News for hackers. Stuff that matters.
Re:Decision models like Jev don't beat LLM-as-a-judge or tra... by vrighter on Tuesday October 06, 2026 @05:39AM (#49976215)
all llms output confidence scores on their tokens. That's literally all they generate. Picking an actual next token is a (semi) random sampling of those confidence levels.

There are no comments on this comment yet.