“AI #191: The Hackening Begins” by Zvi
23 Oct 2026
1h 26m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“Wah wah wah wah do more AI R&D” by TsviBT
23 Oct 2026
10m
“Monitorability evaluations and policy proposals” by evhub
22 Oct 2026
8m
“Greater good arguments in AI safety” by Dean Valentine
22 Oct 2026
7m
“The Alignment Journal: Our Approach and Related Projects” by Dan MacKinlay, Daniel Murfet, JessRiedel, david reinstein, Agustín Covarrubias, Tim G. J. Rudner, Seth Lazar, Kristi Uustalu, David Udell
22 Oct 2026
40m
“How does Fable 5.1 hide messages in images?” by Nikita Kezin, 13ryanC, hronir, James Chua
22 Oct 2026
13m
“Neural nets are exceptionally vulnerable to goal self-hack” by Stuart_Armstrong
22 Oct 2026
4m
“Autonomous researchers will strain peer review, funding, and oversight” by Jason Fantl
22 Oct 2026
14m
“Misaligned!” by Zvi
22 Oct 2026
20m
“Why I’m becoming a professor in AI safety in Beijing” by Buddenbroke
21 Oct 2026
18m
“Circuit priors in NN-bayes: more results” by Kaarel, Dmitry Vaintrob
21 Oct 2026
2m
“Data as particles and mean field theory abound” by Max Hennick
21 Oct 2026
34m
“Anthropic Does Not Understand Why Its Draft Bill Was Unacceptable and Troubling” by Zvi
21 Oct 2026
26m
“How I discovered an Exoplanet & the science apocalypse” by jonathanbreitg
21 Oct 2026
19m
“ACS Infra: free access to large base models for LLM psychology research” by Martin Vaněk, Jan_Kulveit, Ondřej Havlíček, Ivar Frisch, Veronika_H, vgel, Raymond Douglas, Charlie Amis, Faw Ali
20 Oct 2026
7m
“A brief(ish) introduction to LM psychology” by Raymond Douglas, Jan_Kulveit
20 Oct 2026
47m
“There Will Be Hells” by Stephen Martin
20 Oct 2026
14m
“1000 Years of AI Safety” by Simon Steshin, Grigory Reznikov
20 Oct 2026
36m
“AI as a Normal Technology should be a vision” by June Jimenez
20 Oct 2026
16m
“Gradient Routing Localizes and Removes Unintended Behaviors in RL” by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud
19 Oct 2026
13m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.