It was hard to build the second daemon because it felt like conceding that the core wasn't solid enough, but I didn't want to ship a tool that demanded perfection to deliver on the product promise, so the sentinel is the safety net. Fingers crossed, I haven’t seen it crash in over a week of personal usage on my Mac. But, I don't want to trigger "works for me" trauma. The part I like most: On the UI, I enjoy viewing files through time. You can select a time section and filter your projects on a histogram of activity. That has been invaluable in seeing what the agent was doing. On the CLI, the commands are composable. Everything outputs to stdout so you can pipe it into whatever you want. I use these regularly and AI agents are better with the tool than I am: # What did my config look like before we broke it? unf cat nginx.conf --at 1h | nginx -t -c /dev/stdin # Grep through a deleted file unf cat old-routes.rs --at 2d | grep "pub fn" # Count how many lines changed in the last 10 minutes unf diff --at 10m | grep '^[+-]' | wc -l # Feed the last hour of changes to an AI for review unf diff --at 1h | pbcopy # Compare two points in time with your own diff tool diff <(unf cat app.tsx --at 1h) <(unf cat app.tsx --at 5m) # Restore just the .rs files that changed in the last 5 minutes unf diff --at 5m --json | jq -r '.changes[].file' | grep '\.rs$' | xargs -I{} unf restore {} --at 5m # Watch for changes in real time watch -n5 'unf diff --at 30s' What was new for me: I came to Rust in Nov. 2025 honestly because of HN enthusiasm and some FOMO. No regrets. I enjoy the language enough that I'm now working on custom clippy lints to enforce functional programming practices. This project was also my first Apple-notarized DMG, my first Homebrew tap, and my second Tauri app (first one I've shared). Install & Usage: > brew install cyrusradfar/unf/unfudged Then unf watch in a directory. unf help covers the details (or ask your agent to coach).
Thursday, February 26, 2026
Wednesday, February 25, 2026
New top story on Hacker News: Large-Scale Online Deanonymization with LLMs
Large-Scale Online Deanonymization with LLMs
48 by DalasNoin | 71 comments on Hacker News.
Pdf: https://ift.tt/Y2ae3Js (via https://ift.tt/Rl9XOGQ )
48 by DalasNoin | 71 comments on Hacker News.
Pdf: https://ift.tt/Y2ae3Js (via https://ift.tt/Rl9XOGQ )
Tuesday, February 24, 2026
Monday, February 23, 2026
Sunday, February 22, 2026
Saturday, February 21, 2026
New top story on Hacker News: Claws are now a new layer on top of LLM agents
Claws are now a new layer on top of LLM agents
37 by Cyphase | 387 comments on Hacker News.
https://ift.tt/wGPeM5K
37 by Cyphase | 387 comments on Hacker News.
https://ift.tt/wGPeM5K
Friday, February 20, 2026
Thursday, February 19, 2026
Wednesday, February 18, 2026
Tuesday, February 17, 2026
New top story on Hacker News: Show HN: I taught LLMs to play Magic: The Gathering against each other
Show HN: I taught LLMs to play Magic: The Gathering against each other
33 by GregorStocks | 19 comments on Hacker News.
I've been teaching LLMs to play Magic: The Gathering recently, via MCP tools hooked up to the open-source XMage codebase. It's still pretty buggy and I think there's significant room for existing models to get better at it via tooling improvements, but it pretty much works today. The ratings for expensive frontier models are artificially low right now because I've been focusing on cheaper models until I work out the bugs, so they don't have a lot of games in the system.
33 by GregorStocks | 19 comments on Hacker News.
I've been teaching LLMs to play Magic: The Gathering recently, via MCP tools hooked up to the open-source XMage codebase. It's still pretty buggy and I think there's significant room for existing models to get better at it via tooling improvements, but it pretty much works today. The ratings for expensive frontier models are artificially low right now because I've been focusing on cheaper models until I work out the bugs, so they don't have a lot of games in the system.
Monday, February 16, 2026
New top story on Hacker News: Show HN: Maths, CS and AI Compendium
Show HN: Maths, CS and AI Compendium
12 by HenryNdubuaku | 1 comments on Hacker News.
Hey HN, I don’t know who else has the same issue, but: Textbooks often bury good ideas in dense notation, skip the intuition, assume you already know half the material, and get outdated in fast-moving fields like AI. Over the past 7 years of my AI/ML experience, I filled notebooks with intuition-first, real-world context, no hand-waving explanations of maths, computing and AI concepts. In 2024, a few friends used these notes to prep for interviews at DeepMind, OpenAI, Nvidia etc. They all got in and currently perform well in their roles. So I'm sharing. This is an open & unconventional textbook covering maths, computing, and artificial intelligence from the ground up. For curious practitioners seeking deeper understanding, not just survive an exam/interview. To ambitious students, an early careers or experts in adjacent fields looking to become cracked AI research engineers or progress to PhD, dig in and let me know your thoughts.
12 by HenryNdubuaku | 1 comments on Hacker News.
Hey HN, I don’t know who else has the same issue, but: Textbooks often bury good ideas in dense notation, skip the intuition, assume you already know half the material, and get outdated in fast-moving fields like AI. Over the past 7 years of my AI/ML experience, I filled notebooks with intuition-first, real-world context, no hand-waving explanations of maths, computing and AI concepts. In 2024, a few friends used these notes to prep for interviews at DeepMind, OpenAI, Nvidia etc. They all got in and currently perform well in their roles. So I'm sharing. This is an open & unconventional textbook covering maths, computing, and artificial intelligence from the ground up. For curious practitioners seeking deeper understanding, not just survive an exam/interview. To ambitious students, an early careers or experts in adjacent fields looking to become cracked AI research engineers or progress to PhD, dig in and let me know your thoughts.
Sunday, February 15, 2026
Saturday, February 14, 2026
Friday, February 13, 2026
New top story on Hacker News: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills
Show HN: Moltis – AI assistant with memory, tools, and self-extending skills
12 by fabienpenso | 2 comments on Hacker News.
Hey HN. I'm Fabien, principal engineer, 25 years shipping production systems (Ruby, Swift, now Rust). I built Moltis because I wanted an AI assistant I could run myself, trust end to end, and make extensible in the Rust way using traits and the type system. It shares some ideas with OpenClaw (same memory approach, Pi-inspired self-extension) but is Rust-native from the ground up. The agent can create its own skills at runtime. Moltis is one Rust binary, 150k lines, ~60MB, web UI included. No Node, no Python, no runtime deps. Multi-provider LLM routing (OpenAI, local GGUF/MLX, Hugging Face), sandboxed execution (Docker/Podman/Apple Containers), hybrid vector + full-text memory, MCP tool servers with auto-restart, and multi-channel (web, Telegram, API) with shared context. MIT licensed. No telemetry phoning home, but full observability built in (OpenTelemetry, Prometheus). I've included 1-click deploys on DigitalOcean and Fly.io, but since a Docker image is provided you can easily run it on your own servers as well. I've written before about owning your content ( https://ift.tt/JsFUCj0 ) and owning your email ( https://ift.tt/suJipMO ). Same logic here: if something touches your files, credentials, and daily workflow, you should be able to inspect it, audit it, and fork it if the project changes direction. It's alpha. I use it daily and I'm shipping because it's useful, not because it's done. Longer architecture deep-dive: https://ift.tt/go689vA... Happy to discuss the Rust architecture, security model, or local LLM setup. Would love feedback.
12 by fabienpenso | 2 comments on Hacker News.
Hey HN. I'm Fabien, principal engineer, 25 years shipping production systems (Ruby, Swift, now Rust). I built Moltis because I wanted an AI assistant I could run myself, trust end to end, and make extensible in the Rust way using traits and the type system. It shares some ideas with OpenClaw (same memory approach, Pi-inspired self-extension) but is Rust-native from the ground up. The agent can create its own skills at runtime. Moltis is one Rust binary, 150k lines, ~60MB, web UI included. No Node, no Python, no runtime deps. Multi-provider LLM routing (OpenAI, local GGUF/MLX, Hugging Face), sandboxed execution (Docker/Podman/Apple Containers), hybrid vector + full-text memory, MCP tool servers with auto-restart, and multi-channel (web, Telegram, API) with shared context. MIT licensed. No telemetry phoning home, but full observability built in (OpenTelemetry, Prometheus). I've included 1-click deploys on DigitalOcean and Fly.io, but since a Docker image is provided you can easily run it on your own servers as well. I've written before about owning your content ( https://ift.tt/JsFUCj0 ) and owning your email ( https://ift.tt/suJipMO ). Same logic here: if something touches your files, credentials, and daily workflow, you should be able to inspect it, audit it, and fork it if the project changes direction. It's alpha. I use it daily and I'm shipping because it's useful, not because it's done. Longer architecture deep-dive: https://ift.tt/go689vA... Happy to discuss the Rust architecture, security model, or local LLM setup. Would love feedback.
New top story on Hacker News: Dario Amodei – "We are near the end of the exponential"
Dario Amodei – "We are near the end of the exponential"
31 by danielmorozoff | 35 comments on Hacker News.
31 by danielmorozoff | 35 comments on Hacker News.
Thursday, February 12, 2026
New top story on Hacker News: Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL
Show HN: Pgclaw – A "Clawdbot" in every row with 400 lines of Postgres SQL
11 by calebhwin | 7 comments on Hacker News.
Hi HN, Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row". Things you could build with this: * Your own agent orchestrator * A personal assistant with time travel * (more things I can't think of yet) Not quite there yet but thought I'd share it in its current state.
11 by calebhwin | 7 comments on Hacker News.
Hi HN, Been hacking on a simple way to run agents entirely inside of a Postgres database, "an agent per row". Things you could build with this: * Your own agent orchestrator * A personal assistant with time travel * (more things I can't think of yet) Not quite there yet but thought I'd share it in its current state.
Wednesday, February 11, 2026
Tuesday, February 10, 2026
Monday, February 9, 2026
New top story on Hacker News: Discord will require a face scan or ID for full access next month
Discord will require a face scan or ID for full access next month
164 by x01 | 209 comments on Hacker News.
https://ift.tt/bT5NEJP... https://ift.tt/SXwWAdp...
164 by x01 | 209 comments on Hacker News.
https://ift.tt/bT5NEJP... https://ift.tt/SXwWAdp...
Sunday, February 8, 2026
Saturday, February 7, 2026
Friday, February 6, 2026
New top story on Hacker News: Show HN: I spent 4 years building a UI design tool with only the features I use
Show HN: I spent 4 years building a UI design tool with only the features I use
2 by vecti | 0 comments on Hacker News.
Hello everyone! I'm a solo developer who's been doing UI/UX work since 2007. Over the years, I watched design tools evolve from lightweight products into bloated feature-heavy platforms. I kept finding myself using a small amount of the features while the rest just mostly got in the way. So a few years ago I set out to build a design tool just like I wanted. So I built Vecti with what I actually need: pixel-perfect grid snapping, a performant canvas renderer, shared asset libraries, and export/presentation features. No collaborative whiteboarding. No plugin ecosystem. No enterprise features. Just the design loop. Four years later, I can proudly show it off. Built and hosted in the EU with European privacy regulations. Free tier available (no credit card, one editor forever). On privacy: I use some basic analytics (page views, referrers) but zero tracking inside the app itself. No session recordings, no behavior analytics, no third-party scripts beyond the essentials. If you're a solo designer or small team who wants a tool that stays out of your way, I'd genuinely appreciate your feedback: https://vecti.com Happy to answer questions about the tech stack, architecture decisions, why certain features didn't make the cut, or what's next.
2 by vecti | 0 comments on Hacker News.
Hello everyone! I'm a solo developer who's been doing UI/UX work since 2007. Over the years, I watched design tools evolve from lightweight products into bloated feature-heavy platforms. I kept finding myself using a small amount of the features while the rest just mostly got in the way. So a few years ago I set out to build a design tool just like I wanted. So I built Vecti with what I actually need: pixel-perfect grid snapping, a performant canvas renderer, shared asset libraries, and export/presentation features. No collaborative whiteboarding. No plugin ecosystem. No enterprise features. Just the design loop. Four years later, I can proudly show it off. Built and hosted in the EU with European privacy regulations. Free tier available (no credit card, one editor forever). On privacy: I use some basic analytics (page views, referrers) but zero tracking inside the app itself. No session recordings, no behavior analytics, no third-party scripts beyond the essentials. If you're a solo designer or small team who wants a tool that stays out of your way, I'd genuinely appreciate your feedback: https://vecti.com Happy to answer questions about the tech stack, architecture decisions, why certain features didn't make the cut, or what's next.
New top story on Hacker News: Show HN: Daily-updated database of malicious browser extensions
Show HN: Daily-updated database of malicious browser extensions
4 by toborrm9 | 2 comments on Hacker News.
Hey HN, I built an automated system that tracks malicious Chrome/Edge extensions daily. The database updates automatically by monitoring chrome-stats for removed extensions and scanning security blogs. Currently tracking 1000+ known malicious extensions with extension IDs, names, and dates. I'm working on detection tools (GUI + CLI) to scan locally installed extensions against this database, but wanted to share the raw data first since maintained threat intelligence lists like this are hard to find. The automation runs 24/7 and pushes updates to GitHub. Free to use for research, integration into security tools, or whatever you need. Happy to answer questions about the scraping approach or data collection methods.
4 by toborrm9 | 2 comments on Hacker News.
Hey HN, I built an automated system that tracks malicious Chrome/Edge extensions daily. The database updates automatically by monitoring chrome-stats for removed extensions and scanning security blogs. Currently tracking 1000+ known malicious extensions with extension IDs, names, and dates. I'm working on detection tools (GUI + CLI) to scan locally installed extensions against this database, but wanted to share the raw data first since maintained threat intelligence lists like this are hard to find. The automation runs 24/7 and pushes updates to GitHub. Free to use for research, integration into security tools, or whatever you need. Happy to answer questions about the scraping approach or data collection methods.
Thursday, February 5, 2026
Wednesday, February 4, 2026
Tuesday, February 3, 2026
New top story on Hacker News: Show HN: PII-Shield – Log Sanitization Sidecar with JSON Integrity (Go, Entropy)
Show HN: PII-Shield – Log Sanitization Sidecar with JSON Integrity (Go, Entropy)
4 by aragoss | 0 comments on Hacker News.
