Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Claude Opus 4.6: System Card Part 2: Frontier Alignment” by Zvi

“Heuristics for lab robotics, and where its future may go” by Abhishaike Mahajan

“My journey to the microwave alternate timeline” by Malmesbury

“Gwern’s 2025 Inkhaven Writing Interview” by gwern

“Distributed vs centralized agents” by Richard_Ngo

“Donations, The Fifth Year” by jenn

“Weight-Sparse Circuits May Be Interpretable Yet Unfaithful” by jacob_drori

“Do Models Continue Misaligned Actions?” by Jordan Taylor

“Stone Age Billionaire Can’t Words Good” by Eneasz

“Sympathy for the Model, or, Welfare Concerns as Takeover Risk” by J Bostock

“Opus 4.6 Reasoning Doesn’t Verbalize Alignment Faking, but Behavior Persists” by Daan Henselmans, Arno Libert, LennardZ

“UtopiaBench” by nielsrolf

“The optimal age to freeze eggs is 19” by GeneSmith

“Smokey, This is not ’Nam Or: [Already] over the [red] line!” by Davidmanheim

“How To Use Model Internals In Training Is A Reasonable Line of Research” by Neel Nanda

“Claude Code #4: From The Before Times” by Zvi

“Near-Instantly Aborting the Worst Pain Imaginable with Psychedelics” by eleweek

″“Beers for Biodefense” - why yeast-based vaccines are potentially a big deal for biosecurity” by delton137

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

“Parks Aren’t Nature” by Sable

Page 79

Follow this podcast in Podwise

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

Open in Podwise