Dwarkesh Podcast cover image

The next big breakthrough will be AIs learning on the job

Dwarkesh Podcast

00:00

Dreaming As Test Time Training

  • Dreaming means the model builds internal simulators to rehearse skills and generate massive additional training samples.
  • If accurate, dreaming becomes a fourth scaling axis: test-time training where the model writes environments and trains against them.
Play episode from 15:35
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app