Re:I replaced Animal Crossing's dialogue with a live LLM by ...
by madaxe_again on Wednesday September 10, 2025 @04:23AM
(#45194795)
No, this is the Einstein/student model that has been proposed for improving LLM output quality.
Basically you have your big clever LLM generating the outputs, and then you have your small dumb LLM reading them and going “did I understand that? Did it make sense?” - basically emulating the user before the response actually gets to the user. If it’s good, on it goes to the user, if not, the student queries Einstein with feedback to have another crack.
Basically you have your big clever LLM generating the outputs, and then you have your small dumb LLM reading them and going “did I understand that? Did it make sense?” - basically emulating the user before the response actually gets to the user. If it’s good, on it goes to the user, if not, the student queries Einstein with feedback to have another crack.
https://openai.com/index/prover-verifier-games-improve-legib...