Episode 46 - Tom Davidson on AI-enabled Coups

My apologies: if you downloaded my most recent episode, my audio cut out around 0:57:40. The issue should be fixed if you re-download the audio. You can also watch on YouTube, which does not have the same problem.

Episode 45 - Samuel Albanie on DeepMind's AGI Safety Approach https://t.co/fdU2zX4IeN

Episode 44 - Peter Salib on AI Rights for Human Safety https://t.co/EBunj8GnkC

Episode 43 - David Lindner on Myopic Optimization with Non-myopic Approval https://t.co/g1YP2B0vyO

Episode 42 - Owain Evans on LLM Psychology https://t.co/TjtCrdyEac

Episode 41 - Lee Sharkey on Attribution-based Parameter Decomposition https://t.co/U5SpftgcNl

Episode 40 - Jason Gross on Compact Proofs and Interpretability

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

https://t.co/OE9AwFPE8K

Episode 38.7 - Anthony Aguirre on the Future of Life Institute. Link to transcript in reply.

https://t.co/gSs9kuv3vc

The AXRP YouTube channel now has topic-based playlists! If there's one particular topic that you'd like to watch episodes about, whether it be governance, agent foundations, or videos that introduce approaches to AI safety, hopefully this will be useful to you :) Link in reply.

https://t.co/UxJpr9LNpM

Episode 38.6 - Joel Lehman on Positive Visions of AI. Link to transcript in next tweet.

https://t.co/99y13lzABE

Episode 38.5 - Adrià Garriga-Alonso on Detecting AI Scheming. Link to transcript in next tweet.

https://t.co/TorUuNMiIS

Episode 38.4 - Shakeel Hashim on AI Journalism. Link to transcript in next tweet.

https://t.co/i9ZNAo53me