causal
RL requires prior probability on correct solutions
For RL-based training to work, the model must already have some nonzero prior probability of producing the correct solution, which is why mind-stretching amounts of human expert trajectories are needed in every skill the model should master.
causalpending
Speaker
Dwarkesh PatelEvidence Quote
“the model must have at least prior some probability to anticipate the correct solution”
Created: 11/17/2026, 6:11:50 AM
Your notes
Loading notes...