LLMs (at least GPT-3.5 and 4) know the semantic meaning of the <|endoftext|> token— which they see very often in training, separating samplesSo do LLMs always know they're predicting LLM…

Posters: repligate. repligate

6 likes recorded by the source corpus.

Topics: AI & LLMs

View Post: https://x.com/repligate/status/1723864725077782962