Start / AXRP – the AI X-risk Research Podcast

AXRP – the AI X-risk Research Podcast

58 avsnitt • Längd: 95 min • Månadsvis

Teknologi • Vetenskap

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.

Avsnitt

45 - Samuel Albanie on DeepMind's AGI Safety Approach

6 juli | 76 min

44 - Peter Salib on AI Rights for Human Safety

28 juni | 202 min

43 - David Lindner on Myopic Optimization with Non-myopic Approval

15 juni | 101 min

42 - Owain Evans on LLM Psychology

6 juni | 134 min

41 - Lee Sharkey on Attribution-based Parameter Decomposition

3 juni | 136 min

40 - Jason Gross on Compact Proofs and Interpretability

28 mars | 156 min

38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future

1 mars | 21 min

38.7 - Anthony Aguirre on the Future of Life Institute

9 februari | 23 min

38.6 - Joel Lehman on Positive Visions of AI

24 januari | 15 min

38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

20 januari | 28 min

38.4 - Shakeel Hashim on AI Journalism

5 januari | 24 min

38.3 - Erik Jenner on Learned Look-Ahead

12 december 2024 | 24 min

39 - Evan Hubinger on Model Organisms of Misalignment

1 december 2024 | 106 min

38.2 - Jesse Hoogland on Singular Learning Theory

27 november 2024 | 18 min

38.1 - Alan Chan on Agent Infrastructure

16 november 2024 | 25 min

Podden AXRP – the AI X-risk Research Podcast är skapad av Daniel Filan. Poddens innehåll och bilderna på den här webbplatsen hämtas med hjälp av poddens RSS-flöde.

Podcastbild

00:00 -00:00

Podcastbild

00:00 -00:00