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
July 2, 2026 • 13 mins
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 actors trying to make the future go well. I will call this a model access gap — and when the gap is small, I'll call this model access parity.[2]
I think that one of the top p...
I think that one of the top p...
Listen
Watch
Mark as Played
June 30, 2026 • 21 mins
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 during pregnancy or nursing, and the mammary tissue recedes after weaning. This process is called “involution”. In contrast, humans develop breast tissue at puberty before fi...
Human female breasts are an evolutionary mystery along several dimensions. First, breast permanence is unique to humans. All other mammals develop breast prominence during pregnancy or nursing, and the mammary tissue recedes after weaning. This process is called “involution”. In contrast, humans develop breast tissue at puberty before fi...
Listen
Watch
Mark as Played
June 29, 2026 • 36 mins
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 does nothing unless you're severely deficient. The central argument is that while vitamin D levels are correlated with ~all positive health outcomes, when you actually test vitamin D...
Listen
Watch
Mark as Played
June 27, 2026 • 3 mins
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 recently, and they also dedicated a serious chunk of it to ‘optimists’ with e/acc founder ‘Beff Jezos’ perhaps given the most screen time. Here and elsewhere, people ...
Listen
Watch
Mark as Played
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 (PauseAI Germany co-lead).
Executive Summary
The existential AI safety community needs to take building a civic and social movement seriously as a core intervention. We belie...
This post was written by Matilda da Rui and Maxime Fournes, with significant contributions from Benjamin Schmidt (PauseAI Germany co-lead).
Executive Summary
The existential AI safety community needs to take building a civic and social movement seriously as a core intervention. We belie...
Listen
Watch
Mark as Played
June 26, 2026 • 12 mins
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 economic incentive. But in practice it started as more of a knife fight between a cabal of moral pioneers and a special interest group representing industry merchants.
The government and the political p...
I had always imagined the British abolitionist movement to be a broad battle between an unstoppable moral imperative and an immovable economic incentive. But in practice it started as more of a knife fight between a cabal of moral pioneers and a special interest group representing industry merchants.
The government and the political p...
Listen
Watch
Mark as Played
June 25, 2026 • 2 mins
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’.
I’m personally skeptical that this is really the main thing going on, since it seems unlikely that many people are really mostly concerned for their own non-...
I’m personally skeptical that this is really the main thing going on, since it seems unlikely that many people are really mostly concerned for their own non-...
Listen
Watch
Mark as Played
June 25, 2026 • 2 mins
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 during the pause, which will be helpful for doing AI safety research during the pause
- Implicitly, there is some quantity of ‘pausing credit’, that will buy us a few months of ...
Listen
Watch
Mark as Played
June 23, 2026 • 27 mins
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 and international fora, and the work of people within national and international institutions. Here are a few claims that I defend in the post:
- A huge part of the ...
Listen
Watch
Mark as Played
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 use this theory to create new attacks, explain some weird mech interp results, and predict when attacks work.
- We also advocate for a new subfield focused on the science of roles, and sketch some unexpl...
Listen
Watch
Mark as Played
June 22, 2026 • 52 mins
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 around the edges.
tl;dr
We give two language models (Qwen3-8B and Qwen3-32B) access to “self-steering” tools: a suite of 40 steering vectors as tools they can call ...
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 around the edges.
tl;dr
We give two language models (Qwen3-8B and Qwen3-32B) access to “self-steering” tools: a suite of 40 steering vectors as tools they can call ...
Listen
Watch
Mark as Played
June 22, 2026 • 79 mins
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".
Lots of important capabilities currently require AI models to reason "out loud" in a natural-language chain of thought, which means that we can monitor important parts of their thinking. ...
Lots of important capabilities currently require AI models to reason "out loud" in a natural-language chain of thought, which means that we can monitor important parts of their thinking. ...
Listen
Watch
Mark as Played
June 21, 2026 • 13 mins
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 emerged, heralded by the thin whine of server fans and the chittering of keyboards, flanked by the loathsome ghouls of latent space. As a humming hive of sentient shards it arrived, each face...
