AXRP - the AI X-risk Research Podcast

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.

Website

Every guest on AXRP - the AI X-risk Research Podcast

57 guests, ranked by how many people never want them back.

1. —
   Ajeya Cotra

   7.5 - Forecasting Transformative AI from Biological Anchors with Ajeya Cotra · May 2021

   0 votes

   Never again
2. —
   Ryan Greenblatt
   0 votes

   Never again
3. —
   Paul Christiano

   12 - AI Existential Risk with Paul Christiano · Dec 2021

   0 votes

   Never again
4. —
   Scott Aaronson

   20 - 'Reform' AI Alignment with Scott Aaronson · Apr 2023

   0 votes

   Never again
5. —
   Anthony Aguirre

   38.7 - Anthony Aguirre on the Future of Life Institute · Feb 2025

   0 votes

   Never again
6. —
   Adam Gleave

   1 - Adversarial Policies with Adam Gleave · Dec 2020

   0 votes

   Never again
7. —
   Buck Shlegeris

   27 - AI Control with Buck Shlegeris and Ryan Greenblatt · Apr 2024

   0 votes

   Never again
8. —
   Daniel Murfet

   31 - Singular Learning Theory with Daniel Murfet · May 2024

   0 votes

   Never again
9. —
   Gabriel Weil

   28 - Suing Labs for AI Risk with Gabriel Weil · Apr 2024

   0 votes

   Never again
10. —
    Geoffrey Irving

    16 - Preparing for Debate AI with Geoffrey Irving · Jul 2022

    0 votes

    Never again
11. —
    Jeffrey Ladish

    30 - AI Security with Jeffrey Ladish · Apr 2024

    0 votes

    Never again
12. —
    Jesse Hoogland

    38.2 - Jesse Hoogland on Singular Learning Theory · Nov 2024

    0 votes

    Never again
13. —
    Katja Grace

    10 - AI's Future and Impacts with Katja Grace · Jul 2021

    0 votes

    Never again
14. —
    Lee Sharkey

    41 - Lee Sharkey on Attribution-based Parameter Decomposition · Jun 2025

    0 votes

    Never again
15. —
    Owain Evans

    42 - Owain Evans on LLM Psychology · Jun 2025

    0 votes

    Never again
16. —
    Tom Davidson

    46 - Tom Davidson on AI-enabled Coups · Aug 2025

    0 votes

    Never again
17. —
    Alan Chan

    38.1 - Alan Chan on Agent Infrastructure · Nov 2024

    0 votes

    Never again
18. —
    Beth Barnes

    34 - AI Evaluations with Beth Barnes · 2 episodes

    0 votes

    Never again
19. —
    David Rein

    47 - David Rein on METR Time Horizons · Jan 2026

    0 votes

    Never again
20. —
    Neel Nanda

    19 - Mechanistic Interpretability with Neel Nanda · Feb 2023

    0 votes

    Never again
21. —
    David Duvenaud

    38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future · Mar 2025

    0 votes

    Never again
22. —
    Elizabeth Seger

    26 - AI Governance with Elizabeth Seger · Nov 2023

    0 votes

    Never again
23. —
    Peter Hase

    35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization · Aug 2024

    0 votes

    Never again
24. —
    Joel Lehman

    38.6 - Joel Lehman on Positive Visions of AI · Jan 2025

    0 votes

    Never again
25. —
    Daniel Ziegler

    17 - Training for Very High Reliability with Daniel Ziegler · Aug 2022

    0 votes

    Never again
26. —
    Jan Leike

    24 - Superalignment with Jan Leike · Jul 2023

    0 votes

    Never again
27. —
    Richard Ngo

    13 - First Principles of AGI Safety with Richard Ngo · Mar 2022

    0 votes

    Never again
28. —
    Rohin Shah

    2 - Learning Human Biases with Rohin Shah · Dec 2020

    0 votes

    Never again
29. —
    Andrew Critch

    3 - Negotiable Reinforcement Learning with Andrew Critch · Dec 2020

    0 votes

    Never again
30. —
    Dylan Hadfield-Menell

    8 - Assistance Games with Dylan Hadfield-Menell · Jun 2021

    0 votes

    Never again
31. —
    Evan Hubinger

    39 - Evan Hubinger on Model Organisms of Misalignment · 2 episodes

    0 votes

    Never again
32. —
    Stuart Armstrong

    18 - Concept Extrapolation with Stuart Armstrong · Sep 2022

    0 votes

    Never again
33. —
    Adam Shai

    36 - Adam Shai and Paul Riechers on Computational Mechanics · Sep 2024

    0 votes

    Never again
34. —
    Adrià Garriga-Alonso

    38.5 - Adrià Garriga-Alonso on Detecting AI Scheming · Jan 2025

    0 votes

    Never again
35. —
    Alex Turner

    11 - Attainable Utility and Power with Alex Turner · Sep 2021

    0 votes

    Never again
36. —
    Caspar Oesterheld

    49 - Caspar Oesterheld on Program Equilibrium · 2 episodes

    0 votes

    Never again
37. —
    David Lindner

    43 - David Lindner on Myopic Optimization with Non-myopic Approval · Jun 2025

    0 votes

    Never again
38. —
    Eli Lifland

    50 - Eli Lifland on AI 2027 · Aug 2026

    0 votes

    Never again
39. —
    Erik Jenner

    38.3 - Erik Jenner on Learned Look-Ahead · Dec 2024

    0 votes

    Never again
40. —
    Guive Assadi

    48 - Guive Assadi on AI Property Rights · Feb 2026

    0 votes

    Never again