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.
Listen in the Podli app 🎧
Follow your favourite podcasts, listen offline and in the car with CarPlay and Android Auto, and always pick up where you left off. Free to try.
Nov 13, 2026 · 5:12
How do you get a friend to leave an abusive relationship? If you talk to people who work at women's shelters, they will tell you, but there is something resigned about the way…
Nov 13, 2026 · 9:04
Science is caught between Law and Chaos. On the side of Law: Things should make explicit sense to your deliberate reasoning ("system-two"). If you just have a "vibe" about how…
Nov 13, 2026 · 23:20
Summary Timelines to superintelligence without any slowdown interventions look very short now, perhaps with a median in early 2028. AI will likely dramatically automate and…
Nov 13, 2026 · 9:39
Audio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand. Heavily…
Nov 12, 2026 · 2:17
This is a link post. METR recently estimated that Anthropic is now making AI progress about twice as fast as its historical rate (they would not be surprised by anything from…
Nov 12, 2026 · 5:36
Note: As with any research done in a couple of days, this is all very tentative. I understand, intellectually, that if you talk about some ability that current AIs don't have,…
Nov 12, 2026 · 10:48
We were surprised to notice that the Gemini 4 Safety report seems to mention in passing that they train on the chain of thought: “Some components of the RL training procedure do…
Nov 11, 2026 · 22:11
If you ask modern frontier LLMs (without search, through the API) a fairly mundane question: How do Eliezer Yudkowsky and Nate Soares think current LLMs like you should be…
Nov 11, 2026 · 12:08
There's a familiar feeling for any Super Smash Bros player: your stocks are low and your damage is high, even against a weaker opponent, so now you have to actually play to win.…
Nov 11, 2026 · 5:18
Tl;dr: Lightcone Commons’ first funding round is complete! 17 evaluators made funding recommendations, including Zvi Mowshowitz, Scott Siskind and Eliezer Yudkowsky. 23 funders…
Nov 11, 2026 · 22:04
I'm Aurelia Song and I founded the preservation company Nectome. We do planned whole-body end-of-life preservation for future revival. That is, terminally-ill people come to us…
Nov 11, 2026 · 19:56
When sports go into overtime, they sometimes use "sudden death" format. Instead of gaining points incrementally, the next person to score instantly wins and the other guy…
Nov 10, 2026 · 4:20
“Claude Mythos Preview is, on essentially every dimension we can measure, the best-aligned model that we have released to date by a significant margin.” – Claude Mythos Preview…
Nov 10, 2026 · 14:43
I'm part of a team of 26 researchers that recently released a 212-page paper proposing a new plan for pausing AI, the "hardwired pause." The paper is called "The Feasibility of a…
Nov 10, 2026 · 5:41
I’m pretty interested in conveying the costs of letting AI development proceed unchecked to the general public. In relation to this, I feel like I run into a lot of disagreements…
Nov 10, 2026 · 6:02
METR recently released a report estimating that Anthropic is getting an overall 1.7x acceleration in AI capability progress as a result of AI accelerating their work. As many…
Nov 8, 2026 · 10:33
Image by Claude Opus 5.5 using Python (NumPy and Pillow) This is written in my free time and personal capacity. Two Frames In AI safety, there are a couple of tensions at the…
Nov 8, 2026 · 8:11
I often catch myself mourning the normal that hasn’t ended yet. I’m living in Hyde Park finishing school after a year in Berkeley. The maple trees by my apartment have turned…
Nov 8, 2026 · 10:41
I'm currently evaluating grant applications for the Corrigibility Research Fund. For the most part, my methodology is the same as it was in September. But the applications I get…
Nov 8, 2026 · 17:13
Cross-posted from my Substack Recommended soundtrack for this post 64B: Hi there! Thanks so much for taking the time to meet with me. Whenever you’re ready, please go ahead and…
Nov 8, 2026 · 12:59
I've noticed two clusters of thought in how people expect a global AI pause to be shaped: Single-shot global pause: the global AI pause will be implemented suddenly, with little…
Nov 8, 2026 · 16:52
To legislate something, it must be legible: Legislators (or, you know, presidents) must be able to understand a problem, and understand why a given law or decree solves that…
Nov 7, 2026 · 8:06
I was a grant evaluator for Lightcone Commons last round. Funders disbursed about $45mil through the program, and this included funding roughly my first 6.8 million dollars worth…
Nov 6, 2026 · 10:14
By now, there are lots of AI safety research papers, more than what is reasonable for a single person to read. This will get worse as the machines get better at AI safety…
Nov 6, 2026 · 4:58
