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

Comment by ForHackernews

2 days ago

Whatever it says is not always what it is doing https://transformer-circuits.pub/2025/attribution-graphs/bio...

> The computation we can see looks like it’s just guessing the answer, despite the chain of thought suggesting it’s computed it using a calculator.

It might be hallucinating or lying, it's not like you are actually observing the internals of the model.

0 comments

ForHackernews

Reply

No comments yet

Contribute on Hacker News ↗

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities