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
"Machinic Psychopharmacology: Do LLMs Self-Medicate?" by Sid Black, Joseph Bloom
Jun 22, 2026 · 52m
"Can activation verbalizers surface an internal chain of thought?" by oakhu, ryan_greenblatt
Jun 22, 2026 · 1h 19m
"The LLM shoggoth meme is weirder than you think" by HedonicEscalator
Jun 21, 2026 · 13m
[Linkpost] "Guardian Angels: LLM Personalization for Productivity and Security" by gwern
Jun 21, 2026 · 3m
"Gears for political races" by Tom Smith
Jun 19, 2026 · 23m
"A frontier AI company should shut down" by MichaelDickens
Jun 16, 2026 · 4m
"Sympathy for both sides of the egregious misalignment debate" by Steven Byrnes
Jun 13, 2026 · 8m
"PSA: Almost nobody is working on alignment" by Chi Nguyen, peterbarnett
Jun 12, 2026 · 1m
"Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models" by Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask
Jun 11, 2026 · 10m
"Even “illegible” Mythos reasoning traces seem pretty legible" by faul_sname
Jun 11, 2026 · 7m
"Sequent: scale and automation for higher confidence in alignment" by Geoffrey Irving, Alex HT, Jesse Hoogland, Daniel Murfet, Jacob Pfau, Marco Cozzi, Stan van Wingerden
Jun 10, 2026 · 23m
"The Machines Lack Honour" by Raymond Douglas
Jun 10, 2026 · 19m
"My favorite depiction of utopia" by Caleb Biddulph
Jun 4, 2026 · 57m
"Announcing the ARC White-Box Estimation Challenge" by Jacob_Hilton
Jun 3, 2026 · 5m
"Lighthaven East - A Feasibility Study" by JohnofCharleston
Jun 1, 2026 · 42m
"Empowerment, corrigibility, etc. are simple abstractions (of a messed-up ontology)" by Steven Byrnes
Jun 1, 2026 · 31m
"Trees are mostly made of air and a generalizable lesson for AI safety" by zroe1
May 31, 2026 · 7m
"Mnemonic portraits for 19,023 human genes" by Brinedew
May 29, 2026 · 34m
"Cognitive Security as an AI Safety Cause Area" by jsteinhardt
May 27, 2026 · 5m
"theory uplift differentially benefits safety & is massively underpriced" by Yudhister Kumar
May 27, 2026 · 2m
"Women should be able to open things" by KatjaGrace
May 21, 2026 · 3m
"A Year Late, Claude Finally Beats Pokémon" by Julian Bradshaw
May 18, 2026 · 18m
"A relatively brief explanation of Boltzmann Brains" by Eliezer Yudkowsky
May 18, 2026 · 5m
"Automated Alignment is Harder Than You Think" by Aleksandr Bowkis, Marie_DB, Jacob Pfau, Geoffrey Irving