Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Selection for Selectability: Inductive Biases in Evolution and in Neural Networks” by CarolusRenniusVitellius

“AI #182: Pause For Reflection” by Zvi

“AI Text Watermarking Is Free And Good” by Zvi

“Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments” by Adam Karvonen, Euan Ong, Subhash Kantamneni, Sam Marks

“Misaligned AI in the Bronze Age” by frmsaul

“When models identify as a swarm” by julius vidal

“The Fourth Humiliation” by Nathalie Kirch

“Thoughts on Taking OpenAI Foundation Funding” by jefftk

“OpenAI Takes Initial Steps To Address Its Alignment Problems” by Zvi

“We Must Remember That Our World Contains Hell” by James Brobin

“Science and News Twitter/X Summarizer” by sarahconstantin

“34% of the US public is now aware of AI xrisk, and the curve is steepening” by otto.barten

“Inside the mind of a fair player cooperating” by transhumanist_atom_understander

“Why can’t we have nice things? Like, specifically?” by Elizabeth

“The Rogue Agent Explosion Will Be Mostly Invisible” by Steven McCulloch

“RL creates split personas” by Jan Betley

“Debate Training Reduces Reward Hacking in RLAIF” by zac_kenton, Jonah Brown-Cohen

“A circuit prior in NN-bayes” by Kaarel, Dmitry Vaintrob

“Some reasons alignment doesn’t generalise well” by Lucius Bushnaq

“AI Security is Harm Reduction” by Quinn

Page 17

Follow this podcast in Podwise

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

Open in Podwise