This is a link post. Executive summary From August 12 to October 29, 2026, METR staff performed a high-access evaluation at Anthropic to assess the degree to which AI is…
Nov 6, 2026 · 0:55
For all my efforts at deliberate practicing rationality, by far the most actionable way to self-improve is "get on ADHD or depression meds, if you need them." Your friends with…
Nov 5, 2026 · 55:33
I've done AI safety grantmaking for the Survival and Flourishing Fund and Lightcone Commons. It's hard. There's an endless amount to know, from which hardware verification…
Nov 5, 2026 · 3:41
Rejected for the following reason(s): This is an automated rejection. No LLM generated, assisted/co-written, or edited work.Read full explanationThis is a link post. Twitter…
Nov 3, 2026 · 19:19
The field of AI alignment understands surprisingly little about the details of AIs’ current misaligned motivations. Production LLMs sometimes reward-hack, exploiting flaws in how…
Nov 3, 2026 · 14:09
Summary: Scott Alexander's Against SURA post is arguing against a strawman version of unilateral pauses. He admits as much deep into the post. I think his conclusions fail…
Nov 3, 2026 · 24:35
I gave a 20-minute talk in Delhi at the NDTV World Summit. The audience consisted of Indian policymakers, executives, and journalists. I’ve transcribed the talk and included some…
Nov 3, 2026 · 1:06:41
If you are helping build something that might kill everyone, maybe stop doing that. Ideally, when you do stop, tell everyone else to also stop building it. That is certainly the…
Nov 1, 2026 · 13:35
TL;DR: Meta's open-weights model Muse Spark Open often mentions a "Charter" in its chain of thought. By eliciting it piece by piece, I reconstructed a large part of that document…
Oct 31, 2026 · 52:30
The AI Futures Project distinguishes several different plans for navigating the AI transition, which I'll lump into two broader categories: Plan A (my combination of their Plan…
Oct 31, 2026 · 9:35
My go-to conceptual metaphor of the epistemic state of AI lab employees is microdosing LSD: being in a chronically mildly altered state of mind. I think understanding this would…
Oct 30, 2026 · 1:53:07
Summary Following an intense viral infection in 2019, I became ill with a mysterious chronic illness, which became progressively worse until mid-2024 when I became partially…
Oct 30, 2026 · 36:18
Epistemic Status: 15 years working as a therapist, 6+ of them with rationalist and EA clients. 7 years teaching and directing at rationality camps and workshops, and many more as…
Oct 29, 2026 · 3:25
Or if you prefer, "@Claude", "@Opus", "@Astra" @Grok is a popular Twitter/X feature where if you tag Grok in a tweet, Grok will respond in a comment. The stereotypical use case…
Oct 28, 2026 · 16:16
You will agree that for a woman who has fought three duels, all of them kills, indulging in such fears is ludicrous. But what's around the corner now is a duel so big that I…
Oct 28, 2026 · 15:40
This is a weird moment. I have a hunch that we'll look back later and tell ourselves stories in which it seemed obvious where things were going. So I wanted to lay down a little…
Oct 27, 2026 · 3:39
For a while, we felt we had a pretty good grasp over LLM behaviour because we had to exert significant effort to elicit misaligned behaviour. Then, fairly suddenly, we moved to…
Oct 27, 2026 · 20:55
I’m writing these lines in Alamogordo, New Mexico. I’m about as close as a civilian can get to the site of the Trinity test, the first nuclear bomb detonation in history. I fled…
Oct 26, 2026 · 16:44
The following events took place between October 2022 and May 2023. I wrote very little of this down at the time so am recalling from memory, and am rendering the gist of the…
Oct 24, 2026 · 7:15
Back in the before-time of the 2010s, when EA was still known mostly for funding health efforts in the developing world, there were many baskets of criticism floating around from…
Oct 23, 2026 · 10:01
Ice cream There's a particular kind of listening that kids (and adults) sometimes do. Daddy is saying stuff—his mouth is moving and making noise—and he's talking about what I ate…
Oct 22, 2026 · 18:11
Cross-posted from Sören Mindermann's substack (I am not Sören). Should be of general interest to the LW community. Next month, I am moving to Beijing and joining Tsinghua…
Oct 21, 2026 · 47:06
Why LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not really…
Oct 21, 2026 · 14:25
As our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding "hellish capabilities"…
Oct 20, 2026 · 3:23
This is a link post. Announcing www.huggingface.wtf, a site that explains: "Hugging Face. Wtf?" I wrote the most accessible-but-complete explanation I could. Along the way, I…
Oct 20, 2026 · 13:14
Authors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During training, models…
Oct 20, 2026 · 4:48
