LessWrong (Curated & Popular)
LessWrong (Curated & Popular)
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.
460 episodes • 0 archived •
“Auditing language models for hidden objectives” by Sam Marks, Johannes Treutlein, dmz, Sam Bowman, Hoagy, Carson Denison, Akbir Khan, Euan Ong, Christopher Olah, Fabien Roger, Meg, Drake Thomas, Adam Jermyn, Monte M, evhub
17 hours ago
24 mins
“The Most Forbidden Technique” by Zvi
March 14
32 mins
“Trojan Sky” by Richard_Ngo
March 13
22 mins
“OpenAI:” by Daniel Kokotajlo
March 11
7 mins
“How Much Are LLMs Actually Boosting Real-World Programmer Productivity?” by Thane Ruthenis
March 9
7 mins
“So how well is Claude playing Pokémon?” by Julian Bradshaw
March 9
9 mins
“Methods for strong human germline engineering” by TsviBT
March 7
18 secs
“Have LLMs Generated Novel Insights?” by abramdemski, Cole Wyeth
March 6
3 mins
“A Bear Case: My Predictions Regarding AI Progress” by Thane Ruthenis
March 6
18 mins
“Statistical Challenges with Making Super IQ babies” by Jan Christian Refsgaard
March 5
17 mins