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.
[ Parent
| on HN ]
There are no comments on this comment yet.