Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“The Economics of Transformative AI” by Jan_Kulveit, David Duvenaud, Raymond Douglas

“Small Steps Towards Proving Stochastic → Deterministic Natural Latent” by Alfred Harwood, Jeremy Gillen

“My 2003 Post on the Evolutionary Argument for AI Misalignment” by Wei Dai

“HIA and X-risk part 2: Why it hurts” by TsviBT

“Two Aspects of Situational Awareness: World Modelling & Indexical Information” by David Scott Krueger (formerly: capybaralet)

“Public intellectuals need to say what they actually believe” by Aaron Bergman

“Broadening the training set should help with alignment” by Seth Herd

“Mainstream approach for alignment evals is a dead end” by Igor Ivanov

“How hard is it to inoculate against misalignment generalization?” by Jozdien

“The Evolution Argument Sucks” by peralice

“How AI Is Learning to Think in Secret” by Nicholas Andresen

“On Owning Galaxies” by Simon Lermen

“Exploring Reinforcement Learning Effects on Chain-of-Thought Legibility” by Julian H, RohanS, Baram Sosis, vedant-badoni, The-Turtle

“Oversight Assistants: Turning Compute into Understanding” by jsteinhardt

“Axiological Stopsigns” by JenniferRM

[Linkpost] “The Thinking Machine” by PeterMcCluskey

“Claude Wrote Me a 400-Commit RSS Reader App” by Brendan Long

“The economy is a graph, not a pipeline” by anithite

“Dos Capital” by Zvi

“The Technology of Liberalism” by L Rudolf L

Page 88

Follow this podcast in Podwise

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

Open in Podwise