News for hackers. Stuff that matters.
Re:John Carmack and Rich Sutton partner to accelerate develo... by bwv848 on Sunday October 08, 2023 @03:42AM (#37808603)
Not really, LLM Decoders(without RLHF) are usually trained by teacher forcing, that means they just get learning singals from just predicting one token.

There are no comments on this comment yet.