What Dwarkesh Patel thinks about reinforcement learning
Interviewer; the Dwarkesh Podcast runs long, heavily researched conversations with AI researchers, historians and economists.
Dwarkesh Patel did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter reinforcement learning · Newest first
Only Dwarkesh Patel on reinforcement learning. See everyone on reinforcement learning
2 dated positions, 2026, in their own words. Our reading of what Dwarkesh Patel has said — not written or endorsed by them.
-
Their wordsIn fact, aggressive data curation is even more harmful once you take into account that frontier models are up to 100x overtrained relative to Chinchilla optimal, in order to minimize the inference compute used for RL and for deployment.
- 2 months earlier
-
Our readingTraining AIs on millions of verifiable tasks in diverse RL environments will lead to AGI.
Their wordsif we train AIs to accomplish millions of verifiable tasks across thousands of diverse RL environments, then we'll basically have built AGI.