What PII-Shield does: It's a K8s sidecar (or CLI tool) that pipes application logs, detects secrets using Shannon entropy (catching unknown keys like "sk-live-..." without predefined patterns), and redacts them deterministically using HMAC. Why deterministic? So that "pass123" always hashes to the same "[HIDDEN:a1b2c]", allowing QA/Devs to correlate errors without seeing the raw data. Key features: 1. JSON Integrity: It parses JSON, sanitizes values, and rebuilds it. It guarantees valid JSON output for your SIEM (ELK/Datadog). 2. Entropy Detection: Uses context-aware entropy analysis to catch high-randomness strings. 3. Fail-Open: Designed as a transparent pipe wrapper to preserve app uptime. The project is open-source (Apache 2.0). Repo: https://ift.tt/gzwqx75 Docs: https://pii-shield.gitbook.io/docs/ I'd love your feedback on the entropy/threshold logic!
4 by aragoss | 0 comments on Hacker News.
What PII-Shield does: It's a K8s sidecar (or CLI tool) that pipes application logs, detects secrets using Shannon entropy (catching unknown keys like "sk-live-..." without predefined patterns), and redacts them deterministically using HMAC. Why deterministic? So that "pass123" always hashes to the same "[HIDDEN:a1b2c]", allowing QA/Devs to correlate errors without seeing the raw data. Key features: 1. JSON Integrity: It parses JSON, sanitizes values, and rebuilds it. It guarantees valid JSON output for your SIEM (ELK/Datadog). 2. Entropy Detection: Uses context-aware entropy analysis to catch high-randomness strings. 3. Fail-Open: Designed as a transparent pipe wrapper to preserve app uptime. The project is open-source (Apache 2.0). Repo: https://ift.tt/gzwqx75 Docs: https://pii-shield.gitbook.io/docs/ I'd love your feedback on the entropy/threshold logic!
Monday, February 2, 2026
New top story on Hacker News: Ask HN: Who wants to be hired? (February 2026)
Ask HN: Who wants to be hired? (February 2026)
35 by whoishiring | 82 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. There's a site for searching these posts at https://ift.tt/tO1Covp .
35 by whoishiring | 82 comments on Hacker News.
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. There's a site for searching these posts at https://ift.tt/tO1Covp .
Sunday, February 1, 2026
New top story on Hacker News: Show HN: Voiden – an offline, Git-native API tool built around Markdown
Show HN: Voiden – an offline, Git-native API tool built around Markdown
5 by dhruv3006 | 1 comments on Hacker News.
Hi HN, We have open-sourced Voiden. Most API tools are built like platforms. They are heavy because they optimize for accounts, sync, and abstraction - not for simple, local API work. Voiden treats API tooling as files. It’s an offline-first, Git-native API tool built on Markdown, where specs, tests, and docs live together as executable Markdown in your repo. Git is the source of truth. No cloud. No syncing. No accounts. No telemetry.Just Markdown, Git, hotkeys, and your damn specs. Voiden is extensible via plugins (including gRPC and WSS). Repo: https://ift.tt/3RH80LI Download Voiden here : https://ift.tt/o0M9HA1 We'd love feedback from folks tired of overcomplicated and bloated API tooling !
5 by dhruv3006 | 1 comments on Hacker News.
Hi HN, We have open-sourced Voiden. Most API tools are built like platforms. They are heavy because they optimize for accounts, sync, and abstraction - not for simple, local API work. Voiden treats API tooling as files. It’s an offline-first, Git-native API tool built on Markdown, where specs, tests, and docs live together as executable Markdown in your repo. Git is the source of truth. No cloud. No syncing. No accounts. No telemetry.Just Markdown, Git, hotkeys, and your damn specs. Voiden is extensible via plugins (including gRPC and WSS). Repo: https://ift.tt/3RH80LI Download Voiden here : https://ift.tt/o0M9HA1 We'd love feedback from folks tired of overcomplicated and bloated API tooling !
Saturday, January 31, 2026
Friday, January 30, 2026
Thursday, January 29, 2026
Wednesday, January 28, 2026
Tuesday, January 27, 2026
New top story on Hacker News: A few random notes from Claude coding quite a bit last few weeks
A few random notes from Claude coding quite a bit last few weeks
21 by bigwheels | 18 comments on Hacker News.
https://ift.tt/lqOLIdx
21 by bigwheels | 18 comments on Hacker News.
https://ift.tt/lqOLIdx
Monday, January 26, 2026
Sunday, January 25, 2026
Saturday, January 24, 2026
New top story on Hacker News: Ask HN: Gmail spam filtering suddenly marking everything as spam?
Ask HN: Gmail spam filtering suddenly marking everything as spam?
10 by goopthink | 36 comments on Hacker News.
Almost all transactional emails are being marked as suspicious even when their SPF/DKIM records are fine and they’ve been whitelisted before. Did Google break something in gmail/spam filtering?
10 by goopthink | 36 comments on Hacker News.
Almost all transactional emails are being marked as suspicious even when their SPF/DKIM records are fine and they’ve been whitelisted before. Did Google break something in gmail/spam filtering?
