News for hackers. Stuff that matters.
Re:Clean up Claude 5's token vomit with a separate LLM by zachahn on Thursday August 20, 2026 @02:00PM (#49377996)
I'm not super sure if this is true (yet?). I think that these newer LLMs are trained on results (the agent got some code to run with minimal prompting), and not on text. (I think this is called RLVR.)

There are no comments on this comment yet.