causal
Human Prior Needed To Kickstart Ground-Truth RL
Imitation learning can leverage models to learn better from ground truth: models have been RLed to win IMO Gold and code entire applications from scratch—ground-truth examinations—but you couldn't RL a model to do these from scratch; you needed a reasonable prior over human data to kickstart the RL process.
causalpending
Speaker
Dwarkesh PatelEvidence Quote
“You needed a reasonable prior over human data in order to kick start the RL process.”
Created: 6/13/2026, 3:28:01 AM
Your notes
Loading notes...