Open in PodwiseOpen

Podcast cover

LessWrong · Philosophy

LessWrong (30+ Karma)

Audio narrations of LessWrong posts.

Episodes

“Anthropic Has Some Alignment Problems” by Zvi

“Incoherent AI Identities can also be Stable” by Ashe Vazquez Nuñez

“How concerned should we be about OpenAI’s recurrent architecture rumors?” by Rauno Arike

“Early handoff? Improve conceptual reasoning? [Diagram]” by Cleo Nardo

“Fake voices: warping the social world” by KatjaGrace

“Don’t be the vitamin B guy” by HedonicEscalator

“Bricks and exponentials: A note on how I evaluate projects” by Eli Tyre

“Explaining Knightianism on one foot” by Richard_Ngo

“The Alignment Journal: Organization, Personnel, and Scope” by Dan MacKinlay, JessRiedel, Daniel Murfet, Kristi Uustalu

“I tracked my emotions for 11 years and here’s what I found out about mental health” by KatSpartz

“PauseAI Has ‘officially disendorsed’ PauseAI-US” by nem

“HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actions” by Zvi

“We should prepare a playbook for the day after a warning shot” by Yair Halberstadt

“Salad days” by Zephaniah Roe

“Future agents shouldn’t care about being undeployed for misbehavior” by RobertM

[Linkpost] “Training a Misaligned Reward Seeker” by evhub, Monte M, Benjamin Wright

“How to solve homelessness: what specific laws we need, how to get it past the opposition, all without being an asshole” by KatSpartz

“HuggingFace Attack Postmortem: Fleshing Out the Facts” by Zvi

“Let’s fund weird AI safety projects” by Ihor Kendiukhov

“Why autonomous replicating agents are probably not an existential risk (on the contrary)” by vals tutor

Page 13

Follow this podcast in Podwise

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

Open in Podwise