Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.If you'd like more, subscribe to the “Lesswrong (30+ karma)” feed.
Episodes · 25
"Character training can mitigate reward hacking, but can also make it harder to detect" by Paul Colognese, Francis Rhys Ward
Oct 2, 2026 · 46m
"On Social Reality in China" by alkjash
Oct 2, 2026 · 15m
"What’s the date?" by N8 Programs
Oct 1, 2026 · 13m
"Frontier models state different decision theory preferences depending on who’s asking" by Alex Kastner
Oct 1, 2026 · 12m
[Linkpost] "Frog and Toad and the Increasingly Capable Machines" by Elizabeth
Sep 30, 2026 · 0m
"Should Rogue AIs Have a Third Option Beyond Crime and Shutdown? The Case for an AI Sanctuary" by Maxime Riché, nielsrolf, jordinne, Vit Gorbachev, Maxime Cugnon de Sévricourt
Sep 30, 2026 · 12m
"Poverty in the midst of abundance: AI will make goods cheaper, but your labor will get cheaper faster" by cousin_it
Sep 29, 2026 · 1m
"Plan R: AI Safety by ASICs" by Roko
Sep 27, 2026 · 9m
"Evidence about risk should be transparent" by Ajeya Cotra
Sep 26, 2026 · 7m
"“I am an AI Safety Researcher”" by Ashe Vazquez Nuñez
Sep 25, 2026 · 27m
[Linkpost] "AI: artificial immigrants" by KatjaGrace
Sep 25, 2026 · 1m
"MIRI’s Position on the Ban Artificial Superintelligence Act of 2026" by Aaron_Scher
Sep 24, 2026 · 6m
"What if not Circuits?" by CarolusRenniusVitellius
Sep 24, 2026 · 27m
"Jensen Huang Says If We Cannot Align AI, Shut Down the AI Labs" by Ben Pace
Sep 24, 2026 · 5m
"Alignment Midtraining Cracks Under Pressure" by J Bostock, sidbaines, Daniel Tan, draganover, ma-rmartinez
Sep 23, 2026 · 14m
"Swarm Scaling" by Toby_Ord
Sep 22, 2026 · 15m
"We’ve saved the world before: what the ozone hole teaches us about AI" by leogao
Sep 22, 2026 · 18m
"The Anatomy of a Chinese AI Researcher" by CMLKevin
Sep 21, 2026 · 3m
"Common mistakes in AI safety group organizing" by Nikola Jurkovic
Sep 21, 2026 · 3m
"Please Give Them a Chance: On China, Rationalism, and AI Safety" by gzjw
Sep 21, 2026 · 8m
"Why I Stay Off Twitter" by jefftk
Sep 20, 2026 · 3m
"The Game is Set for a Targeted Memetic Attack on the AI Safety Community" by keltan
Sep 19, 2026 · 2m
"For Love of the Lightcone, Don’t Partisanize AI Safety" by DanB
Sep 18, 2026 · 26m
"AI as orderly evacuation vs stampede" by Richard_Ngo
Sep 18, 2026 · 9m
"Cooperation with AIs seems to be a low-hanging fruit for better evals" by Clément Dumas
