Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Text Compression Can Help Secure Model Weights” by Roy Rinberg

“AI #158: The Department of War” by Zvi

“Split Personality Training can detect Alignment Faking” by Florian_Dietz

“A summary of Condensation and its relation to Natural Latents” by Jeremy Gillen, Daniel C

“Maybe there’s a pattern here?” by dynomight

“Is GDP a Kind of Factory? d Draft” by Benquo

“Mass surveillance, red lines, and a crazy weekend” by Boaz Barak

“Sacred values of future AIs” by Cleo Nardo

“Physics of RL: Toy scaling laws for the emergence of reward-seeking” by AlexMeinke

“Mass Surveillance w/ LLMs is the Default Outcome. Contracts Won’t Change That.” by Logan Riggs

“OpenAI’s surveillance language has many potential loopholes and they can do better” by Tom Smith

“A Tale of Three Contracts” by Zvi

“I’m confused by the change in the METR trend” by Expertium

“I Had Claude Read Every AI Safety Paper Since 2020” by Corm

“Game Recognizes Game” by eva_

“An Alignment Journal: Coming Soon” by Dan MacKinlay, JessRiedel, Edmund Lau, Daniel Murfet, Scott Aaronson, Jan_Kulveit

“Current activation oracles are hard to use” by aryaj, Senthooran Rajamanoharan, Neel Nanda

“In-context learning of representations can be explained by induction circuits” by Andy Arditi

“Epstein and my world model” by Eye You

“Secretary of War Tweets That Anthropic is Now a Supply Chain Risk” by Zvi

Page 72

Follow this podcast in Podwise

Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.

Open in Podwise