Podcasts Technology AXRP - the AI X-risk Research Podcast
AXRP - the AI X-risk Research Podcast

AXRP - the AI X-risk Research Podcast

5 episodes

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.

Podcasts

33 - RLHF Problems with Scott Emmons

Published: June 12, 2024, 3:29 a.m.
Duration: 1 hour 41 minutes 24 seconds

Listed in: Technology

32 - Understanding Agency with Jan Kulveit

Published: May 30, 2024, 3:47 a.m.
Duration: 2 hours 22 minutes 29 seconds

Listed in: Technology

31 - Singular Learning Theory with Daniel Murfet

Published: May 7, 2024, 3:46 a.m.
Duration: 2 hours 32 minutes 7 seconds

Listed in: Technology

30 - AI Security with Jeffrey Ladish

Published: April 30, 2024, 8:58 p.m.
Duration: 2 hours 15 minutes 44 seconds

Listed in: Technology

29 - Science of Deep Learning with Vikrant Varma

Published: April 25, 2024, 6:36 p.m.
Duration: 2 hours 13 minutes 46 seconds

Listed in: Technology

28 - Suing Labs for AI Risk with Gabriel Weil

Published: April 17, 2024, 9:43 p.m.
Duration: 1 hour 57 minutes 30 seconds

Listed in: Technology

27 - AI Control with Buck Shlegeris and Ryan Greenblatt

Published: April 11, 2024, 9:22 p.m.
Duration: 2 hours 56 minutes 5 seconds

Listed in: Technology

26 - AI Governance with Elizabeth Seger

Published: Nov. 26, 2023, 10:57 p.m.
Duration: 1 hour 57 minutes 13 seconds

Listed in: Technology

25 - Cooperative AI with Caspar Oesterheld

Published: Oct. 3, 2023, 9:46 p.m.
Duration: 3 hours 2 minutes 9 seconds

Listed in: Technology

24 - Superalignment with Jan Leike

Published: July 27, 2023, 3:59 a.m.
Duration: 2 hours 8 minutes 29 seconds

Listed in: Technology

23 - Mechanistic Anomaly Detection with Mark Xu

Published: July 27, 2023, 1:47 a.m.
Duration: 2 hours 5 minutes 52 seconds

Listed in: Technology

Survey, store closing, Patreon

Published: June 28, 2023, 11:20 p.m.
Duration: 4 minutes 26 seconds

Listed in: Technology

22 - Shard Theory with Quintin Pope

Published: June 15, 2023, 6:45 p.m.
Duration: 3 hours 28 minutes 21 seconds

Listed in: Technology

21 - Interpretability for Engineers with Stephen Casper

Published: May 2, 2023, 12:50 a.m.
Duration: 1 hour 56 minutes 2 seconds

Listed in: Technology

20 - 'Reform' AI Alignment with Scott Aaronson

Published: April 12, 2023, 9:43 p.m.
Duration: 2 hours 27 minutes 35 seconds

Listed in: Technology

Store, Patreon, Video

Published: Feb. 7, 2023, 4:27 a.m.
Duration: 2 minutes 39 seconds

Listed in: Technology

19 - Mechanistic Interpretability with Neel Nanda

Published: Feb. 4, 2023, 2:56 a.m.
Duration: 3 hours 52 minutes 47 seconds

Listed in: Technology

New podcast - The Filan Cabinet

Published: Oct. 13, 2022, 9:19 p.m.
Duration: 1 minute 18 seconds

Listed in: Technology

18 - Concept Extrapolation with Stuart Armstrong

Published: Sept. 3, 2022, 11:03 p.m.
Duration: 1 hour 46 minutes 19 seconds

Listed in: Technology

17 - Training for Very High Reliability with Daniel Ziegler

Published: Aug. 21, 2022, 11:43 p.m.
Duration: 1 hour 59 seconds

Listed in: Technology

16 - Preparing for Debate AI with Geoffrey Irving

Published: July 1, 2022, 10:12 p.m.
Duration: 1 hour 4 minutes 49 seconds

Listed in: Technology

15 - Natural Abstractions with John Wentworth

Published: May 23, 2022, 5:27 a.m.
Duration: 1 hour 36 minutes 30 seconds

Listed in: Technology

14 - Infra-Bayesian Physicalism with Vanessa Kosoy

Published: April 5, 2022, 11:02 p.m.
Duration: 1 hour 47 minutes 31 seconds

Listed in: Technology

13 - First Principles of AGI Safety with Richard Ngo

Published: March 31, 2022, 5:15 a.m.
Duration: 1 hour 33 minutes 53 seconds

Listed in: Technology

12 - AI Existential Risk with Paul Christiano

Published: Dec. 2, 2021, 2:37 a.m.
Duration: 2 hours 49 minutes 36 seconds

Listed in: Technology

11 - Attainable Utility and Power with Alex Turner

Published: Sept. 25, 2021, 9:13 p.m.
Duration: 1 hour 27 minutes 36 seconds

Listed in: Technology

10 - AI's Future and Impacts with Katja Grace

Published: July 23, 2021, 10:34 p.m.
Duration: 2 hours 2 minutes 58 seconds

Listed in: Technology

9 - Finite Factored Sets with Scott Garrabrant

Published: June 24, 2021, 10:15 p.m.
Duration: 1 hour 38 minutes 59 seconds

Listed in: Technology

8 - Assistance Games with Dylan Hadfield-Menell

Published: June 8, 2021, 11:34 p.m.
Duration: 2 hours 23 minutes 17 seconds

Listed in: Technology

7.5 - Forecasting Transformative AI from Biological Anchors with Ajeya Cotra

Published: May 28, 2021, 12:21 a.m.
Duration: 1 minute 3 seconds

Listed in: Technology

7 - Side Effects with Victoria Krakovna

Published: May 14, 2021, 3:57 a.m.
Duration: 1 hour 19 minutes 29 seconds

Listed in: Technology

6 - Debate and Imitative Generalization with Beth Barnes

Published: April 8, 2021, 9:15 p.m.
Duration: 1 hour 58 minutes 48 seconds

Listed in: Technology

5 - Infra-Bayesianism with Vanessa Kosoy

Published: March 10, 2021, 4:30 a.m.
Duration: 1 hour 23 minutes 51 seconds

Listed in: Technology

4 - Risks from Learned Optimization with Evan Hubinger

Published: Feb. 17, 2021, 11:26 p.m.
Duration: 2 hours 13 minutes 32 seconds

Listed in: Technology

3 - Negotiable Reinforcement Learning with Andrew Critch

Published: Dec. 11, 2020, 4:13 a.m.
Duration: 58 minutes 14 seconds

Listed in: Technology

2 - Learning Human Biases with Rohin Shah

Published: Dec. 11, 2020, 4:06 a.m.
Duration: 1 hour 8 minutes 51 seconds

Listed in: Technology

1 - Adversarial Policies with Adam Gleave

Published: Dec. 11, 2020, 3:37 a.m.
Duration: 58 minutes 41 seconds

Listed in: Technology