
Over deze podcast
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.
63 afleveringen · technology
AXRP - the AI X-risk Research Podcast
Over deze podcast
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.
Recente afleveringen
- 49 - Caspar Oesterheld on Program Equilibrium18 feb · 2 u 32 min
- 48 - Guive Assadi on AI Property Rights15 feb · 2 u 06 min
- 47 - David Rein on METR Time Horizons2 jan · 1 u 47 min
- 46 - Tom Davidson on AI-enabled Coups7 aug 2025 · 2 u 05 min
- 45 - Samuel Albanie on DeepMind's AGI Safety Approach6 jul 2025 · 1 u 16 min
- 44 - Peter Salib on AI Rights for Human Safety28 jun 2025 · 3 u 22 min
- 43 - David Lindner on Myopic Optimization with Non-myopic Approval15 jun 2025 · 1 u 41 min
- 42 - Owain Evans on LLM Psychology6 jun 2025 · 2 u 14 min
- 41 - Lee Sharkey on Attribution-based Parameter Decomposition3 jun 2025 · 2 u 16 min
- 40 - Jason Gross on Compact Proofs and Interpretability28 mrt 2025 · 2 u 36 min