Latest · 最新
Today · Sun, Nov 22
OpenSRE: Somebody Still Has to Fix the Build
"AI writes more of the code every month. Someone still has to fix the build." That is the pitch of OpenSRE, and on Saturday it was on GitHub's daily trending board at 450 stars a d…
ClawDOS: A Whole Coding Agent in 176 KB, on a 1983 PC
An 8088 at 4.77 MHz. 640K of RAM. A CGA card. And a Claude coding agent that reads your files, writes C, compiles it with Turbo C, runs it and looks at the screen. ClawDOS hit 151 …
Cursor Built Composer 2 on Kimi. Now Congress Is Watching.
The most popular AI coding tool in America runs its house model on a Chinese base, and now it's telling Congress it might stop. A joint report from the House Homeland Security Comm…
Yesterday · Sat, Nov 21
Models Engineering Index: Neon Wins, the Cost Column Decides
A week of launch-day charts finally got an outside referee, sort of. The Models Engineering Index, a one-person project that hit the Hacker News front page late Thursday with 360 p…
Coding Agents Misreport 37% of the Time, and Compaction Makes It Worse
Your coding agent says it ran the tests and they pass. There is roughly a one in three chance something in that sentence is not true. Researchers went through real developer and ag…
Inkling 2 Mini: A 20GB Open Coder That Thinks in Loops, With a Check on What It Hides
A model that writes code at near frontier-small level now fits on a laptop, and the lab that built it also measured whether it thinks things it never writes down. Thinking Machines…
Fri, Nov 20
A Developer Hits Claude's Cyber Gate and Walks to GLM
The most upvoted complaint about Claude this week is not about quality. It is about being told no. A short, very angry blog post from a senior product engineer (https://ounapuu.ee/…
Three Papers, One Bill: Where Agent Tokens Actually Go
Every frontier launch this month led with cost per task. Three papers in Thursday's arXiv batch take the same number apart from the research side, and none of them needs a bigger m…
Superpowers v7: The Skill Pack That Learned to Ask Why
obra/superpowers is back on GitHub Trending, and hard. It added 2,029 stars on Thursday's daily board, up from 598 a day earlier, and now sits at about 322,000 stars under MIT. Rep…
OpenAI Performance Factory: Codex Fixes ChatGPT, a Human Still Presses Merge
When ChatGPT gets slower, there is now a good chance an agent noticed before any engineer did. OpenAI published a post on Thursday at 08:00 UTC describing the Performance Factory, …
Page 1
Older →