Reinforcement Learning from Human Feedback

130 points | by onurkanbkrc 1 day ago

4 comments

• dang

  1 day ago
  Related. Others?

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

  1 day 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

    1 day ago
    You could say he's also learning from human feedback
• klelatti

  1 day ago
  Web version with links, etc:

  https://rlhfbook.com/

  [-]
  • dang

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

  1 day ago
  [dead]