Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by visarga

1 day ago

I think it's more RLVR (reinforcement learning from verified rewards). The RLHF is just to align models to human preferences, meaning to behave nice.

2 comments

visarga

Reply

versteegen  19 hours ago

More accurate to say RLHF aligns models to human preferences, most significantly to be helpful.

redanddead  1 day ago

What makes you say that

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities