causal

Training Sample Inefficiency Amortized Across Users

Models are about one-millionth as sample efficient as humans during training, but this is a one-time cost amortized across billions of user sessions, so what matters is within-session sample efficiency, which has been improving with more RL training.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“Yes, these models are 1/1-millionth as sample efficient as humans during training. But training a one-time cost amortized across billions of user sessions.”

Source

Dwarkesh Patel Podcast - The next big breakthrough will be AIs learning on the job— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:25:50 AM

Your notes

Loading notes...