Alex Dimakis
@AlexGDimakis · Jun 19, 2024
This paper seems very interesting: say you train an LLM to play chess using only transcripts of games of players up to 1000 elo. Is it possible that the model plays better than 1000 elo? (i.e. "transcends" the training data performance?). It seems you get something from nothing,
Elon Musk
@elonmusk
Interesting
02:59 PM · June 19, 2024 · 43.6K views
56
17
563