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 geraneum

13 hours ago

> can be rerailed

What rerails it?

2 comments

geraneum

Reply

Marha01  4 hours ago

The model can realize it made a mistake earlier and correct itself in subsequent output. I have seen it happen many times in CoT.

  • geraneum  42 minutes ago

    That’s the point. It may or may not. It can derail it.

    This realization is something you assign meaning to. For the model there’s no difference between either of these states.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities