factual

Test-time compute scaling shows consistent performance gains

When reasoning models' performance is plotted against test-time compute, performance on basically any reasoning benchmark rises clearly the longer the model thinks, analogous to people performing better on the SAT with five hours than with five minutes.

factualpending

Speaker

Noam Brown

Evidence Quote

“you see a very clear pattern where the longer these models take to think about their answer, the better they do.”

Source

Dwarkesh Patel Podcast - Noam Brown – Agent swarms, alignment, & recursive self-improvement— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:12:01 AM

Your notes

Loading notes...