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

Comment by egl2020

6 hours ago

Any idea how being persistent is trained? I've noticed that telling an LLM that it needs to think some more sometimes produces better results, but the claim here is that "they are very persistent" and "...kept going...".

1 comment

egl2020

Reply

naasking  4 hours ago

It's from work like this:

https://arxiv.org/abs/2309.11495

A RL pipeline can reinforce verification behaviour even better than simple prompting.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities