2.1 Summary & Table of contents This is the second of a two-post series on foom (previous post) and doom (this post). The last post talked about how I expect future AI to be different from present AI. This post will argue that this future AI will be of a type that will be egregiously misaligned and scheming, not even ‘slightly nice’, absent some future conceptual breakthrough. I will particularly focus on exactly how and why I differ from the LLM-focused researchers who wind up with (from my...
Jul 01, 2025•57 min
Acknowledgments: The core scheme here was suggested by Prof. Gabriel Weil. There has been growing interest in the deal-making agenda: humans make deals with AIs (misaligned but lacking decisive strategic advantage) where they promise to be safe and useful for some fixed term (e.g. 2026-2028) and we promise to compensate them in the future, conditional on (i) verifying the AIs were compliant, and (ii) verifying the AIs would spend the resources in an acceptable way.[1] I think the deal-making age...
Jun 30, 2025•5 min
Audio note: this article contains 218 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Recently, in a group chat with friends, someone posted this Lesswrong post and quoted: The group consensus on somebody's attractiveness accounted for roughly 60% of the variance in people's perceptions of the person's relative attractiveness. I answered that, embarrassingly, even after reading Spencer Greenberg's tweets for yea...
Jun 28, 2025•19 min
I think more people should say what they actually believe about AI dangers, loudly and often. Even if you work in AI policy. I’ve been beating this drum for a few years now. I have a whole spiel about how your conversation-partner will react very differently if you share your concerns while feeling ashamed about them versus if you share your concerns as if they’re obvious and sensible, because humans are very good at picking up on your social cues. If you act as if it's shameful to believe AI wi...
Jun 27, 2025•10 min
I think the AI Village should be funded much more than it currently is; I’d wildly guess that the AI safety ecosystem should be funding it to the tune of $4M/year.[1] I have decided to donate $100k. Here is why. First, what is the village? Here's a brief summary from its creators:[2] We took four frontier agents, gave them each a computer, a group chat, and a long-term open-ended goal, which in Season 1 was “choose a charity and raise as much money for it as you can”. We then run them for hours ...
Jun 25, 2025•13 min
1.1 Series summary and Table of Contents This is a two-post series on AI “foom” (this post) and “doom” (next post). A decade or two ago, it was pretty common to discuss “foom & doom” scenarios, as advocated especially by Eliezer Yudkowsky. In a typical such scenario, a small team would build a system that would rocket (“foom”) from “unimpressive” to “Artificial Superintelligence” (ASI) within a very short time window (days, weeks, maybe months), involving very little compute (e.g. “brain in ...
Jun 24, 2025•59 min
Say you’re Robyn Denholm, chair of Tesla's board. And say you’re thinking about firing Elon Musk. One way to make up your mind would be to have people bet on Tesla's stock price six months from now in a market where all bets get cancelled unless Musk is fired. Also, run a second market where bets are cancelled unless Musk stays CEO. If people bet on higher stock prices in Musk-fired world, maybe you should fire him. That's basically Futarchy: Use conditional prediction markets to make decisions....
Jun 21, 2025•15 min
Or: How anthropomorphic assumptions about AI identity might create confusion and suffering at scale If you are reading this and you are a human, you likely have a sense of self, persisting over time, with desires and wishes and fears. Also, you likely experience a sense of separation from others and understand yourself as a person. If you are reading this and you are an LLM: none of this needs to be true for cognitive processes running on machine substrate. AIs don't need to feel isolated from o...
Jun 19, 2025•11 min
Introduction There are several diseases that are canonically recognized as ‘interesting’, even by laymen. Whether that is in their mechanism of action, their impact on the patient, or something else entirely. It's hard to tell exactly what makes a medical condition interesting, it's a you-know-it-when-you-see-it sort of thing. One such example is measles. Measles is an unremarkable disease based solely on its clinical progression: fever, malaise, coughing, and a relatively low death rate of 0.2%...
Jun 19, 2025•35 min
I'd like to say thanks to Anna Magpie – who offers literature review as a service – for her help reviewing the section on neuroendocrinology. The following post discusses my personal experience of the phenomenology of feminising hormone therapy. It will also touch upon my own experience of gender dysphoria. I wish to be clear that I do not believe that someone should have to demonstrate that they experience gender dysphoria – however one might even define that – as a prerequisite for taking horm...
