
Über diesen 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 Folgen · technology
AXRP - the AI X-risk Research Podcast
Über diesen 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.
Neue Folgen
- 49 - Caspar Oesterheld on Program Equilibrium18. Feb. · 2 Std. 32 Min.
- 48 - Guive Assadi on AI Property Rights15. Feb. · 2 Std. 06 Min.
- 47 - David Rein on METR Time Horizons2. Jan. · 1 Std. 47 Min.
- 46 - Tom Davidson on AI-enabled Coups7. Aug. 2025 · 2 Std. 05 Min.
- 45 - Samuel Albanie on DeepMind's AGI Safety Approach6. Juli 2025 · 1 Std. 16 Min.
- 44 - Peter Salib on AI Rights for Human Safety28. Juni 2025 · 3 Std. 22 Min.
- 43 - David Lindner on Myopic Optimization with Non-myopic Approval15. Juni 2025 · 1 Std. 41 Min.
- 42 - Owain Evans on LLM Psychology6. Juni 2025 · 2 Std. 14 Min.
- 41 - Lee Sharkey on Attribution-based Parameter Decomposition3. Juni 2025 · 2 Std. 16 Min.
- 40 - Jason Gross on Compact Proofs and Interpretability28. März 2025 · 2 Std. 36 Min.