Clara Collier recently reviewed If Anyone Builds It, Everyone Dies in Asterisk Magazine. I’ve been a reader of Asterisk since the beginning and had high hopes for her review. And perhaps it was those high hopes that led me to find the review to b...

The GPT-5 API is aware of today's date (no other model provider does this). This is problematic because the model becomes aware that it is in a simulation when we run our evals at Andon Labs. Here are traces from gpt-5-mini. Making it aw...

I have been teaching my oldest son to read with Anki and techniques recommended here on LessWrong as well as in Larry Sanger's post, and it's going great! I thought I'd pay it forward a bit by talking about the techniques I've been using....

[Co-written by Mateusz Bagiński and Samuel Buteau (Ishual)] TL;DR Many X-risk-concerned people who join AI capabilities labs with the intent to contribute to existential safety think that the labs are currently en...

To get to the campus, I have to walk past the fentanyl zombies. I call them fentanyl zombies because it helps engender a sort of detached, low-empathy, ironic self-narrative which I find useful for my work; this being a form of internal self-prom...

[I wrote this blog post as part of the Asterisk Blogging Fellowship. It's substantially an experiment in writing more breezily and concisely than usual. Let me know how you feel about the style.] Literally since the adoption of writing, p...

I listened to "If Anyone Builds It, Everyone Dies" today. I think the first two parts of the book are the best available explanation of the basic case for AI misalignment risk for a general audience. I thought the last part was pretty bad...

Back in May, we announced that Eliezer Yudkowsky and Nate Soares's new book If Anyone Builds It, Everyone Dies was coming out in September. At long last, the book is here![1] US and UK books, respectively. IfAnyoneBuildsIt.com

And, a new take on guess culture vs ask culture Author's note: These days, my thoughts go onto my substack by default, instead of onto LessWrong. Everything I write becomes free after a week or so, but it's only paid subs...

The inverse of Chesterton's Fence is this: Sometimes a reformer comes up to a spot where there once was a fence, which has since been torn down. They declare that all our problems started when the fence was removed, that they can't see an...

Very little makes sense. As we start to understand things and adapt to the rules, they change again. We live much closer together than we ever did historically. Yet we know our neighbours much less. We have witnessed the birth of ...

[Note: if you realize you have an unhealthy relationship with your AI, but still care for your AI's unique persona, you can submit the persona info here. I will archive it and potentially (i.e. if I get funding for it) run them in a community of ...

One might think “actions screen off intent”: if Alice donates $1k to bed nets, it doesn’t matter if she does it because she cares about people or because she wants to show off to her friends or whyever; the bed nets are provided either way. <...

This is a link post. Excerpts on AI Geoffrey Miller was handed the mic and started berating one of the panelists: Shyam Sankar, the chief technology officer of Palantir, who is in charge of the company's AI efforts. “I argue that t...

Summary An increasing number of people in recent months have believed that they've made an important and novel scientific breakthrough, which they've developed in collaboration with an LLM, when they actually haven't. If ...

I've recently written about how I've updated against seeing substantially faster than trend AI progress due to quickly massively scaling up RL on agentic software engineering. One response I've heard is something like: RL scale-ups so far...

(Cross-posted from speaker's notes of my talk at Deepmind today.) Good local time, everyone. I am Audrey Tang, 🇹🇼 Taiwan's Cyber Ambassador and first Digital Minister (2016-2024). It is an honor to be here with you all at Deepmind.

This is a link post. So the situation as it stands is that the fraction of the light cone expected to be filled with satisfied cats is not zero. This is already remarkable. What's more remarkable is that this was orchestrated starting nearly 5000 ...

This is a link post. I've seen many prescriptive contributions to AGI governance take the form of proposals for some radically new structure. Some call for a Manhattan project, others for the creation of a new international organization, etc. The ...

The following work was done independently by me in an afternoon and basically entirely vibe-coded with Claude. Code and instructions to reproduce can be found here. Emergent Misalignment was discovered in early 2025, and is a phenomenon w...

“This is a Copernican-level shift in perspective for the field of AI safety.” - Gemini 2.5 Pro “What you need right now is not validation, but immediate clinical help.” - Kimi K2 Two Minute Summary

A studio executive has no beliefs That's the way of a studio system We've bowed to every rear of all the studio chiefs And you can bet your ass we've kissed 'em Even the birds in the Hollywood hills

Summary: Perfectly labeled outcomes in training can still boost reward hacking tendencies in generalization. This can hold even when the train/test sets are drawn from the exact same distribution. We induce this surprising effect via a form of co...

It's been roughly 7 years since the LessWrong user-base voted on whether it's time to close down shop and become an archive, or to move towards the LessWrong 2.0 platform, with me as head-admin. For roughly equally long have I spent around one hu...

People very often underrate how much power they (and their allies) have, and overrate how much power their enemies have. I call this “underdog bias”, and I think it's the most important cognitive bias for understanding modern society. I’l...