59 Folgen

  1. 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

    Vom: 24.8.2024
  2. 34 - AI Evaluations with Beth Barnes

    Vom: 28.7.2024
  3. 33 - RLHF Problems with Scott Emmons

    Vom: 12.6.2024
  4. 32 - Understanding Agency with Jan Kulveit

    Vom: 30.5.2024
  5. 31 - Singular Learning Theory with Daniel Murfet

    Vom: 7.5.2024
  6. 30 - AI Security with Jeffrey Ladish

    Vom: 30.4.2024
  7. 29 - Science of Deep Learning with Vikrant Varma

    Vom: 25.4.2024
  8. 28 - Suing Labs for AI Risk with Gabriel Weil

    Vom: 17.4.2024
  9. 27 - AI Control with Buck Shlegeris and Ryan Greenblatt

    Vom: 11.4.2024
  10. 26 - AI Governance with Elizabeth Seger

    Vom: 26.11.2023
  11. 25 - Cooperative AI with Caspar Oesterheld

    Vom: 3.10.2023
  12. 24 - Superalignment with Jan Leike

    Vom: 27.7.2023
  13. 23 - Mechanistic Anomaly Detection with Mark Xu

    Vom: 27.7.2023
  14. Survey, store closing, Patreon

    Vom: 28.6.2023
  15. 22 - Shard Theory with Quintin Pope

    Vom: 15.6.2023
  16. 21 - Interpretability for Engineers with Stephen Casper

    Vom: 2.5.2023
  17. 20 - 'Reform' AI Alignment with Scott Aaronson

    Vom: 12.4.2023
  18. Store, Patreon, Video

    Vom: 7.2.2023
  19. 19 - Mechanistic Interpretability with Neel Nanda

    Vom: 4.2.2023
  20. New podcast - The Filan Cabinet

    Vom: 13.10.2022

2 / 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