AXRP – the AI X-risk Research Podcast
by Daniel Filan
November 27, 2024 5:28 pm
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.
Recent Episodes
38.2 - Jesse Hoogland on Singular Learning Theory
2 days ago38.1 - Alan Chan on Agent Infrastructure
2 weeks ago38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems
2 weeks ago37 - Jaime Sevilla on AI Forecasting
2 months ago36 - Adam Shai and Paul Riechers on Computational Mechanics
2 months agoNew Patreon tiers + MATS applications
2 months ago35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization
3 months ago34 - AI Evaluations with Beth Barnes
4 months ago33 - RLHF Problems with Scott Emmons
6 months ago32 - Understanding Agency with Jan Kulveit
6 months ago