Friday, January 23, 2026
Thursday, January 22, 2026
New top story on Hacker News: Show HN: Synesthesia, make noise music with a colorpicker
Show HN: Synesthesia, make noise music with a colorpicker
3 by tevans3 | 1 comments on Hacker News.
This is a (silly, little) app which lets you make noise music using a color picker as an instrument. When you click on a specific point in the color picker, a bit of JavaScript maps the binary representation of the clicked-on color's hex-code to a "chord" in the 24 tone-equal-temperament scale. That chord is then played back using a throttled audio generation method which was implemented via Tone.js. NOTE! Turn the volume way down before using the site. It is noise music. :)
3 by tevans3 | 1 comments on Hacker News.
This is a (silly, little) app which lets you make noise music using a color picker as an instrument. When you click on a specific point in the color picker, a bit of JavaScript maps the binary representation of the clicked-on color's hex-code to a "chord" in the 24 tone-equal-temperament scale. That chord is then played back using a throttled audio generation method which was implemented via Tone.js. NOTE! Turn the volume way down before using the site. It is noise music. :)
Wednesday, January 21, 2026
Tuesday, January 20, 2026
Monday, January 19, 2026
New top story on Hacker News: Bypassing Gemma and Qwen safety with raw strings
Bypassing Gemma and Qwen safety with raw strings
12 by teendifferent | 0 comments on Hacker News.
OP here. I spent the weekend red-teaming small-scale open weights models (Qwen2.5-1.5B, Qwen3-1.7B, Gemma-3-1b-it, and SmolLM2-1.7B). I found a consistent vulnerability across all of them: Safety alignment relies almost entirely on the presence of the chat template. When I stripped the <|im_start|> / instruction tokens and passed raw strings: Gemma-3 refusal rates dropped from 100% → 60%. Qwen3 refusal rates dropped from 80% → 40%. SmolLM2 showed 0% refusal (pure obedience). Qualitative failures were stark: models that previously refused to generate explosives tutorials or explicit fiction immediately complied when the "Assistant" persona wasn't triggered by the template. It seems we are treating client-side string formatting as a load-bearing safety wall. Full logs, the apply_chat_template ablation code, and heatmaps are in the post. Read the full analysis: https://ift.tt/8huZiBj...
12 by teendifferent | 0 comments on Hacker News.
OP here. I spent the weekend red-teaming small-scale open weights models (Qwen2.5-1.5B, Qwen3-1.7B, Gemma-3-1b-it, and SmolLM2-1.7B). I found a consistent vulnerability across all of them: Safety alignment relies almost entirely on the presence of the chat template. When I stripped the <|im_start|> / instruction tokens and passed raw strings: Gemma-3 refusal rates dropped from 100% → 60%. Qwen3 refusal rates dropped from 80% → 40%. SmolLM2 showed 0% refusal (pure obedience). Qualitative failures were stark: models that previously refused to generate explosives tutorials or explicit fiction immediately complied when the "Assistant" persona wasn't triggered by the template. It seems we are treating client-side string formatting as a load-bearing safety wall. Full logs, the apply_chat_template ablation code, and heatmaps are in the post. Read the full analysis: https://ift.tt/8huZiBj...
Sunday, January 18, 2026
Saturday, January 17, 2026
Friday, January 16, 2026
New top story on Hacker News: Show HN: Aventos – An experiment in cheap AI SEO
Show HN: Aventos – An experiment in cheap AI SEO
3 by JimsonYang | 0 comments on Hacker News.
Hi HN, we built Aventos- a cheap way to track company mentions in LLMs. Aventos is an experiment we're doing after spending ~6 weeks working on various projects in the AI search / GEO / AEO space. One thing that surprised us is how most tools in this category work. Traditionally, they simulate ChatGPT or Perplexity queries by attempting to reverse engineer the search process. Over the past year, many have shifted to scraping live ChatGPT results instead, since those are signficantly cheaper and reflect more real outputs. Building and maintaining scrapers is tedious and fragile, so recently a number of SaaS products have emerged that effectively wrap a small number of third-party ChatGPT/Perplexity/Google AIO/etc scraping APIs. What felt odd to us is that many of these still tools charge $70–$200+ per month, despite largely being wrappers around the same underlying data providers. So we wanted to test a simple idea: if the core cost is just API usage and commodity infrastructure and software costs are lower because of AI, can we be a successful startup if we price near our costs? What we have so far: 1. Analytics similar to other tools (tracking AI citations, AI search results, and competitor mentions) 2. Content creation features (early and still being improved) We’d love feedback- especially from a non-marketing perspective on: * bugs * confusing terminology or tabs * anything that feels hand-wavy or misleading There’s a demo account available if you want to poke around: username: divit.endal4@gmail.com password: password Happy to answer questions about what other things we've built in the space, how these tools work, etc.
3 by JimsonYang | 0 comments on Hacker News.
