http://ln.ht/_/images/favicon-4c526c32c48400028d7739cac47cd2a3.svg?vsn=dhttp://ln.ht/_/feed/llm/aiBookmarks tagged with: llm,ai2026-07-24T21:55:09.409223Zistvanbozsohttps://ln.ht/~istvanbozsohttps://simonwillison.net/2026/Jul/22/openai-cyberattack/OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened2026-07-24T09:49:58Zsebastienhttps://ln.ht/~sebastien<p>
Karpathy’s wiki but for code: distills agent sessions into knowledge that then can be reused.</p>
https://github.com/AlmanacCode/codealmanac/GitHub - AlmanacCode/codealmanac: A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas. · GitHub2026-07-21T21:08:52Zrustiebeatshttps://ln.ht/~rustiebeats<p>
I think from this blog you may misunderestimate how absolutely giddy I am about AI. I did hacking from 2007-2014, after that my whole career has been devoted to AI. I love the progress. I’m so excited for the new LLMs, self driving cars, video generation models, and coding agents. I set up a Linux box with opencode on my local GLM-5.2 last week and wow like just saying install tmux with the geohot configuration works; the Year of the Linux Desktop is finally here!</p>
https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.htmlI love LLMs, I hate hype | the singularity is nearer2026-07-13T02:12:11Zistvanbozsohttps://ln.ht/~istvanbozsohttps://mail.cyberneticforests.com/its-not-just-data-its-post-training/It's Not Just X. It's Y.2026-07-09T14:26:31Zistvanbozsohttps://ln.ht/~istvanbozsohttps://www.scattered-thoughts.net/writing/artificial-adventures/Artificial adventures2026-07-08T13:04:11Zistvanbozsohttps://ln.ht/~istvanbozsohttps://sg.hu/cikkek/tudomany/165647/az-mi-kutatasi-tanulmanyok-egyre-jobbak-es-ez-komoly-problema-a-tudosok-szamaraAz MI kutatási tanulmányok egyre jobbak, és ez komoly probléma a tudósok számára – SG.hu2026-07-08T12:42:29Ztmfnkhttps://ln.ht/~tmfnk<p>
OpenMed 1.7.0 brings multimodal de-identification, OCR, FHIR and HL7 helpers, signed audit evidence, Transformers.js browser export, 1,000 open-source healthcare LLM models, and Swift-native OpenMedKit.</p>
https://openmed.life/#OpenMed — Clinical AI that never leaves the device2026-07-08T12:36:51ZchrisSthttps://ln.ht/~chrisSthttps://news.ycombinator.com/item?id=48811644Ternlight – 7 MB embedding model that runs in browser (WASM) | Hacker News2026-07-07T16:45:15ZchrisSthttps://ln.ht/~chrisSthttps://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/Introducing TabFM: A zero-shot foundation model for tabular data2026-07-02T22:23:15Znickbhttps://ln.ht/~nickb<p>
Keep your Mac awake only while AI coding agents are working - kageroumado/adrafinil</p>
https://github.com/kageroumado/adrafinilkageroumado/adrafinil: Keep your Mac awake only while AI coding agents are working2026-06-27T23:32:31Zistvanbozsohttps://ln.ht/~istvanbozsohttps://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writingWikipedia:Signs of AI writing - Wikipedia2026-06-24T13:20:54ZchrisSthttps://ln.ht/~chrisSt<p>
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone - OpenBMB/MiniCPM-V</p>
https://github.com/openbmb/MiniCPM-VOpenBMB/MiniCPM-V: A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone2026-06-22T14:28:23Zbibi29https://ln.ht/~bibi29https://www.marble.onl/posts/cancel_claude.htmlcancel_claude2026-06-22T09:41:41ZchrisSthttps://ln.ht/~chrisSt<p>
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. - DietrichGebert/ponytail</p>
https://github.com/DietrichGebert/ponytailDietrichGebert/ponytail: Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.2026-06-20T14:41:35Ztheonlymrcathttps://ln.ht/~theonlymrcathttps://lantian.pub/en/article/fun/ai-agent-bankrupted-their-operator-scan-dn42lantian.lantian/AI Agent Bankrupted Their Operator While Trying to Scan DN422026-06-14T22:11:10Zsilashttps://ln.ht/~silas<p>
via: https://lobste.rs/s/rnmkrg/extinction_level_capitalism</p>
https://matthewbutterick.com/extinction-level-capitalism.htmlMatthew Butterick | Extinction-level capitalism2026-06-14T08:46:09Zthezipcreatorhttps://ln.ht/~thezipcreator<p>
funny read</p>
https://lantian.pub/en/article/fun/ai-agent-bankrupted-their-operator-scan-dn42lantian.lantian/AI Agent Bankrupted Their Operator While Trying to Scan DN422026-06-14T01:45:26ZchrisSthttps://ln.ht/~chrisSt<p>
QA harness built for Claude Code | E2E testing with screen recordings, console logs, network HARs, and Playwright traces - wizenheimer/canary</p>
https://github.com/wizenheimer/canarywizenheimer/canary: QA harness built for Claude Code | E2E testing with screen recordings, console logs, network HARs, and Playwright traces2026-06-09T17:38:25ZchrisSthttps://ln.ht/~chrisSthttps://github.com/soniqo/speech-swiftsoniqo/speech-swift: AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML2026-06-09T12:38:33Zisaachttps://ln.ht/~isaac<p>
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop.</p>
https://www.0xkato.xyz/how-llms-actually-work/How LLMs Actually Work2026-06-08T03:49:39Z