Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“AIs will be used in “unhinged” configurations” by Arthur Conmy

“Can models gradient hack SFT elicitation?” by Patrick Leask, Charlie Griffin

“The Lethal Reality Hypothesis” by Ihor Kendiukhov

“The Day After Move 37” by Eneasz

“Less Dead” by Aurelia

“What do we know about AI company employee giving?” by David Scott Krueger (formerly: capybaralet)

“AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors” by abhayesian

“Interview with Steven Byrnes on His Mainline Takeoff Scenario” by Liron

“Letting Claude do Autonomous Research to Improve SAEs” by chanind

“Don’t Let LLMs Write For You” by JustisMills

“Economic efficiency often undermines sociopolitical autonomy” by Richard_Ngo

“Gemma Needs Help” by Anna Soligo

“Not Loving Liking What You See” by Tomás B.

“The case for satiating cheaply-satisfied AI preferences” by Alex Mallen

“The case for AI safety capacity-building work” by abergal

“Claude Code, Claude Cowork and Codex #5” by Zvi

“Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation” by Bartosz Cywiński, Helena Casademunt, Khoi Tran, aryaj, Sam Marks, Neel Nanda

“Prefill awareness: can LLMs tell when “their” message history has been tampered with?” by David Africa

“Prologue to Terrified Comments on Claude’s Constitution” by Zack_M_Davis

“Promoting enmity and bad vibes around AI safety” by Andrew_Critch

Page 70

Follow this podcast in Podwise

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

Open in Podwise