News for hackers. Stuff that matters.

A comment on Reinforcement Learning from Human Feedback. Parent comment

Re:Reinforcement Learning from Human Feedback by verdverm on Saturday February 07, 2026 @09:47AM (#46924305)
Last time I saw Nathan say something about the book, he's actively working on the next version and looking for feedback, check his socials
[ Parent | on HN ]
Re:Reinforcement Learning from Human Feedback by leggerss on Saturday February 07, 2026 @11:38AM (#46925169)
You could say he's also learning from human feedback
[ Parent | on HN ]