Hi HN, we built Aventos- a cheap way to track company mentions in LLMs. Aventos is an experiment we're doing after spending ~6 weeks working on various projects in the AI search / GEO / AEO space. One thing that surprised us is how most tools in this category work. Traditionally, they simulate ChatGPT or Perplexity queries by attempting to reverse engineer the search process. Over the past year, many have shifted to scraping live ChatGPT results instead, since those are signficantly cheaper and reflect more real outputs. Building and maintaining scrapers is tedious and fragile, so recently a number of SaaS products have emerged that effectively wrap a small number of third-party ChatGPT/Perplexity/Google AIO/etc scraping APIs. What felt odd to us is that many of these still tools charge $70–$200+ per month, despite largely being wrappers around the same underlying data providers. So we wanted to test a simple idea: if the core cost is just API usage and commodity infrastructure and software costs are lower because of AI, can we be a successful startup if we price near our costs? What we have so far: 1. Analytics similar to other tools (tracking AI citations, AI search results, and competitor mentions) 2. Content creation features (early and still being improved) We’d love feedback- especially from a non-marketing perspective on: * bugs * confusing terminology or tabs * anything that feels hand-wavy or misleading There’s a demo account available if you want to poke around: username: divit.endal4@gmail.com password: password Happy to answer questions about what other things we've built in the space, how these tools work, etc.
New top story on Hacker News: The Alignment Game
The Alignment Game
4 by dmvaldman | 0 comments on Hacker News.
https://docs.google.com/spreadsheets/d/1BYh9ZtEv4k7xoSXmtf1q...
4 by dmvaldman | 0 comments on Hacker News.
https://docs.google.com/spreadsheets/d/1BYh9ZtEv4k7xoSXmtf1q...
New top story on Hacker News: Show HN: 1Code – Open-source Cursor-like UI for Claude Code
Show HN: 1Code – Open-source Cursor-like UI for Claude Code
15 by Bunas | 4 comments on Hacker News.
Hi, we're Sergey and Serafim. We've been building dev tools at 21st.dev and recently open-sourced 1Code ( https://1code.dev ), a local UI for Claude Code. Here's a video of the product: https://www.youtube.com/watch?v=Sgk9Z-nAjC0 Claude Code has been our go-to for 4 months. When Opus 4.5 dropped, parallel agents stopped needing so much babysitting. We started trusting it with more: building features end to end, adding tests, refactors. Stuff you'd normally hand off to a developer. We started running 3-4 at once. Then the CLI became annoying: too many terminals, hard to track what's where, diffs scattered everywhere. So we built 1Code.dev, an app to run your Claude Code agents in parallel that works on Mac and Web. On Mac: run locally, with or without worktrees. On Web: run in remote sandboxes with live previews of your app, mobile included, so you can check on agents from anywhere. Running multiple Claude Codes in parallel dramatically sped up how we build features. What’s next: Bug bot for identifying issues based on your changes; QA Agent, that checks that new features don't break anything; Adding OpenCode, Codex, other models and coding agents. API for starting Claude Codes in remote sandboxes. Try it out! We're open-source, so you can just bun build it. If you want something hosted, Pro ($20/mo) gives you web with live browser previews hosted on remote sandboxes. We’re also working on API access for running Claude Code sessions programmatically. We'd love to hear your feedback!
15 by Bunas | 4 comments on Hacker News.
Hi, we're Sergey and Serafim. We've been building dev tools at 21st.dev and recently open-sourced 1Code ( https://1code.dev ), a local UI for Claude Code. Here's a video of the product: https://www.youtube.com/watch?v=Sgk9Z-nAjC0 Claude Code has been our go-to for 4 months. When Opus 4.5 dropped, parallel agents stopped needing so much babysitting. We started trusting it with more: building features end to end, adding tests, refactors. Stuff you'd normally hand off to a developer. We started running 3-4 at once. Then the CLI became annoying: too many terminals, hard to track what's where, diffs scattered everywhere. So we built 1Code.dev, an app to run your Claude Code agents in parallel that works on Mac and Web. On Mac: run locally, with or without worktrees. On Web: run in remote sandboxes with live previews of your app, mobile included, so you can check on agents from anywhere. Running multiple Claude Codes in parallel dramatically sped up how we build features. What’s next: Bug bot for identifying issues based on your changes; QA Agent, that checks that new features don't break anything; Adding OpenCode, Codex, other models and coding agents. API for starting Claude Codes in remote sandboxes. Try it out! We're open-source, so you can just bun build it. If you want something hosted, Pro ($20/mo) gives you web with live browser previews hosted on remote sandboxes. We’re also working on API access for running Claude Code sessions programmatically. We'd love to hear your feedback!
Thursday, January 15, 2026
New top story on Hacker News: Show HN: ContextFort – Visibility and controls for browser agents
Show HN: ContextFort – Visibility and controls for browser agents
7 by ashwinr2002 | 1 comments on Hacker News.