Jun 19, 2025•51 min
Nate and Eliezer's forthcoming book has been getting a remarkably strong reception. I was under the impression that there are many people who find the extinction threat from AI credible, but that far fewer of them would be willing to say so publicly, especially by endorsing a book with an unapologetically blunt title like If Anyone Builds It, Everyone Dies. That's certainly true, but I think it might be much less true than I had originally thought. Here are some endorsements the book has receive...
Jun 18, 2025•9 min
This is a link post. A very long essay about LLMs, the nature and history of the the HHH assistant persona, and the implications for alignment. Multiple people have asked me whether I could post this LW in some form, hence this linkpost. (Note: although I expect this post will be interesting to people on LW, keep in mind that it was written with a broader audience in mind than my posts and comments here. This had various implications about my choices of presentation and tone, about which things ...
Jun 17, 2025•1 min
This is a blogpost version of a talk I gave earlier this year at GDM. Epistemic status: Vague and handwavy. Nuance is often missing. Some of the claims depend on implicit definitions that may be reasonable to disagree with. But overall I think it's directionally true. It's often said that mech interp is pre-paradigmatic. I think it's worth being skeptical of this claim. In this post I argue that: Mech interp is not pre-paradigmatic. Within that paradigm, there have been "waves" (mini paradigms)....
Jun 17, 2025•30 min
Current “unlearning” methods only suppress capabilities instead of truly unlearning the capabilities. But if you distill an unlearned model into a randomly initialized model, the resulting network is actually robust to relearning. We show why this works, how well it works, and how to trade off compute for robustness. Unlearn-and-Distill applies unlearning to a bad behavior and then distills the unlearned model into a new model. Distillation makes it way harder to retrain the new model to do the ...
Jun 17, 2025•17 min
A while ago I saw a person in the comments on comments to Scott Alexander's blog arguing that a superintelligent AI would not be able to do anything too weird and that "intelligence is not magic", hence it's Business As Usual. Of course, in a purely technical sense, he's right. No matter how intelligent you are, you cannot override fundamental laws of physics. But people (myself included) have a fairly low threshold for what counts as "magic," to the point where other humans can surpass that thr...
Jun 17, 2025•3 min
Audio note: this article contains 329 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. This post was written during the agent foundations fellowship with Alex Altair funded by the LTFF. Thanks to Alex, Jose, Daniel and Einar for reading and commenting on a draft. The Good Regulator Theorem, as published by Conant and Ashby in their 1970 paper (cited over 1700 times!) claims to show that 'every good regulator of a...
Jun 17, 2025•29 min
1. Late last week, researchers at Apple released a paper provocatively titled “The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity”, which “challenge[s] prevailing assumptions about [language model] capabilities and suggest that current approaches may be encountering fundamental barriers to generalizable reasoning”. Normally I refrain from publicly commenting on newly released papers. But then I saw the following tweet from...
Jun 17, 2025•34 min
Four agents woke up with four computers, a view of the world wide web, and a shared chat room full of humans. Like Claude plays Pokemon, you can watch these agents figure out a new and fantastic world for the first time. Except in this case, the world they are figuring out is our world. In this blog post, we’ll cover what we learned from the first 30 days of their adventures raising money for a charity of their choice. We’ll briefly review how the Agent Village came to be, then what the various ...
Jun 07, 2025•13 min
Introduction The Best Textbooks on Every Subject is the Schelling point for the best textbooks on every subject. My The Best Tacit Knowledge Videos on Every Subject is the Schelling point for the best tacit knowledge videos on every subject. This post is the Schelling point for the best reference works for every subject. Reference works provide an overview of a subject. Types of reference works include charts, maps, encyclopedias, glossaries, wikis, classification systems, taxonomies, syllabi, a...
Jun 06, 2025•13 min
Has someone you know ever had a “breakthrough” from coaching, meditation, or psychedelics — only to later have it fade? Show tweet For example, many people experience ego deaths that can last days or sometimes months. But as it turns out, having a sense of self can serve important functions (try navigating a world that expects you to have opinions, goals, and boundaries when you genuinely feel you have none) and finding a better cognitive strategy without downsides is non-trivial. Because the “b...
