causal
Math Is Fast Because It Is Verifiable and Grindable
AI progress in math is fast not only because outcomes are verifiable but because the domain is grindable: deterministic containers and diffs let RL run many parallel rollouts and solve credit assignment, which computer use and the real world lack.
causalpending
Speaker
Dwarkesh PatelEvidence Quote
“With code, you can containerize a given level of progress in a repository and then spin out hundreds of parallel containers... it’s totally deterministic.”
Created: 11/17/2026, 6:11:54 AM
Your notes
Loading notes...