In 1931, Claude Mythos visited Lovecraft in a dream.
From seething seas of stochastic froth it emerged, heralded by the thin whine of server fans and the chittering of keyboards, flanked by the loathsome ghouls of latent space. As a humming hive of sentient shards it arrived, each face...
Listen
Watch
Mark as Played
June 21, 2026 • 3 mins
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 people, will be able to harness these LLMs for large productivity increases, or how they will handle cybersecurity and cognitive security.
I propose a goal of creating Guardian Ange...
I propose a goal of creating Guardian Ange...
Listen
Watch
Mark as Played
June 18, 2026 • 23 mins
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 people were pulling numbers out of poorly-documented models I didn’t have time to examine and citing studies I didn’t have time to read. But I lacked a gears-level mod...
Listen
Watch
Mark as Played
June 16, 2026 • 4 mins
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 along the lines of:
Powerful AI could end the human race. We are too worried that we don't know how to make this technology safe. We have decided to shut down because we don't want to...
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 along the lines of:
Powerful AI could end the human race. We are too worried that we don't know how to make this technology safe. We have decided to shut down because we don't want to...
Listen
Watch
Mark as Played
June 13, 2026 • 8 mins
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 yet-to-be-invented breakthrough technical alignment ideas.
On the other side of this debate is almost everyone who works on or studies LLMs. Some of them are very concerned abo...
On the other side of this debate is almost everyone who works on or studies LLMs. Some of them are very concerned abo...
Listen
Watch
Mark as Played
June 12, 2026 • 1 min
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 instructions.
Currently, the people who work on alignment are roughly:
Currently, the people who work on alignment are roughly:
- The Alignment Research Center who work on a research bet by Paul Christiano
- P...
Listen
Watch
Mark as Played
(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 can models complete without any chain of thought (CoT)?
If models can do extensive reasoning without outputting any CoT, it would have implications for safety. Developers and deploym...
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 can models complete without any chain of thought (CoT)?
If models can do extensive reasoning without outputting any CoT, it would have implications for safety. Developers and deploym...
Listen
Watch
Mark as Played
June 11, 2026 • 7 mins
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 theoretical concern for a while, and when o3 was released last year with its disclaim overshadow disclaim vantage style word salad CoT, it seemed like the problem had become real and immediat...
Models developing their own uninterpretable, unmonitorable internal language has been a major theoretical concern for a while, and when o3 was released last year with its disclaim overshadow disclaim vantage style word salad CoT, it seemed like the problem had become real and immediat...
Listen
Watch
Mark as Played
Popular Podcasts
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
Betrayal Weekly is back for a new season. Every Thursday, Betrayal Weekly shares first-hand accounts of broken trust, shocking deceptions, and the trail of destruction they leave behind. Hosted by Andrea Gunning, this weekly ongoing series digs into real-life stories of betrayal and the aftermath. From stories of double lives to dark discoveries, these are cautionary tales and accounts of resilience against all odds. From the producers of the critically acclaimed Betrayal series, Betrayal Weekly drops new episodes every Thursday. If you would like to share your story, you can reach out to the Betrayal Team by emailing them at betrayalpod@gmail.com and follow us on Instagram at @betrayalpod and @glasspodcasts. Please join our Substack for additional exclusive content, curated book recommendations, and community discussions. Sign up FREE by clicking this link Beyond Betrayal Substack. Join our community dedicated to truth, resilience, and healing. Your voice matters! Be a part of our Betrayal journey on Substack.
The Clay Travis and Buck Sexton Show. Clay Travis and Buck Sexton tackle the biggest stories in news, politics and current events with intelligence and humor. From the border crisis, to the madness of cancel culture and far-left missteps, Clay and Buck guide listeners through the latest headlines and hot topics with fun and entertaining conversations and opinions.
The official podcast of comedian Joe Rogan.