Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Prompt injection in Google Translate reveals base model behaviors behind task-specific fine-tuning” by megasilverfist

“Parks Aren’t Nature” by Sable

“Voting Results for the 2024 Review” by RobertM

“Honey, I shrunk the brain” by Andy_McKenzie

“Spectral Signatures of Gradual Disempowerment” by Jonas Hallgren

“In (highly contingent!) defense of interpretability-in-the-loop ML training” by Steven Byrnes

“AI benchmarking has a Y-axis problem” by Lizka

“The Simplest Case for AI Catastrophe” by Linch

“What’s the Point of the Math?” by Ashe Vazquez Nuñez

“The nature of LLM algorithmic progress” by Steven Byrnes

“Preparing for a Warning Shot” by Noah Birnbaum

“AI #154: Claw Your Way To The Top” by Zvi

[Linkpost] “METR have released Time Horizons 1.1” by Sean Herrington

“Finding Cruxes: Help Reality Punch You In the Face” by Raemon

“Solemn Courage” by aysja

“Post-AGI Economics As If Nothing Ever Happens” by Jan_Kulveit

“New AI safety funding newsletter” by Bryce Robertson

“Anthropic’s “Hot Mess” paper overstates its case (and the blog post is worse)” by RobertM

″‘Inventing the Renaissance’ Review” by Commander Zander

“Concrete research ideas on AI personas” by nielsrolf, Maxime Riché, Daniel Tan

Page 80

Follow this podcast in Podwise

Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.

Open in Podwise