Hey HN! I’m Ashwin, co-founder of ContextFort ( https://contextfort.ai/ ). We provide visibility and controls for AI browser agents like Claude in Chrome through an open-source browser extension. Browser agents are AI copilots that can autonomously navigate and take actions in your browser. They show up as standalone browsers (Comet, Atlas) or Chrome extensions (Claude). They’re especially useful in sites where search/API connectors don’t work well, like searching through Google Groups threads for a bug fix or pulling invoices from BILL.com. Anthropic released Claude CoWork yesterday, and in their launch video, they showcased their browser-use chromium extension: https://www.youtube.com/watch?v=UAmKyyZ-b9E But enterprise adoption is slow because of indirect prompt injection risks, about which Simon Willison has written in great detail in his blogs: https://ift.tt/SREVDQO... . And before security teams can decide on guardrails, they need to know how employees are using browser agents to understand where the risks are. So, we reverse-engineered how the Claude in Chrome extension works and built a visibility layer that tracks agent sessions end-to-end. It detects when an AI agent takes control of the browser and records which pages it visited during a session and what it does on each page (what was clicked and where text was input). On top of that, we’ve also added simple controls for security teams to act on based on what the visibility layer captures: (1) Block specific actions on specific pages (e.g., prevent the agent from clicking “Submit” on email) (2) Block risky cross-site flows in a single session (e.g., block navigation to Atlassian after interacting with StackOverflow), or apply a stricter policy and block bringing any external context to Atlassian entirely. We demo all the above features here in this 2-minute YouTube video: https://www.youtube.com/watch?v=1YtEGVZKMeo You can try our browser extension here: https://ift.tt/XwepOd1 Thrilled to share this with you and hear your comments!
7 by ashwinr2002 | 1 comments on Hacker News.
Hey HN! I’m Ashwin, co-founder of ContextFort ( https://contextfort.ai/ ). We provide visibility and controls for AI browser agents like Claude in Chrome through an open-source browser extension. Browser agents are AI copilots that can autonomously navigate and take actions in your browser. They show up as standalone browsers (Comet, Atlas) or Chrome extensions (Claude). They’re especially useful in sites where search/API connectors don’t work well, like searching through Google Groups threads for a bug fix or pulling invoices from BILL.com. Anthropic released Claude CoWork yesterday, and in their launch video, they showcased their browser-use chromium extension: https://www.youtube.com/watch?v=UAmKyyZ-b9E But enterprise adoption is slow because of indirect prompt injection risks, about which Simon Willison has written in great detail in his blogs: https://ift.tt/SREVDQO... . And before security teams can decide on guardrails, they need to know how employees are using browser agents to understand where the risks are. So, we reverse-engineered how the Claude in Chrome extension works and built a visibility layer that tracks agent sessions end-to-end. It detects when an AI agent takes control of the browser and records which pages it visited during a session and what it does on each page (what was clicked and where text was input). On top of that, we’ve also added simple controls for security teams to act on based on what the visibility layer captures: (1) Block specific actions on specific pages (e.g., prevent the agent from clicking “Submit” on email) (2) Block risky cross-site flows in a single session (e.g., block navigation to Atlassian after interacting with StackOverflow), or apply a stricter policy and block bringing any external context to Atlassian entirely. We demo all the above features here in this 2-minute YouTube video: https://www.youtube.com/watch?v=1YtEGVZKMeo You can try our browser extension here: https://ift.tt/XwepOd1 Thrilled to share this with you and hear your comments!
New top story on Hacker News: Inside The Internet Archive's Infrastructure
Inside The Internet Archive's Infrastructure
8 by dvrp | 1 comments on Hacker News.
https://ift.tt/MRcAV9g
8 by dvrp | 1 comments on Hacker News.
https://ift.tt/MRcAV9g
New top story on Hacker News: Show HN: OpenWork – an open-source alternative to Claude Cowork
Show HN: OpenWork – an open-source alternative to Claude Cowork
7 by ben_talent | 1 comments on Hacker News.
hi hn, i built openwork, an open-source, local-first system inspired by claude cowork. it’s a native desktop app that runs on top of opencode (opencode.ai). it’s basically an alternative gui for opencode, which (at least until now) has been more focused on technical folks. the original seed for openwork was simple: i have a home server, and i wanted my wife and i to be able to run privileged workflows. things like controlling home assistant, or deploying custom web apps (e.g. our customs recipe app recipes.benjaminshafii.com), legal torrents, without living in a terminal. our initial setup was running the opencode web server directly and sharing credentials to it. that worked, but i found the web ui unreliable and very unfriendly for non-technical users. the goal with openwork is to bring the kind of workflows i’m used to running in the cli into a gui, while keeping a very deep extensibility mindset. ideally this grows into something closer to an obsidian-style ecosystem, but for agentic work. some core principles i had in mind: - open by design: no black boxes, no hosted lock-in. everything runs locally or on your own servers. (models don’t run locally yet, but both opencode and openwork are built with that future in mind.) - hyper extensible: skills are installable modules via a skill/package manager, using the native opencode plugin ecosystem. - non-technical by default: plans, progress, permissions, and artifacts are surfaced in the ui, not buried in logs. you can already try it: - there’s an unsigned dmg - or you can clone the repo, install deps, and if you already have opencode running it should work right away it’s very alpha, lots of rough edges. i’d love feedback on what feels the roughest or most confusing. happy to answer questions.
