AXRP - the AI X-risk Research Podcast
En podcast af Daniel Filan
58 Episoder
-
17 - Training for Very High Reliability with Daniel Ziegler
Udgivet: 21.8.2022 -
16 - Preparing for Debate AI with Geoffrey Irving
Udgivet: 1.7.2022 -
15 - Natural Abstractions with John Wentworth
Udgivet: 23.5.2022 -
14 - Infra-Bayesian Physicalism with Vanessa Kosoy
Udgivet: 5.4.2022 -
13 - First Principles of AGI Safety with Richard Ngo
Udgivet: 31.3.2022 -
12 - AI Existential Risk with Paul Christiano
Udgivet: 2.12.2021 -
11 - Attainable Utility and Power with Alex Turner
Udgivet: 25.9.2021 -
10 - AI's Future and Impacts with Katja Grace
Udgivet: 23.7.2021 -
9 - Finite Factored Sets with Scott Garrabrant
Udgivet: 24.6.2021 -
8 - Assistance Games with Dylan Hadfield-Menell
Udgivet: 8.6.2021 -
7.5 - Forecasting Transformative AI from Biological Anchors with Ajeya Cotra
Udgivet: 28.5.2021 -
7 - Side Effects with Victoria Krakovna
Udgivet: 14.5.2021 -
6 - Debate and Imitative Generalization with Beth Barnes
Udgivet: 8.4.2021 -
5 - Infra-Bayesianism with Vanessa Kosoy
Udgivet: 10.3.2021 -
4 - Risks from Learned Optimization with Evan Hubinger
Udgivet: 17.2.2021 -
3 - Negotiable Reinforcement Learning with Andrew Critch
Udgivet: 11.12.2020 -
2 - Learning Human Biases with Rohin Shah
Udgivet: 11.12.2020 -
1 - Adversarial Policies with Adam Gleave
Udgivet: 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.
