causal
RL Unlocks Skill, Pre-Training Provides Knowledge
RL post-training does not teach the model new knowledge but unlocks the knowledge it already has from pre-training—it is skill learning (how to solve problems) rather than knowledge soaking, which is why RLVR can take a base model from 15% to 50% accuracy on MATH-500 in 50 steps without teaching new math.
causalpending
Speaker
Sebastian RaschkaEvidence Quote
“the knowledge is already there in the pre-training; you’re just unlocking it.”
Created: 6/13/2026, 3:24:41 AM
Your notes
Loading notes...