Karpathy’s wiki but for code: distills agent sessions into knowledge that then can be reused.

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!

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.

Keep your Mac awake only while AI coding agents are working - kageroumado/adrafinil

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone - OpenBMB/MiniCPM-V

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. - DietrichGebert/ponytail

via: https://lobste.rs/s/rnmkrg/extinction_level_capitalism

funny read

QA harness built for Claude Code | E2E testing with screen recordings, console logs, network HARs, and Playwright traces - wizenheimer/canary

A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop.