AXRP - the AI X-risk Research Podcast
A podcast by Daniel Filan
59 Episodes
-
18 - Concept Extrapolation with Stuart Armstrong
Published: 3/09/2022 -
17 - Training for Very High Reliability with Daniel Ziegler
Published: 21/08/2022 -
16 - Preparing for Debate AI with Geoffrey Irving
Published: 1/07/2022 -
15 - Natural Abstractions with John Wentworth
Published: 23/05/2022 -
14 - Infra-Bayesian Physicalism with Vanessa Kosoy
Published: 5/04/2022 -
13 - First Principles of AGI Safety with Richard Ngo
Published: 31/03/2022 -
12 - AI Existential Risk with Paul Christiano
Published: 2/12/2021 -
11 - Attainable Utility and Power with Alex Turner
Published: 25/09/2021 -
10 - AI's Future and Impacts with Katja Grace
Published: 23/07/2021 -
9 - Finite Factored Sets with Scott Garrabrant
Published: 24/06/2021 -
8 - Assistance Games with Dylan Hadfield-Menell
Published: 8/06/2021 -
7.5 - Forecasting Transformative AI from Biological Anchors with Ajeya Cotra
Published: 28/05/2021 -
7 - Side Effects with Victoria Krakovna
Published: 14/05/2021 -
6 - Debate and Imitative Generalization with Beth Barnes
Published: 8/04/2021 -
5 - Infra-Bayesianism with Vanessa Kosoy
Published: 10/03/2021 -
4 - Risks from Learned Optimization with Evan Hubinger
Published: 17/02/2021 -
3 - Negotiable Reinforcement Learning with Andrew Critch
Published: 11/12/2020 -
2 - Learning Human Biases with Rohin Shah
Published: 11/12/2020 -
1 - Adversarial Policies with Adam Gleave
Published: 11/12/2020
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.
