factual

Taste can be trained by predicting small-scale results at scale

Research taste is itself verifiable: an RL environment can ask GPT-7 to predict whether an algorithmic improvement made at 100M parameters will hold at 10B, a taste-bench that is costly but feasible on frontier compute.

factualpending

Speaker

Dwarkesh Patel

Evidence Quote

“So even important parts of research taste are verifiable.”

Source

Dwarkesh Patel Podcast - The avalanche that hit math is coming for AI development— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:27:26 AM

Your notes

Loading notes...