58 Episodes

  1. 17 - Training for Very High Reliability with Daniel Ziegler

    Published: 8/21/2022
  2. 16 - Preparing for Debate AI with Geoffrey Irving

    Published: 7/1/2022
  3. 15 - Natural Abstractions with John Wentworth

    Published: 5/23/2022
  4. 14 - Infra-Bayesian Physicalism with Vanessa Kosoy

    Published: 4/5/2022
  5. 13 - First Principles of AGI Safety with Richard Ngo

    Published: 3/31/2022
  6. 12 - AI Existential Risk with Paul Christiano

    Published: 12/2/2021
  7. 11 - Attainable Utility and Power with Alex Turner

    Published: 9/25/2021
  8. 10 - AI's Future and Impacts with Katja Grace

    Published: 7/23/2021
  9. 9 - Finite Factored Sets with Scott Garrabrant

    Published: 6/24/2021
  10. 8 - Assistance Games with Dylan Hadfield-Menell

    Published: 6/8/2021
  11. 7.5 - Forecasting Transformative AI from Biological Anchors with Ajeya Cotra

    Published: 5/28/2021
  12. 7 - Side Effects with Victoria Krakovna

    Published: 5/14/2021
  13. 6 - Debate and Imitative Generalization with Beth Barnes

    Published: 4/8/2021
  14. 5 - Infra-Bayesianism with Vanessa Kosoy

    Published: 3/10/2021
  15. 4 - Risks from Learned Optimization with Evan Hubinger

    Published: 2/17/2021
  16. 3 - Negotiable Reinforcement Learning with Andrew Critch

    Published: 12/11/2020
  17. 2 - Learning Human Biases with Rohin Shah

    Published: 12/11/2020
  18. 1 - Adversarial Policies with Adam Gleave

    Published: 12/11/2020

3 / 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.