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 raincole

12 hours ago

When it comes to LLM you really cannot draw conclusions from first principles like this. Yes, it sounds reasonable. And things in reality aren't always reasonable.

Benchmark or nothing.

1 comment

raincole

Reply

samus  12 hours ago

There have been papers about introducing thinking tokens in intermediary layers that get stripped from the output.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities