factual
Naive Fine-Tuning On Observed Tokens Fails
If you tried to fit the transition-model spec into LLMs by fine-tuning on all observed tokens, in practice the most naive way of doing this doesn't work well, according to researcher friends.
factualpending
Speaker
Dwarkesh PatelEvidence Quote
“in practice the most naive way of doing this doesn’t work well.”
Created: 6/13/2026, 3:28:01 AM
Your notes
Loading notes...