58 Episodes

  1. 45 - Samuel Albanie on DeepMind's AGI Safety Approach

    Published: 7/6/2025
  2. 44 - Peter Salib on AI Rights for Human Safety

    Published: 6/28/2025
  3. 43 - David Lindner on Myopic Optimization with Non-myopic Approval

    Published: 6/15/2025
  4. 42 - Owain Evans on LLM Psychology

    Published: 6/6/2025
  5. 41 - Lee Sharkey on Attribution-based Parameter Decomposition

    Published: 6/3/2025
  6. 40 - Jason Gross on Compact Proofs and Interpretability

    Published: 3/28/2025
  7. 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future

    Published: 3/1/2025
  8. 38.7 - Anthony Aguirre on the Future of Life Institute

    Published: 2/9/2025
  9. 38.6 - Joel Lehman on Positive Visions of AI

    Published: 1/24/2025
  10. 38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

    Published: 1/20/2025
  11. 38.4 - Shakeel Hashim on AI Journalism

    Published: 1/5/2025
  12. 38.3 - Erik Jenner on Learned Look-Ahead

    Published: 12/12/2024
  13. 39 - Evan Hubinger on Model Organisms of Misalignment

    Published: 12/1/2024
  14. 38.2 - Jesse Hoogland on Singular Learning Theory

    Published: 11/27/2024
  15. 38.1 - Alan Chan on Agent Infrastructure

    Published: 11/16/2024
  16. 38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems

    Published: 11/14/2024
  17. 37 - Jaime Sevilla on AI Forecasting

    Published: 10/4/2024
  18. 36 - Adam Shai and Paul Riechers on Computational Mechanics

    Published: 9/29/2024
  19. New Patreon tiers + MATS applications

    Published: 9/28/2024
  20. 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

    Published: 8/24/2024

1 / 3

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.