58 Episoder

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

    Udgivet: 6.7.2025
  2. 44 - Peter Salib on AI Rights for Human Safety

    Udgivet: 28.6.2025
  3. 43 - David Lindner on Myopic Optimization with Non-myopic Approval

    Udgivet: 15.6.2025
  4. 42 - Owain Evans on LLM Psychology

    Udgivet: 6.6.2025
  5. 41 - Lee Sharkey on Attribution-based Parameter Decomposition

    Udgivet: 3.6.2025
  6. 40 - Jason Gross on Compact Proofs and Interpretability

    Udgivet: 28.3.2025
  7. 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future

    Udgivet: 1.3.2025
  8. 38.7 - Anthony Aguirre on the Future of Life Institute

    Udgivet: 9.2.2025
  9. 38.6 - Joel Lehman on Positive Visions of AI

    Udgivet: 24.1.2025
  10. 38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

    Udgivet: 20.1.2025
  11. 38.4 - Shakeel Hashim on AI Journalism

    Udgivet: 5.1.2025
  12. 38.3 - Erik Jenner on Learned Look-Ahead

    Udgivet: 12.12.2024
  13. 39 - Evan Hubinger on Model Organisms of Misalignment

    Udgivet: 1.12.2024
  14. 38.2 - Jesse Hoogland on Singular Learning Theory

    Udgivet: 27.11.2024
  15. 38.1 - Alan Chan on Agent Infrastructure

    Udgivet: 16.11.2024
  16. 38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems

    Udgivet: 14.11.2024
  17. 37 - Jaime Sevilla on AI Forecasting

    Udgivet: 4.10.2024
  18. 36 - Adam Shai and Paul Riechers on Computational Mechanics

    Udgivet: 29.9.2024
  19. New Patreon tiers + MATS applications

    Udgivet: 28.9.2024
  20. 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

    Udgivet: 24.8.2024

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.

Visit the podcast's native language site