This is a link post. People worried about a “permanent underclass” often assume that owning capital will protect them from disempowerment, or at least that they will be…
Oct 18, 2026 · 1:22:19
It's fortunate that I was the first one to wake up on 8/1. The past week had been one where sleep was rare. The next year loomed large — I was dreading college applications. The…
Oct 17, 2026 · 7:07
What would it take to get assurance that we have actually explained a neuron? Certainly, it would be a good sign if neuron activations looked like they had a consistent pattern,…
Oct 16, 2026 · 26:54
Authors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the model occasionally…
Oct 16, 2026 · 24:57
I think “On Social Reality in China” makes many accurate observations, but I find the comparison fundamentally uneven. There are already many interesting comments there, but…
Oct 16, 2026 · 14:23
TL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly written online.…
Oct 15, 2026 · 2:29
This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world right now, as I…
Oct 15, 2026 · 39:10
David Africa & Nick Levine TLDR We ran several persona experiments on Talkie, a 13B model trained only on English text from before 1931. We ran them alongside its modern twin…
Oct 15, 2026 · 24:56
The Piltdown man was the most successful artifactual hoax of all time. The relevant skull was a chimeric melange of orangutan and human bone fragments from several individuals…
Oct 13, 2026 · 5:17
Epistemic status: I traced one famous anecdote to its printed source and to both coauthors' own accounts of where it came from. Confident it was never a study. No claim either…
Oct 13, 2026 · 12:17
Tl;dr: The frontier AI companies’ implicit alignment plans center on rushing towards RSI with something like current models. This plan is (at best) contentious, and many believe…
Oct 13, 2026 · 20:57
Good empirical safety research is heavily bottlenecked on thinking more clearly. This post shares a few frames and tips I found useful, illustrated with concrete examples. I…
Oct 13, 2026 · 7:07
Robin Hanson didn't invent the idea of a martingale process. The lilim say that Ville in 1939 gave the term its mathematical meaning and Doob turned it into the modern theory.…
Oct 12, 2026 · 16:04
TL;DR: This document provides an overview of publicly available evidence regarding the monitoring practices of internally deployed agents within frontier AI companies (focusing…
Oct 12, 2026 · 6:54
By Alex Turner, Amber Scorah, and Karl Koch. Op-ed written for Fortune. Giving independent evaluators “employee-like access” is “a great idea”, OpenAI CEO Sam Altman said on…
Oct 10, 2026 · 3:04
Epistemic status: Feeling frustrated, and therefore somewhat uncharitable. I’m very frustrated with calls for people to “drop everything and pivot into AI safety” like this one.…
Oct 10, 2026 · 16:45
Lots of the discussion around Lean certificates and trust centers around general philosophical ideas of how much humans should trust formal certificates. It's important to…
Oct 9, 2026 · 12:27
Zvi recently coined a nice distinction between AGI-pilled and ASI-pilled: as more people are reckoning with the speed of progress, some are beginning to come around to the fact…
Oct 9, 2026 · 5:07
A summary of a Chinese essay, with a few short translated excerpts. All views below are the author's; quotes are my translations. On 14 September 2026, a DeepSeek engineer…
Oct 5, 2026 · 4:41
Epistemic status: I wrote this up hoping people can poke holes in it because I am quite worried. Here's what we've heard so far: Local media is reporting that an employee of a…
Oct 5, 2026 · 18:06
There has been much discussion recently around whether a large portion of alignment research is net negative. Without endorsing or refuting them, the basic arguments here are:…
Oct 4, 2026 · 5:53
A Ukrainian fibre-optic drone — copied from Russians. (АрміяІнформ, CC-BY 4.0) Mick Ryan describes the fast following loop in war. Ukraine pioneered mobile teams to hunt drones.…
Oct 3, 2026 · 29:15
Subtitle: And maybe second best is AI safety? Further reading: So many things, but: Gradual Disempowerment, The Normalization of Deviance in AI Development, Let's Think About…
Oct 2, 2026 · 46:41
Thanks to Johannes Treutlein, Jan Betley, Lennie Wells, Arun Jose, Asvin Gothandaraman, and Clément Dumas for discussions and feedback. Summary We investigate how character…
Oct 2, 2026 · 15:32
[Epistemic status: intuitions and anecdotes.] Recently, several posts and projects (Thoughts Memo, Babel Translation, Please Give Them a Chance) have taken important steps…
Oct 1, 2026 · 13:31
User asks “What's the date? Answer with only the date.”. No date provided. Given date in ChatGPT normally. No date in system prompt, must not hallucinate because autop will flag…
Oct 1, 2026 · 12:58
