RLVR might be disproportionately bad at science
the verification loop for theories can be on the order of decades and centuries, and even then we know today as the better theory can often actually make worse predictions
Blog RLVR might be disproportionately bad at science the verification loop for theories can be on the order of decades and centuries, and even then we know today as the better theory can often actually make worse predictions Dwarkesh Patel May 16, 2026 23 6 1 Share I’m writing up some threads that we explored in my interview with Michael Nielson . That episode was one of my favorites. The organizing question from my interview with Michael Nielson was, “How do we recognize scientific progress?” It’s especially relevant to thinking about what it would take for AI to close the RL verification loo
saved by
related reading
- Designing AI for Disruptive Scienceasimov.press
- Is Science Stagnant? - The Atlantictheatlantic.com
- When do ideas get easier to find?freaktakes.substack.com
- Terence Tao – Kepler, Newton, and the true nature of mathematical discoverydwarkesh.com
- The Need for Verification in AI-Driven Scientific Discoveryalphaxiv.org
- The Structure of Scientific Revolutions - Wikipediaen.wikipedia.org
- Could AI slow science?normaltech.ai
- The Beginning of Infinity, Part 1nav.al
- Constellations of Borrowed Light · Velaborrowedlight.org
- Book Review: The Structure of Scientific Revolutionsamid.fish
- Faster Than Science — LessWronglesswrong.com
- Philosophy of science and the blockchain: A book review – Windows On Theorywindowsontheory.org