LessWrong

LessWrong (Curated & Popular)

Enjoy audio narrations of top posts from LessWrong, highlighting curated content and popular discussions. Subscribe for more engaging insights and ideas.

Listen on Apple Podcasts

“A Three-Layer Model of LLM Psychology” by Jan_Kulveit

18 mins • Jan 26, 2025

Recent Episodes

Jan 26, 2025

“A Three-Layer Model of LLM Psychology” by Jan_Kulveit

18 mins

Jan 24, 2025

“Training on Documents About Reward Hacking Induces Reward Hacking” by evhub

5 mins

Jan 24, 2025

“AI companies are unlikely to make high-assurance safety cases if timelines are short” by ryan_greenblatt

25 mins

Jan 24, 2025

“Mechanisms too simple for humans to design” by Malmesbury

29 mins

Jan 22, 2025

“The Gentle Romance” by Richard_Ngo

1 mins

Language
English
Country
United States
Feed Host
Request an Update
Updates may take a few minutes.