AI Safety Radar

Tuesday, 10 November 2026

Videos

Kind All

Length Any

65 videosNewest Most viewed

AXRP

65 videos

50 - Eli Lifland on AI 2027

AXRP3.1k3 mo ago

49 - Caspar Oesterheld on Program Equilibrium

AXRP5888 mo ago

48 - Guive Assadi on AI Property Rights

AXRP4568 mo ago

47 - David Rein on METR Time Horizons

AXRP1.5k10 mo ago

46 - Tom Davidson on AI-enabled Coups

AXRP3831 yr ago

45 - Samuel Albanie on DeepMind's AGI Safety Approach

AXRP6691 yr ago

44 - Peter Salib on AI Rights for Human Safety

AXRP3001 yr ago

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

AXRP4061 yr ago

42 - Owain Evans on LLM Psychology

AXRP1.7k1 yr ago

41 - Lee Sharkey on Attribution-based Parameter Decomposition

AXRP8461 yr ago

40 - Jason Gross on Compact Proofs and Interpretability

AXRP7681 yr ago

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

AXRP4151 yr ago

38.7 - Anthony Aguirre on the Future of Life Institute

AXRP3721 yr ago

38.6 - Joel Lehman on Positive Visions of AI

AXRP3881 yr ago

38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

AXRP5791 yr ago

38.4 - Shakeel Hashim on AI Journalism

AXRP3921 yr ago

38.3 - Erik Jenner on Learned Look-Ahead

AXRP6131 yr ago

39 - Evan Hubinger on Model Organisms of Misalignment

AXRP4.3k1 yr ago

38.2 - Jesse Hoogland on Singular Learning Theory

AXRP8791 yr ago

38.1 - Alan Chan on Agent Infrastructure

AXRP6431 yr ago

38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems

AXRP1.1k1 yr ago

37 - Jaime Sevilla on Forecasting AI

AXRP8522 yr ago

36 - Adam Shai and Paul Riechers on Computational Mechanics

AXRP1k2 yr ago

New Patreon tiers + MATS applications

AXRP1512 yr ago

35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

AXRP5052 yr ago

34 - AI Evaluations with Beth Barnes

AXRP1.6k2 yr ago

33 - RLHF Problems with Scott Emmons

AXRP6472 yr ago

32 - Understanding Agency with Jan Kulveit

AXRP6272 yr ago

31 - Singular Learning Theory with Daniel Murfet

AXRP1.9k2 yr ago

30 - AI Security with Jeffrey Ladish

AXRP1.1k2 yr ago

29 - Science of Deep Learning with Vikrant Varma

AXRP6522 yr ago

28 - Suing Labs for AI Risk with Gabriel Weil

AXRP3192 yr ago

27 - AI Control with Buck Shlegeris and Ryan Greenblatt

AXRP2.3k2 yr ago

26 - AI Governance with Elizabeth Seger

AXRP2982 yr ago

25 - Cooperative AI with Caspar Oesterheld

AXRP3723 yr ago

mechanistic anomaly detection (animated explanation)

AXRP2703 yr ago

24 - Superalignment with Jan Leike

AXRP2k3 yr ago

23 - Mechanistic Anomaly Detection with Mark Xu

AXRP3133 yr ago

Paul Christiano on AI (animated)

AXRP4843 yr ago

22 - Shard Theory with Quintin Pope

AXRP7013 yr ago

21 - Interpretability for Engineers with Stephen Casper

AXRP3173 yr ago

20 - 'Reform' AI Alignment with Scott Aaronson

AXRP1k3 yr ago

How do neural networks do modular addition?

AXRP7833 yr ago

What is mechanistic interpretability? Neel Nanda explains.

AXRP10k3 yr ago

Vanessa Kosoy on the Monotonicity Principle

AXRP4323 yr ago

19 - Mechanistic Interpretability with Neel Nanda

AXRP1.7k3 yr ago

18 - Concept Extrapolation with Stuart Armstrong

AXRP1254 yr ago

17 - Training for Very High Reliability with Daniel Ziegler

AXRP1214 yr ago