United States Australia Brazil Canada Germany India Ireland Japan Mexico New Zealand Philippines South Africa United Kingdom
AXRP - the AI X-risk Research Podcast podcast artwork
Technology

AXRP - the AI X-risk Research Podcast

by Daniel Filan
TechnologyScience
Is this your show? Claim it
Listen on Apple PodcastsRSS feed

Recently ranked · United States

Last recorded placements from this show’s chart history. These are not current rankings.

Not on the United States charts we track today.

If you like AXRP - the AI X-risk Research Podcast, try…

Latest episodes

  • 50 - Eli Lifland on AI 2027

    August 2, 2026 · 2 hr 41 min

    Remember AI 2027? Not AI 2040, the newest coolest thing AI Futures Project has done, but AI 2027, their OG product? At long last, we have an AXRP episode about it. Enjoy!   Transcript: https://axrp.net/episode/2026/08/…

  • 49 - Caspar Oesterheld on Program Equilibrium

    February 18, 2026 · 2 hr 32 min

    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…

  • 48 - Guive Assadi on AI Property Rights

    February 15, 2026 · 2 hr 6 min

    In this episode, Guive Assadi argues that we should give AIs property rights, so that they are integrated in our system of property and come to rely on it. The claim is that this means that AIs would not kill or steal from humans, because…

  • 47 - David Rein on METR Time Horizons

    January 2, 2026 · 1 hr 47 min

    When METR says something like "Claude Opus 4.5 has a 50% time horizon of 4 hours and 50 minutes", what does that mean? In this episode David Rein, METR researcher and co-author of the paper "Measuring AI ability to complete long tasks"…

  • 46 - Tom Davidson on AI-enabled Coups

    August 7, 2025 · 2 hr 5 min

    Could AI enable a small group to gain power over a large country, and lock in their power permanently? Often, people worried about catastrophic risks from AI have been concerned with misalignment risks. In this episode, Tom Davidson talks…

Show 7 more episodesShow fewer episodes

  • 45 - Samuel Albanie on DeepMind's AGI Safety Approach

    July 6, 2025 · 1 hr 16 min

    In this episode, I chat with Samuel Albanie about the Google DeepMind paper he co-authored called "An Approach to Technical AGI Safety and Security". It covers the assumptions made by the approach, as well as the types of mitigations it…

  • 44 - Peter Salib on AI Rights for Human Safety

    June 28, 2025 · 3 hr 22 min

    In this episode, I talk with Peter Salib about his paper "AI Rights for Human Safety", arguing that giving AIs the right to contract, hold property, and sue people will reduce the risk of their trying to attack humanity and take over. He…

  • 43 - David Lindner on Myopic Optimization with Non-myopic Approval

    June 15, 2025 · 1 hr 41 min

    In this episode, I talk with David Lindner about Myopic Optimization with Non-myopic Approval, or MONA, which attempts to address (multi-step) reward hacking by myopically optimizing actions against a human's sense of whether those actions…

  • 42 - Owain Evans on LLM Psychology

    June 6, 2025 · 2 hr 14 min

    Earlier this year, the paper "Emergent Misalignment" made the rounds on AI x-risk social media for seemingly showing LLMs generalizing from 'misaligned' training data of insecure code to acting comically evil in response to innocuous…

  • 41 - Lee Sharkey on Attribution-based Parameter Decomposition

    June 3, 2025 · 2 hr 16 min

    What's the next step forward in interpretability? In this episode, I chat with Lee Sharkey about his proposal for detecting computational mechanisms within neural networks: Attribution-based Parameter Decomposition, or APD for short…

  • 40 - Jason Gross on Compact Proofs and Interpretability

    March 28, 2025 · 2 hr 36 min

    How do we figure out whether interpretability is doing its job? One way is to see if it helps us prove things about models that we care about knowing. In this episode, I speak with Jason Gross about his agenda to benchmark interpretability…

  • 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future

    March 1, 2025 · 21 min

    In this episode, I chat with David Duvenaud about two topics he's been thinking about: firstly, a paper he wrote about evaluating whether or not frontier models can sabotage human decision-making or monitoring of the same models; and…

Full episode archive on Apple Podcasts →

About the show

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.