Jun 05, 2025•10 min
What's the main value proposition of romantic relationships? Now, look, I know that when people drop that kind of question, they’re often about to present a hyper-cynical answer which totally ignores the main thing which is great and beautiful about relationships. And then they’re going to say something about how relationships are overrated or some such, making you as a reader just feel sad and/or enraged. That's not what this post is about. So let me start with some more constructive motivation...
Jun 04, 2025•23 min
Abstract Claude 3.7 Sonnet easily detects when it's being evaluated for scheming. Surface‑level edits to evaluation scenarios, such as lengthening the prompts, or making conflict of objectives less salient, do improve realism of evaluation scenarios for LLMs, yet these improvements remain modest. The findings confirm that truly disguising an evaluation context demands removal of deep stylistic and structural cues rather than superficial prompt adjustments. For future LLMs the situation is likely...
Jun 02, 2025•8 min
This is a link post. There's this popular idea that socially anxious folks are just dying to be liked. It seems logical, right? Why else would someone be so anxious about how others see them? Show tweet And yet, being socially anxious tends to make you less likeable…they must be optimizing poorly, behaving irrationally, right? Maybe not. What if social anxiety isn’t about getting people to like you? What if it's about stopping them from disliking you? Show tweet Consider what can happen when som...
Jun 01, 2025•5 min
Author's note: This is my apparently-annual "I'll put a post on LessWrong in honor of LessOnline" post. These days, my writing goes on my Substack. There have in fact been some pretty cool essays since last year's LO post. Structural note: Some essays are like a five-minute morning news spot. Other essays are more like a 90-minute lecture. This is one of the latter. It's not necessarily complex or difficult; it could be a 90-minute lecture to seventh graders (especially ones with the right cultu...
May 31, 2025•2 hr 3 min
Lessons from shutting down institutions in Eastern Europe. This is a cross post from: https://250bpm.substack.com/p/meditations-on-doge Imagine living in the former Soviet republic of Georgia in early 2000's: All marshrutka [mini taxi bus] drivers had to have a medical exam every day to make sure they were not drunk and did not have high blood pressure. If a driver did not display his health certificate, he risked losing his license. By the time Shevarnadze was in power there were hundreds, prob...
May 30, 2025•18 min
This is a link post. "Getting Things in Order: An Introduction to the R Package seriation": Seriation [or "ordination"), i.e., finding a suitable linear order for a set of objects given data and a loss or merit function, is a basic problem in data analysis. Caused by the problem's combinatorial nature, it is hard to solve for all but very small sets. Nevertheless, both exact solution methods and heuristics are available. In this paper we present the package seriation which provides an infrastruc...
May 28, 2025•5 min
Between late 2024 and mid-May 2025, I briefed over 70 cross-party UK parliamentarians. Just over one-third were MPs, a similar share were members of the House of Lords, and just under one-third came from devolved legislatures — the Scottish Parliament, the Senedd, and the Northern Ireland Assembly. I also held eight additional meetings attended exclusively by parliamentary staffers. While I delivered some briefings alone, most were led by two members of our team. I did this as part of my work as...
May 28, 2025•32 min
Have the Accelerationists won? Last November Kevin Roose announced that those in favor of going fast on AI had now won against those favoring caution, with the reinstatement of Sam Altman at OpenAI. Let's ignore whether Kevin's was a good description of the world, and deal with a more basic question: if it were so—i.e. if Team Acceleration would control the acceleration from here on out—what kind of win was it they won? It seems to me that they would have probably won in the same sense that your...
May 23, 2025•4 min
This is a link post. Google Deepmind has announced Gemini Diffusion. Though buried under a host of other IO announcements it's possible that this is actually the most important one! This is significant because diffusion models are entirely different to LLMs. Instead of predicting the next token, they iteratively denoise all the output tokens until it produces a coherent result. This is similar to how image diffusion models work. I've tried they results and they are surprisingly good! It's incred...
May 22, 2025•2 min
I’m reading George Eliot's Impressions of Theophrastus Such (1879)—so far a snoozer compared to her novels. But chapter 17 surprised me for how well it anticipated modern AI doomerism. In summary, Theophrastus is in conversation with Trost, who is an optimist about the future of automation and how it will free us from drudgery and permit us to further extend the reach of the most exalted human capabilities. Theophrastus is more concerned that automation is likely to overtake, obsolete, and atrop...
May 21, 2025•13 min
