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 PatelEvidence 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 PodcastCreated: 11/17/2026, 6:25:50 AM
Your notes
Loading notes...