causal

Computer Use Lag Reveals Replayable Target Need

The slow progress of computer use shows that unless a domain has a very replayable training target, models will struggle to make much progress, because models are highly sample inefficient during training.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“unless you can build a very replayable training target for a domain, the models will struggle to make much progress.”

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...