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

Comment by aixpert

18 days ago

The article basically claims that LLMs are bad at politics and poker which is both not true (at least if they receive some level of reinforcement learning after sweep training)

1 comment

aixpert

Reply

conradkay  18 days ago

Top LLMs are still very bad at poker, see this breakdown of a recent Kaggle experiment: <https://www.youtube.com/watch?v=jyv1bv7JKIQ>

What do you mean by sweep training here?

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities