Dwarkesh Podcast cover image

Richard Sutton – Father of RL thinks LLMs are a dead end

Dwarkesh Podcast

00:00

Auxiliary Rewards and Temporal Abstraction

Dwarkesh asks how long-term goals produce useful short-term learning; Sutton explains TD learning and value functions for intermediate feedback.

Transcript
Play full episode

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