Inference-time Reasoning
Chain of thought, self-consistency voting, search and verifier loops with a price on every extra token.
0 of 2 complete
- ▶ Up nextPro18 min+50 XPChain of thought and self-consistency: majority voting, and when it failsWhy writing intermediate steps helps, how sampling several chains and voting improves accuracy, a runnable simulation…
- Pro19 min+50 XPSearch and verifier loops: best-of-n, trees, refinement and reasoning budgetsUse a verifier to pick among samples (best-of-n with simulated accuracy from 40% to 93%), why verifier quality caps…