AXRP - the AI X-risk Research Podcast
Un pódcast de Daniel Filan
59 Episodo
-
46 - Tom Davidson on AI-enabled Coups
Publicado: 7/8/2025 -
45 - Samuel Albanie on DeepMind's AGI Safety Approach
Publicado: 6/7/2025 -
44 - Peter Salib on AI Rights for Human Safety
Publicado: 28/6/2025 -
43 - David Lindner on Myopic Optimization with Non-myopic Approval
Publicado: 15/6/2025 -
42 - Owain Evans on LLM Psychology
Publicado: 6/6/2025 -
41 - Lee Sharkey on Attribution-based Parameter Decomposition
Publicado: 3/6/2025 -
40 - Jason Gross on Compact Proofs and Interpretability
Publicado: 28/3/2025 -
38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future
Publicado: 1/3/2025 -
38.7 - Anthony Aguirre on the Future of Life Institute
Publicado: 9/2/2025 -
38.6 - Joel Lehman on Positive Visions of AI
Publicado: 24/1/2025 -
38.5 - Adrià Garriga-Alonso on Detecting AI Scheming
Publicado: 20/1/2025 -
38.4 - Shakeel Hashim on AI Journalism
Publicado: 5/1/2025 -
38.3 - Erik Jenner on Learned Look-Ahead
Publicado: 12/12/2024 -
39 - Evan Hubinger on Model Organisms of Misalignment
Publicado: 1/12/2024 -
38.2 - Jesse Hoogland on Singular Learning Theory
Publicado: 27/11/2024 -
38.1 - Alan Chan on Agent Infrastructure
Publicado: 16/11/2024 -
38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems
Publicado: 14/11/2024 -
37 - Jaime Sevilla on AI Forecasting
Publicado: 4/10/2024 -
36 - Adam Shai and Paul Riechers on Computational Mechanics
Publicado: 29/9/2024 -
New Patreon tiers + MATS applications
Publicado: 28/9/2024
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.
