John Carmack
@ID_AA_Carmack · Jan 2, 2025
It would be interesting if LLM training tracked the per-token loss back to the source material — it would be an objective measure of how much each specific book / document contributed to the training. Might say something useful for human learning!
Elon Musk
@elonmusk
💯
02:50 AM · January 3, 2025 · 33.8K views
39
18
414