Reinforcement Learning from Human Feedback

Re:Reinforcement Learning from Human Feedback by klelatti on Saturday February 07, 2026 @08:46AM (#46923832)

Web version with links, etc:

[ Parent | on HN ]

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 ]

Re:Reinforcement Learning from Human Feedback by dang on Saturday February 07, 2026 @01:17PM (#46926123)

Thanks! We've switched to that above from https://arxiv.org/abs/2504.12501, and put the latter in the toptext.

[ Parent | on HN ]