“An analysis of AI-generated content at the Mechanistic Interpretability Workshop” by Andy Arditi, Ivan Arcuschin
14 Jul 2026
19m
LessWrong · Philosophy
LessWrong (30+ Karma)
Audio narrations of LessWrong posts.
Episodes
“Some Quick Thoughts AI 2027” by Tomás B.
14 Jul 2026
4m
“Prism: Automating Science-of-Evals Research” by LAThomson
14 Jul 2026
31m
“The Flood, by Anton Leicht” by Austin Chen
14 Jul 2026
28m
“Toy Models of Initialisation Effects on RL Dynamics” by Edward James Young, lennie
14 Jul 2026
21m
“Our response to Séb Krier on Plan A” by MKodama, Thomas Larsen
14 Jul 2026
31m
“Better Call Sol The Workhorse” by Zvi
14 Jul 2026
56m
“Pausing AI at human level seems harder than pausing ASAP” by MichaelDickens
13 Jul 2026
4m
“It’s 2030 and we fucked up. How did it happen?” by Boaz Barak
13 Jul 2026
40m
“The Whitney Biennial Should Admit That Emilie Gossiaux Wants to Fuck Their Dog” by jenn
13 Jul 2026
17m
“The US Government may find it difficult to seize control during takeoff” by RobertM
13 Jul 2026
3m
“One-Pager Brief on Pangram Labs” by Sheikh Abdur Raheem Ali
13 Jul 2026
3m
“5 “Plan A” scenarios” by Dave Orr
13 Jul 2026
7m
“Persona Cartography: Charting Language Model Personality Traits in Weight Space” by antonghawthorne, Mariia Koroliuk, Irakli Shalibashvili, sidbaines, Clément Dumas, Konstantinos Voudouris, David Africa
12 Jul 2026
37m
“The Human Substitution Test as a Sanity Check for AI Evaluations” by VojtaKovarik, Tomáš Gavenčiak, Mateusz Bagiński
12 Jul 2026
16m
“The current bottleneck is political will, not research” by Charbel-Raphaël
12 Jul 2026
47m
“Freeing Thucydides” by djbinder
11 Jul 2026
8m
“Additional Research for Plan A” by Thomas Larsen
11 Jul 2026
14m
“Plan A’s problem with dry tinder” by Tom Davidson
11 Jul 2026
15m
“The easiest pathway to control is through executive power” by djbinder
10 Jul 2026
11m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.