59 Avsnitt

  1. 46 - Tom Davidson on AI-enabled Coups

    Publicerades: 2025-08-07

  2. 45 - Samuel Albanie on DeepMind's AGI Safety Approach

    Publicerades: 2025-07-06

  3. 44 - Peter Salib on AI Rights for Human Safety

    Publicerades: 2025-06-28

  4. 43 - David Lindner on Myopic Optimization with Non-myopic Approval

    Publicerades: 2025-06-15

  5. 42 - Owain Evans on LLM Psychology

    Publicerades: 2025-06-06

  6. 41 - Lee Sharkey on Attribution-based Parameter Decomposition

    Publicerades: 2025-06-03

  7. 40 - Jason Gross on Compact Proofs and Interpretability

    Publicerades: 2025-03-28

  8. 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future

    Publicerades: 2025-03-01

  9. 38.7 - Anthony Aguirre on the Future of Life Institute

    Publicerades: 2025-02-09

  10. 38.6 - Joel Lehman on Positive Visions of AI

    Publicerades: 2025-01-24

  11. 38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

    Publicerades: 2025-01-20

  12. 38.4 - Shakeel Hashim on AI Journalism

    Publicerades: 2025-01-05

  13. 38.3 - Erik Jenner on Learned Look-Ahead

    Publicerades: 2024-12-12

  14. 39 - Evan Hubinger on Model Organisms of Misalignment

    Publicerades: 2024-12-01

  15. 38.2 - Jesse Hoogland on Singular Learning Theory

    Publicerades: 2024-11-27

  16. 38.1 - Alan Chan on Agent Infrastructure

    Publicerades: 2024-11-16

  17. 38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems

    Publicerades: 2024-11-14

  18. 37 - Jaime Sevilla on AI Forecasting

    Publicerades: 2024-10-04

  19. 36 - Adam Shai and Paul Riechers on Computational Mechanics

    Publicerades: 2024-09-29

  20. New Patreon tiers + MATS applications

    Publicerades: 2024-09-28

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.

Visit the podcast's native language site