News for hackers. Stuff that matters.
Re:Evaluating Chain-of-Thought Monitorability by canjobear on Monday December 22, 2025 @12:03AM (#46351473)
It’s more like if the supervillain had to write one word of his chain of thought, then go away and forget what he was thinking, then come back and write one more word based on what he had written so far, repeating the process until the whole chain of thought is written out. Each token is generated conditional only on the previous tokens.

There are no comments on this comment yet.