Claude Code Found a Linux Vulnerability Hidden for 23 Years(mtlynch.io)

10 pointsby mtlynch3 months ago2 comments

Claude Code Found a Linux Vulnerability Hidden for 23 Years

https://mtlynch.io/claude-code-found-linux-vulnerability/

2 comments

I thought maybe you can find more if you write a "special" skill for AI to think hardly.

For example, I'v implemented "Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought" into a skill and the AI becomes able to "think".

The correct rate becomes higher but the only drawback is consuming token very much.

gus_massa3 months ago

Reposted later with more luck: https://news.ycombinator.com/item?id=47633855