Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Should control down-weight negative net-sabotage-value threats?” by Fabien Roger

“Precedents for the Unprecedented: Historical Analogies for Thirteen Artificial Superintelligence Risks” by James_Miller

“Powerful misaligned AIs may be extremely persuasive, especially absent mitigations” by Cody Rushing

“When Will They Take Our Jobs?” by Zvi

“Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought” by Riya Tyagi, daria, Arthur Conmy, Neel Nanda

“Test your interpretability techniques by de-censoring Chinese models” by Khoi Tran, aryaj, Senthooran Rajamanoharan, Neel Nanda

“Reflections on TA-ing Harvard’s first AI safety course” by Roy Rinberg

“GD Roundup #4 - inference, monopolies, and AI Jesus” by Raymond Douglas

“Deeper Reviews for the top 15 (of the 2024 Review)” by Raemon

“Why Motivated Reasoning?” by johnswentworth

“Why we are excited about confession!” by boazbarak, Gabriel Wu, Manas Joglekar

“Claude Coworks” by Zvi

“Apply to Vanessa’s mentorship in PIBBSS” by Vanessa Kosoy

“Backyard cat fight shows Schelling points preexist language” by jchan

“Contra Dance as a Model For Post-AI Culture” by jefftk

“What Happens When Superhuman AIs Compete for Control?” by steveld

“When does competition lead to recognisable values?” by Jan_Kulveit, beren, David Duvenaud, Raymond Douglas

“Lies, Damned Lies, and Proofs: Formal Methods are not Slopless” by Quinn, Max von Hippel

“Brief Explorations in LLM Value Rankings” by Tim Hua, Josh Engels, Neel Nanda, Senthooran Rajamanoharan

“Tensor-Transformer Variants are Surprisingly Performant” by Logan Riggs

Page 86

Follow this podcast in Podwise

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

Open in Podwise