What Do We Tell the Humans? Errors, Hallucinations, and Lies in the AI Village
21 Nov 2025
22m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“Evrart Claire: A Case Study in Anti-Epistemology” by Ben Pace
21 Nov 2025
13m
“The Boring Part of Bell Labs” by Elizabeth
21 Nov 2025
25m
“[Paper] Output Supervision Can Obfuscate the CoT” by jacob_drori, lukemarks, cloud, TurnTrout
20 Nov 2025
10m
“Dominance: The Standard Everyday Solution To Akrasia” by johnswentworth
20 Nov 2025
3m
Gemini 3 is Evaluation-Paranoid and Contaminated
20 Nov 2025
15m
“Thinking about reasoning models made me less worried about scheming” by Fabien Roger
20 Nov 2025
22m
“What Is The Basin Of Convergence For Kelly Betting?” by johnswentworth
20 Nov 2025
6m
“In Defense of Goodness” by abramdemski
20 Nov 2025
6m
“Out-paternalizing the government (getting oxygen for my baby)” by Ruby
20 Nov 2025
14m
“Beren’s Essay on Obedience and Alignment” by StanislavKrym
20 Nov 2025
16m
“Preventing covert ASI development in countries within our agreement” by Aaron_Scher
20 Nov 2025
22m
“Current LLMs seem to rarely detect CoT tampering” by Bart Bussmann, Arthur Conmy, Neel Nanda, Senthooran Rajamanoharan, Josh Engels, Bartosz Cywiński
19 Nov 2025
16m
“The Bughouse Effect” by TsviBT
19 Nov 2025
27m
“Serious Flaws in CAST” by Max Harms
19 Nov 2025
14m
“Memories of a British Boarding School #2” by Ben Pace
19 Nov 2025
12m
“Automate, automate it all” by habryka
19 Nov 2025
9m
“How the aliens next door shower” by Ruby
19 Nov 2025
6m
“Victor Taelin’s notes on Gemini 3” by Gunnar_Zarncke
19 Nov 2025
6m
“Anthropic is (probably) not meeting its RSP security commitments” by habryka
19 Nov 2025
8m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.