7 by ben_talent | 1 comments on Hacker News.
hi hn, i built openwork, an open-source, local-first system inspired by claude cowork. it’s a native desktop app that runs on top of opencode (opencode.ai). it’s basically an alternative gui for opencode, which (at least until now) has been more focused on technical folks. the original seed for openwork was simple: i have a home server, and i wanted my wife and i to be able to run privileged workflows. things like controlling home assistant, or deploying custom web apps (e.g. our customs recipe app recipes.benjaminshafii.com), legal torrents, without living in a terminal. our initial setup was running the opencode web server directly and sharing credentials to it. that worked, but i found the web ui unreliable and very unfriendly for non-technical users. the goal with openwork is to bring the kind of workflows i’m used to running in the cli into a gui, while keeping a very deep extensibility mindset. ideally this grows into something closer to an obsidian-style ecosystem, but for agentic work. some core principles i had in mind: - open by design: no black boxes, no hosted lock-in. everything runs locally or on your own servers. (models don’t run locally yet, but both opencode and openwork are built with that future in mind.) - hyper extensible: skills are installable modules via a skill/package manager, using the native opencode plugin ecosystem. - non-technical by default: plans, progress, permissions, and artifacts are surfaced in the ui, not buried in logs. you can already try it: - there’s an unsigned dmg - or you can clone the repo, install deps, and if you already have opencode running it should work right away it’s very alpha, lots of rough edges. i’d love feedback on what feels the roughest or most confusing. happy to answer questions.
Wednesday, January 14, 2026
Tuesday, January 13, 2026
New top story on Hacker News: Show HN: FastScheduler – Decorator-first Python task scheduler, async support
Show HN: FastScheduler – Decorator-first Python task scheduler, async support
7 by michielme | 2 comments on Hacker News.
Hi! I've built this because I kept reaching for Celery for simple scheduled tasks and it felt like overkill. I just needed "run this function every hour" or "daily at 9am", not distributed workers. So it's decorators for scheduling (@scheduler.every(5).minutes, @scheduler.daily.at("09:00")), state saves to JSON so jobs survive restarts, and there's an optional FastAPI dashboard if you want to see what's running. No Redis, no message broker, runs in-process with your app. Trade-off is it's single process only — if you need distributed workers, stick with Celery.
7 by michielme | 2 comments on Hacker News.
Hi! I've built this because I kept reaching for Celery for simple scheduled tasks and it felt like overkill. I just needed "run this function every hour" or "daily at 9am", not distributed workers. So it's decorators for scheduling (@scheduler.every(5).minutes, @scheduler.daily.at("09:00")), state saves to JSON so jobs survive restarts, and there's an optional FastAPI dashboard if you want to see what's running. No Redis, no message broker, runs in-process with your app. Trade-off is it's single process only — if you need distributed workers, stick with Celery.
Monday, January 12, 2026
New top story on Hacker News: Unauthenticated remote code execution in OpenCode
Unauthenticated remote code execution in OpenCode
46 by CyberShadow | 4 comments on Hacker News.
Previous versions of OpenCode started a server which allowed any website visited in a web browser to execute arbitrary commands on the local machine. Make sure you are using v1.1.10 or newer; see link for more details.
46 by CyberShadow | 4 comments on Hacker News.
Previous versions of OpenCode started a server which allowed any website visited in a web browser to execute arbitrary commands on the local machine. Make sure you are using v1.1.10 or newer; see link for more details.
Sunday, January 11, 2026
New top story on Hacker News: Ask HN: What Are You Working On? (January 2026)
Ask HN: What Are You Working On? (January 2026)
22 by david927 | 29 comments on Hacker News.
What are you working on? Any new ideas that you're thinking about?
22 by david927 | 29 comments on Hacker News.
What are you working on? Any new ideas that you're thinking about?
Saturday, January 10, 2026
New top story on Hacker News: Bichon: A lightweight, high-performance Rust email archiver with WebUI
Bichon: A lightweight, high-performance Rust email archiver with WebUI
16 by rendx | 4 comments on Hacker News.
via https://ift.tt/DYu7VQh
16 by rendx | 4 comments on Hacker News.
via https://ift.tt/DYu7VQh
Friday, January 9, 2026
Thursday, January 8, 2026
Wednesday, January 7, 2026
New top story on Hacker News: Show HN: Free and local browser tool for designing gear models for 3D printing
Show HN: Free and local browser tool for designing gear models for 3D printing
7 by neogoose | 0 comments on Hacker News.
Just build a local tool for designing gears that kinda looks and works nice
7 by neogoose | 0 comments on Hacker News.
Just build a local tool for designing gears that kinda looks and works nice