forecast

Dreaming Would Be a Fourth Scaling Axis

If dreaming works, it would become a fourth axis of scaling alongside pretraining, RL, and inference-time compute, with the model spending compute to write RL environments that rehearse skills needed for a specific user's production work.

forecastpending

Speaker

Dwarkesh Patel

Evidence Quote

“If it works, it would become a fourth axis of scaling, alongside pretraining, RL, and inference-time compute.”

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...