factual

Reasoning best from combining test-time and training-time

Reasoning—tasks requiring test-time, step-by-step computation or deduction—is best achieved by combining inference-time computation (the model thinking step by step while deployed) with practice at training time, rather than relying on either approach alone.

factualpending

Speaker

John Schulman (OpenAI Cofounder)

Evidence Quote

“you'd get the best results by combining these two things.”

Source

John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:30 AM

Your notes

Loading notes...