Episode

Some thoughts on the Sutton interview

Podcast
Dwarkesh Podcast
Published
Oct 4, 2025
Duration seconds
699
Processing state
not_requested
Canonical source
https://www.dwarkesh.com/p/thoughts-on-sutton
Audio
https://api.substack.com/feed/podcast/175283310/64bc9b781df688895e748ab6d0d0554b.mp3
JSON
/v1/public/podcasts/dwarkesh-podcast/episodes/some-thoughts-on-the-sutton-interview
Markdown
/podcast/dwarkesh-podcast/some-thoughts-on-the-sutton-interview.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/dwarkesh-podcast/episodes/some-thoughts-on-the-sutton-interview/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/dwarkesh-podcast/some-thoughts-on-the-sutton-interview.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

I have a much better understanding of Sutton’s perspective now. I wanted to reflect on it a bit. (00:00:00) - The steelman (00:02:42) - TLDR of my current thoughts (00:03:22) - Imitation learning is continuous with and complementary to RL (00:08:26) - Continual learning (00:10:31) - Concluding thoughts Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe