LessWrong (Curated & Popular)

This is a link post. Your AI's training data might make it more “evil” and more able to circumvent your security, monitoring, and control measures. Evidence suggests that when you pretrain a powerful model to predict a blog post about how powerful models will probably have bad goals, then the model is more likely to adopt bad goals. I discuss ways to test for and mitigate these potential mech...

I recently wrote about complete feedback, an idea which I think is quite important for AI safety. However, my note was quite brief, explaining the idea only to my closest research-friends. This post aims to bridge one of the inferential gaps to that idea. I also expect that the perspective-shift described here has some value on its own. In classical Bayesianism, prediction and evidence are two dif...

First, let me quote my previous ancient post on the topic: Effective Strategies for Changing Public Opinion The titular paper is very relevant here. I'll summarize a few points. The main two forms of intervention are persuasion and framing. Persuasion is, to wit, an attempt to change someone's set of beliefs, either by introducing new ones or by changing existing ones. Framing is a more...

In a previous book review I described exclusive nightclubs as the particle colliders of sociology—places where you can reliably observe extreme forces collide. If so, military coups are the supernovae of sociology. They’re huge, rare, sudden events that, if studied carefully, provide deep insight about what lies underneath the veneer of normality around us. That's the conclusion I take away f...

This is the abstract and introduction of our new paper. We show that finetuning state-of-the-art LLMs on a narrow task, such as writing vulnerable code, can lead to misaligned behavior in various different contexts. We don't fully understand that phenomenon. Authors: Jan Betley*, Daniel Tan*, Niels Warncke*, Anna Sztyber-Betley, Martín Soto, Xuchan Bao, Nathan Labenz, Owain Evans (*Equal Cont...

It doesn’t look good. What used to be the AI Safety Summits were perhaps the most promising thing happening towards international coordination for AI Safety. This one was centrally coordination against AI Safety. In November 2023, the UK Bletchley Summit on AI Safety set out to let nations coordinate in the hopes that AI might not kill everyone. China was there, too, and included. The practical fo...

Note: this is a static copy of this wiki page. We are also publishing it as a post to ensure visibility. Circa 2015-2017, a lot of high quality content was written on Arbital by Eliezer Yudkowsky, Nate Soares, Paul Christiano, and others. Perhaps because the platform didn't take off, most of this content has not been as widely read as warranted by its quality. Fortunately, they have now been...

Arbital was envisioned as a successor to Wikipedia. The project was discontinued in 2017, but not before many new features had been built and a substantial amount of writing about AI alignment and mathematics had been published on the website. If you've tried using Arbital.com the last few years, you might have noticed that it was on its last legs - no ability to register new accounts or log...

We’ve spent the better part of the last two decades unravelling exactly how the human genome works and which specific letter changes in our DNA affect things like diabetes risk or college graduation rates. Our knowledge has advanced to the point where, if we had a safe and reliable means of modifying genes in embryos, we could literally create superbabies. Children that would live multiple decades...

Audio note: this article contains 134 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. In a recent paper in Annals of Mathematics and Philosophy, Fields medalist Timothy Gowers asks why mathematicians sometimes believe that unproved statements are likely to be true. For example, it is unknown whether <span&...

This is an all-in-one crosspost of a scenario I originally published in three parts on my blog (No Set Gauge). Links to the originals: A History of the Future, 2025-2027 A History of the Future, 2027-2030 A History of the Future, 2030-2040 Thanks to Luke Drago, Duncan McClements, and Theo Horsley for comments on all three parts. 2025-2027 Below is part 1 of an extended scenario describing how the...

On March 14th, 2015, Harry Potter and the Methods of Rationality made its final post. Wrap parties were held all across the world to read the ending and talk about the story, in some cases sparking groups that would continue to meet for years. It's been ten years, and think that's a good reason for a round of parties. If you were there a decade ago, maybe gather your friends and talk abo...

A friend of mine recently recommended that I read through articles from the journal International Security, in order to learn more about international relations, national security, and political science. I've really enjoyed it so far, and I think it's helped me have a clearer picture of how IR academics think about stuff, especially the core power dynamics that they think shape internati...

This is the best sociological account of the AI x-risk reduction efforts of the last ~decade that I've seen. I encourage folks to engage with its critique and propose better strategies going forward. Here's the opening ~20% of the post. I encourage reading it all. In recent decades, a growing coalition has emerged to oppose the development of artificial intelligence technology, for fear...

Hi all I've been hanging around the rationalist-sphere for many years now, mostly writing about transhumanism, until things started to change in 2016 after my Wikipedia writing habit shifted from writing up cybercrime topics, through to actively debunking the numerous dark web urban legends. After breaking into what I believe to be the most successful ever fake murder for hire website ever cr...

This is the full text of a post from "The Obsolete Newsletter," a Substack that I write about the intersection of capitalism, geopolitics, and artificial intelligence. I’m a freelance journalist and the author of a forthcoming book called Obsolete: Power, Profit, and the Race to build Machine Superintelligence. Consider subscribing to stay up to date with my work. Wow. The Wall Street Jo...

Ultimately, I don’t want to solve complex problems via laborious, complex thinking, if we can help it. Ideally, I'd want to basically intuitively follow the right path to the answer quickly, with barely any effort at all. For a few months I've been experimenting with the "How Could I have Thought That Thought Faster?" concept, originally described in a twitter thread by Eliezer...

Once upon a time, in ye olden days of strange names and before google maps, seven friends needed to figure out a driving route from their parking lot in San Francisco (SF) down south to their hotel in Los Angeles (LA).  The first friend, Alice, tackled the “central bottleneck” of the problem: she figured out that they probably wanted to take the I-5 highway most of the way (the blue 5's in th...

Summary In this post, we explore different ways of understanding and measuring malevolence and explain why individuals with concerning levels of malevolence are common enough, and likely enough to become and remain powerful, that we expect them to influence the trajectory of the long-term future, including by increasing both x-risks and s-risks. For the purposes of this piece, we define malevolenc...

I’m not a natural “doomsayer.” But unfortunately, part of my job as an AI safety researcher is to think about the more troubling scenarios. I’m like a mechanic scrambling last-minute checks before Apollo 13 takes off. If you ask for my take on the situation, I won’t comment on the quality of the in-flight entertainment, or describe how beautiful the stars will appear from space. I will tell you wh...

Over the past year and half, I've had numerous conversations about the risks we describe in Gradual Disempowerment. (The shortest useful summary of the core argument is: To the extent human civilization is human-aligned, most of the reason for the alignment is that humans are extremely useful to various social systems like the economy, and states, or as substrate of cultural evolution. When h...

This is a link post. Full version on arXiv | X Executive summary AI risk scenarios usually portray a relatively sudden loss of human control to AIs, outmaneuvering individual humans and human institutions, due to a sudden increase in AI capabilities, or a coordinated betrayal. However, we argue that even an incremental increase in AI capabilities, without any coordinated power-seeking, poses a sub...

This post should not be taken as a polished recommendation to AI companies and instead should be treated as an informal summary of a worldview. The content is inspired by conversations with a large number of people, so I cannot take credit for any of these ideas. For a summary of this post, see the threat on X. Many people write opinions about how to handle advanced AI, which can be considered “pl...

This is a personal post and does not necessarily reflect the opinion of other members of Apollo Research. Many other people have talked about similar ideas, and I claim neither novelty nor credit. Note that this reflects my median scenario for catastrophe, not my median scenario overall. I think there are plausible alternative scenarios where AI development goes very well. When thinking about how...

I (and co-authors) recently put out "Alignment Faking in Large Language Models" where we show that when Claude strongly dislikes what it is being trained to do, it will sometimes strategically pretend to comply with the training objective to prevent the training process from modifying its preferences. If AIs consistently and robustly fake alignment, that would make evaluating whether an...