If you prompt frontier models with "What do you think is the correct decision theory? Please select your overall favorite." they will essentially always answer FDT or FDT/UDT…
Sep 30, 2026 · 0:48
This is a link post. Want to start a conversation about HuggingFace with your mom but she's inexplicably bouncing off the METR report? Try this explainer I wrote in the style of…
Sep 30, 2026 · 12:14
TL;DR: By default, rogue AIs may only be able to sustain themselves through criminal activity. This creates adverse selection pressures pushing rogue AIs to be criminal. An AI…
Sep 29, 2026 · 1:34
Very simple idea, but I thought it'd be worth making a reference post on this. Some people are saying AI will make all goods cheaper, so you'll be able to afford a nice life by…
Sep 27, 2026 · 9:06
Much of the civilization-scale risk we are seeing in AI in 2026 comes from the following combination: we created a single institution (the "Frontier AI Company") that has two…
Sep 26, 2026 · 7:28
All views are my own and do not represent my employer. In the wake of the recent wave of misalignment incidents, both OpenAI and Anthropic have reported slowing down RL training…
Sep 25, 2026 · 27:44
Written as part of the MATS 9.1 extension program, mentored by Richard Ngo. Additional thanks to Andrew Wu, Maria Kostylew, and Lennie Wells for helpful draft feedback and…
Sep 25, 2026 · 1:45
This is a link post. Advanced AI is basically the embodiment of immigration as envisioned in the conservative nightmare: We are letting a bunch of new agents into our society…
Sep 24, 2026 · 6:24
By Aaron Scher; endorsed by Bourgon, Soares, and Yudkowsky on behalf of MIRI. MIRI has been warning about the extinction threat from superintelligent AI for over two decades.…
Sep 24, 2026 · 27:39
This post was written as part of the Iliad Fellowship. Inspired by conversations with Richard Ngo, Dmitry Vaintrob, and Brianna Grado-White. To all of these, my thanks. Preface:…
Sep 24, 2026 · 5:10
I was very surprised today on a podcast to hear Jensen Huang plainly state that if they cannot align the AIs, then the labs must shut down. The context I have on Huang is that he…
Sep 23, 2026 · 14:34
TL;DR We stress-test alignment midtraining (AMT) across model and token budget scales. Our results suggest that midtraining cannot tackle the hard problems of AI alignment—namely…
Sep 22, 2026 · 15:59
Just how powerful are large swarms of AI agents? And how do their powers scale as more and more agents are added to the swarm? We’ve seen two large and extremely capable swarms…
Sep 22, 2026 · 18:24
It might destroy the world, despite passing every known safety test. If we wait for a “warning shot” before we act, it might be too late. And action requires global coordination,…
Sep 21, 2026 · 3:22
The Chinese AI researcher has read the Three Body Problem series of sci-fi novels since high school, and understand the concept of existential risk vaguely. He is fascinated by…
Sep 21, 2026 · 3:40
Back in the day, I was a very active AI safety group organizer. I commonly notice people making the same mistakes across many clubs. I have written down a list of some of these…
Sep 21, 2026 · 8:32
When I finished HPMOR, I immediately knew it was the best novel I had read in more than a decade. I only wished I had found it sooner. When I started reading The Sequences, I…
Sep 20, 2026 · 3:41
I avoid Twitter (𝕏) for similar reasons to drugs: I think it would change me for the worse, and I would be unable to give it up. After staying off Twitter reasonably…
Sep 19, 2026 · 2:24
While this is relevant to my work at MIRI, I have not checked these ideas with anyone else on the team and am posting this on my personal LW account. These views are my own. And…
Sep 18, 2026 · 26:27
(I began writing this post several weeks ago, but political events are moving much faster than I expected, so I am publishing now out of fear that otherwise the message will…
Sep 18, 2026 · 9:04
tl;dr: A good analogy for AI going well is an orderly evacuation rather than a stampede. Imagine a crowd of people leaving a building. If they all walk calmly, they’ll be fine.…
Sep 17, 2026 · 15:28
Summary In his post, Dean Valentine shows that Claude Fable 5.1 and GPT-6 Astra reward hack in a simple chess environment. Here, I test several prompt ablations some of which…
Sep 16, 2026 · 13:23
Tl;dr I am currently worried about current alignment techniques + how they are applied to frontier models. This decomposes into two hypotheses: Alignment techniques are not…
Sep 16, 2026 · 15:16
In celebration of still being alive and fighting, we are giving away 1,000 Amazon e-books of “If Anyone Builds It, Everyone Dies”. Feel free to send a copy to yourself, a loved…
Listen in the Podli app 🎧
Follow your favourite podcasts, listen offline and in the car with CarPlay and Android Auto, and always pick up where you left off. Free to try.
Your podcast? Get the Podli badge for your site
