AXRP - the AI X-risk Research Podcast

Daniel Filan

AXRP (pronounced axe-urp) is the AI X-risk Research Podcast where I, Daniel Filan, have conversations with researchers about their papers. We discuss the paper, and hopefully get a sense of why it's been written and how it might reduce the risk of AI causing an existential catastrophe: that is, permanently and drastically curtailing humanity's future potential. You can visit the website and read transcripts at axrp.net.

About PodLP

PodLP is the leading podcast app for feature phones. With 10M+ installs in nearly every country, PodLP is available for KaiOS on the KaiStore and JioStore, as well as Cloud Phone and Android. If you're interested in promoting "AXRP - the AI X-risk Research Podcast" on PodLP, contact sales@podlp.com.

Screenshots are mockup renders of PodLP for KaiOS. Actual design may vary based on platform, operating system, and app version.

AXRP - the AI X-risk Research Podcast

Episodes (62)

Feb 18th 49 - Caspar Oesterheld on Program Equilibrium
Feb 15th 48 - Guive Assadi on AI Property Rights
Jan 2nd 47 - David Rein on METR Time Horizons

AXRP - the AI X-risk Research Podcast

Feb 18, 2026
3 hours
222 MB

How does game theory work when everyone is a computer program who can read everyone else's source code? This is the problem of 'program equilibria'. In this episode, I talk with Caspar Oesterheld on work he's done on equilibria of programs that simulate each other, and how robust these equilibria are. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast Transcript: https://axrp.net/episode/2026/02/18/episode-49-caspar-oesterheld-program-equilibrium.html Note from Caspar on 2:00:06: At least given my current interpretation of what you say here, my answer is wrong. What actually...

AXRP - the AI X-risk Research Podcast

49 - Caspar Oesterheld on Program Equilibrium

Daniel Filan

00:00 -02:32:07