LessWrong (Curated & Popular)
Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.
If you'd like more, subscribe to the “Lesswrong (30+ karma)” feed.
Episodes
890 episodes
"Model access for third-parties — it’s a big deal!" by Cleo Nardo
Over time, there might be an increasingly large gap between insider model access and outsider model access. By insiders, I mean employees at the frontier lab.[1] By "outsiders", I mean external safety researchers, third-party auditors, and other ...
"Who Got Breasts First and How We Got Them" by rba
It really is Sydney Sweeney's world, and we’re all just living in it. Human female breasts are an evolutionary mystery along several dimensions. First, breast permanence is unique to humans. All other mammals develop breast prominence dur...
"The worthlessness of vitamin D is mildly exaggerated" by dynomight
For a while there, many people thought vitamin D was magical—that it could improve bones, the heart, infections, cancer, heart disease, longevity, even mental health. But among people I respect, opinion is now overwhelmingly that taking vitamin D...
"What is up with e/acc?" by KatjaGrace
I was chatting with someone tonight about a planned documentary; they had interviewed various people in AI safety, and we got to discussing who they should talk to from an e/acc (effective accelerationist) perspective. I also watched The AI Doc r...
"Existential AI safety needs an effective social movement. PauseAI is building it" by Maxime Fournes, Espedair Street
Note: this post is about PauseAI, not PauseAI US, which is a distinct entity with a different leadership team and approach. This post was written by Matilda da Rui and Maxime Fournes, with significant contributions from Benjamin Schmidt (...
"Surprising facts about the slave trade" by Joseph Miller
1. The obstacle to abolition was not the economic system, but an industry lobby. I had always imagined the British abolitionist movement to be a broad battle between an unstoppable moral imperative and an immovable econom...
"AI catastrophe: more like a genocide than a thought experiment" by KatjaGrace
A notable fraction of people respond to hearing about existential risk from AI by saying they don’t really care if everyone dies. I think the idea is often along the lines of ‘well if we are all dead, then there's nobody to be unhappy about it’.<...
"AI pause: the case for ASAP" by KatjaGrace
I often hear people say they think we should pause AI at some point, but not yet. Their basis for this seems to be some combination of: If we pause at the last possible moment, then we will have the most advanced AI possible dur...
"The Invisible Side of AI Governance" by Charbel-Raphaël
Tldr: Most strategic writing on AI governance on LessWrong describes the outsider game, which is most often visible: press, statements, open letters. Here I want to describe the other, invisible half: the insider work within ministerial cabinets ...
"A Theory of Prompt Injection (and why you should study roles)" by Charles Ye, softboiledheart
Summary We've been building a theory of how prompt injections work under the hood.We show it comes down to how LLMs perceive roles (the humble chat template tags).We...
"Machinic Psychopharmacology: Do LLMs Self-Medicate?" by Sid Black, Joseph Bloom
Sid Black, Joseph Bloom UK AISI, Model Transparency Team Epistemic status: Most experiments were run over a period of ~2-3 days during a hackathon at UK AISI, and were fairly heavily vibe coded. Expect some of this to be rough aro...
"Can activation verbalizers surface an internal chain of thought?" by oakhu, ryan_greenblatt
We introduce an evaluation for activation verbalizers: can they surface a target model's reasoning as it solves a math problem in a single forward pass? For open-weight NLAs, the answer seems to be: "possibly, but definitely not reliably".
"The LLM shoggoth meme is weirder than you think" by HedonicEscalator
This article contains spoilers for At the Mountains of Madness, The Case of Charles Dexter Ward, and other works by H. P. Lovecraft. In 1931, Claude Mythos visited Lovecraft in a dream. From seething seas of stochastic froth it em...
[Linkpost] "Guardian Angels: LLM Personalization for Productivity and Security" by gwern
This is a link post. Powerful LLMs will be deployed at global scale in the next few years, and will dominate the Internet, and increasingly, ordinary life. As of mid-2026, there is no coherent vision for how knowledge professionals, or ordinary pe...
"Gears for political races" by Tom Smith
In the past few years, many people around me have tried to convince me that US electoral politics is important. But like many other people in the community, I’ve been suspicious of many of the high-level arguments that I’ve heard. It felt like pe...
"A frontier AI company should shut down" by MichaelDickens
Cross-posted from my website. Prior discussion: niplav's shortform (2025); Planning for Extreme AI Risks (2025) by Joshua Clymer A frontier AI company (any one, I don't care which) should close shop and make an announcement alon...
"Sympathy for both sides of the egregious misalignment debate" by Steven Byrnes
On one side of this debate is Yudkowsky & Soares, who think that (if AI progress continues) we’re on a direct path to egregiously-misaligned, scheming, out-of-control, rogue superintelligence (ASI), not even slightly nice, in the absence of y...
"PSA: Almost nobody is working on alignment" by Chi Nguyen, peterbarnett
People often assume that a large fraction of the AI safety community works on alignment. As far as we're aware, this is not true. Most people are not working on making sure superintelligent AIs are aligned with human values or follow human instru...
"Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models" by Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask
(see full author list at the end) PAPER LINK About a year ago, METR showed that the length of tasks frontier models can reliably complete doubles every few months. A related safety-relevant question is this: what length of tasks c...
"Even “illegible” Mythos reasoning traces seem pretty legible" by faul_sname
The Claude Fable 5/Mythos 5 System Card has a section in which they talk about illegible reasoning, and provide an "extreme" example thereof. Models developing their own uninterpretable, unmonitorable internal language has been a major th...
"Sequent: scale and automation for higher confidence in alignment" by Geoffrey Irving, Alex HT, Jesse Hoogland, Daniel Murfet, Jacob Pfau, Marco Cozzi, Stan van Wingerden
Alignment is not on track Artificial superintelligence (ASI) may be developed in the next few years. It is unclear whether alignment is on track to be ready on the same timeframe. At a minimum, the empirical programs at A...
"The Machines Lack Honour" by Raymond Douglas
The battle lines of the AI morality debate are being laid down. On one side you have the ChatGPT dogma: AI as mere tools with no real preferences or even beliefs. On the other you have the twitter AI whisperers: AIs as complex beings with rich pe...
"My favorite depiction of utopia" by Caleb Biddulph
For those who are trying to bring about a glorious transhuman utopia with the help of hopefully-aligned ASI, I think it's worth thinking explicitly about what utopia might actually look like and where it's likely to fall short. To that en...
"Announcing the ARC White-Box Estimation Challenge" by Jacob_Hilton
ARC has teamed up with AIcrowd to launch the ARC White-Box Estimation Challenge, a contest to improve upon our estimation algorithms for random MLPs. The warm-up round begins this week, and later rounds will have a total prize pool of at least $1...
"Lighthaven East - A Feasibility Study" by JohnofCharleston
As a bureaucrat, my role is to annoy my friends. Someone voices an idea, “Wouldn’t it be nice if…” or “I wonder if we could…” I make a note. I do some estimates. If it pencils out, I’ll bring it back up, week after week. The discussions are fun, ...