News for hackers. Stuff that matters.
Re:Recent AI model progress feels mostly like bullshit by Workaccount2 on Monday April 07, 2025 @10:12AM (#43611758)
On top of that, what the model prints out in the CoT window is not necessarily what the model is actually thinking. Anthropic just showed this in their paper from last week where they got models to cheat at a question by "accidentally" slipping them the answer, and the CoT had no mention of answer being slipped to them.

There are no comments on this comment yet.