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. —
   Jaime Sevilla

   37 - Jaime Sevilla on AI Forecasting · Oct 2024

   0 votes

   Never again
2. —
   Jan Kulveit

   32 - Understanding Agency with Jan Kulveit · May 2024

   0 votes

   Never again
3. —
   Jason Gross

   40 - Jason Gross on Compact Proofs and Interpretability · Mar 2025

   0 votes

   Never again
4. —
   John Wentworth

   15 - Natural Abstractions with John Wentworth · May 2022

   0 votes

   Never again
5. —
   Mark Xu

   23 - Mechanistic Anomaly Detection with Mark Xu · Jul 2023

   0 votes

   Never again
6. —
   Paul Riechers
   0 votes

   Never again
7. —
   Peter Salib

   44 - Peter Salib on AI Rights for Human Safety · Jun 2025

   0 votes

   Never again
8. —
   Quintin Pope

   22 - Shard Theory with Quintin Pope · Jun 2023

   0 votes

   Never again
9. —
   Samuel Albanie

   45 - Samuel Albanie on DeepMind's AGI Safety Approach · Jul 2025

   0 votes

   Never again
10. —
    Scott Emmons

    33 - RLHF Problems with Scott Emmons · Jun 2024

    0 votes

    Never again
11. —
    Scott Garrabrant

    9 - Finite Factored Sets with Scott Garrabrant · Jun 2021

    0 votes

    Never again
12. —
    Shakeel Hashim

    38.4 - Shakeel Hashim on AI Journalism · Jan 2025

    0 votes

    Never again
13. —
    Stephen Casper

    21 - Interpretability for Engineers with Stephen Casper · May 2023

    0 votes

    Never again
14. —
    Vanessa Kosoy

    14 - Infra-Bayesian Physicalism with Vanessa Kosoy · 2 episodes

    0 votes

    Never again
15. —
    Victoria Krakovna

    7 - Side Effects with Victoria Krakovna · May 2021

    0 votes

    Never again
16. —
    Vikrant Varma

    29 - Science of Deep Learning with Vikrant Varma · Apr 2024

    0 votes

    Never again
17. —
    Zhijing Jin

    38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems · Nov 2024

    0 votes

    Never again