HN.zip

Reinforcement Learning from Human Feedback

https://arxiv.org/abs/2504.12501

95 points by onurkanbkrc - 5 comments

5 Comments

dang [3 hidden]5 mins ago
Related. Others?

RLHF Book - https://news.ycombinator.com/item?id=42902936 - Feb 2025 (37 comments)

verdverm [3 hidden]5 mins ago
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
leggerss [3 hidden]5 mins ago
You could say he's also learning from human feedback
klelatti [3 hidden]5 mins ago
Web version with links, etc:

https://rlhfbook.com/

dang [3 hidden]5 mins ago
Thanks! We've switched to that above from https://arxiv.org/abs/2504.12501, and put the latter in the toptext.