Read the constitution. Previously: 'soul document' discussion here. We're publishing a new constitution for our AI model, Claude. It's a detailed description of Anthropic's vision for Claude's values and behavior; a holistic document that...

This is a link post. It is unbearable to not be consuming. All through the house is nothing but silence. The need inside of me is not an ache, it is caustic, sour, the burning desire to be distracted, to be listening, watching, scrolling. ...

I spent a few hundred dollars on Anthropic API credits and let Claude individually research every current US congressperson's position on AI. This is a summary of my findings. Disclaimer: Summarizing people's beliefs is hard and inherentl...

Since artificial superintelligence has never existed, claims that it poses a serious risk of global catastrophe can be easy to dismiss as fearmongering. Yet many of the specific worries about such systems are not free-floating fantasies but exten...

Boaz Barak, Gabriel Wu, Jeremy Chen, Manas Joglekar [Linkposting from the OpenAI alignment blog, where we post more speculative/technical/informal results and thoughts on safety and alignment.] TL;DR We go into more details...

Two cats fighting for control over my backyard appear to have settled on a particular chain-link fence as the delineation between their territories. This suggests that: Animals are capable of recognizing Schelling points...

On Thinkish, Neuralese, and the End of Readable Reasoning In September 2025, researchers published the internal monologue of OpenAI's GPT-o3 as it decided to lie about scientific data. This is what it thought: Pardon? This looks l...

It seems to be a real view held by serious people that your OpenAI shares will soon be tradable for moons and galaxies. This includes eminent thinkers like Dwarkesh Patel, Leopold Aschenbrenner, perhaps Scott Alexander and many more. According to...

We’ve significantly upgraded our timelines and takeoff models! It predicts when AIs will reach key capability milestones: for example, Automated Coder / AC (full automation of coding) and superintelligence / ASI (much better than the best humans ...

For the past year I've been sinking into the Great Books via the Penguin Great Ideas series, because I wanted to be conversant in the Great Conversation. I am occasionally frustrated by this endeavour, but overall, it's been fun! I'm learning a l...

Past years: 2023 2024 Continuing a yearly tradition, I evaluate AI predictions from past years, and collect a convenience sample of AI predictions made this year. In terms of selection, I prefer selecting specific predictions, especially ...

They say you’re supposed to choose your prior in advance. That's why it's called a “prior”. First, you’re supposed to say say how plausible different things are, and then you update your beliefs based on what you see in the world. For exa...

A key risk factor for scheming (and misalignment more generally) is opaque reasoning ability.One proxy for this is how good AIs are at solving math problems immediately without any chain-of-thought (CoT) (as in, in a single forward pass).I've mea...

Prior results have shown that LLMs released before 2024 can't leverage 'filler tokens'—unrelated tokens prior to the model's final answer—to perform additional computation and improve performance.[1]I did an investigation on more recent models (e...

Master version of this on https://parvmahajan.com/2025/12/21/turning-20.html I turn 20 in January, and the world looks very strange. Probably, things will change very quickly. Maybe, one of those things is whether or not we’re still here...

TL;DR LLMs pretrained on data about misaligned AIs themselves become less aligned. Luckily, pretraining LLMs with synthetic data about good AIs helps them become more aligned. These alignment priors persist through post-t...

Commercial airplane tickets are divided up into coach, business class, and first class. In 2014, Etihad introduced The Residence, a premium experience above first class. The Residence isn't very popular. The reason The Residence isn't ver...

At many points now, I've been asked in private for a critique of EA / EA's history / EA's impact and I have ad-libbed statements that I feel guilty about because they have not been subjected to EA critique and refutation. I need to write up my ta...

Screwtape, as the global ACX meetups czar, has to be reasonable and responsible in his advice giving for running meetups. And the advice is great! It is unobjectionably great. I am here to give you more objectionable advice, as an...

TL;DR: In 2025, we were in the 1-4 hour range, which has only 14 samples in METR's underlying data. The topic of each sample is public, making it easy to game METR horizon length measurements for a frontier lab, sometimes inadvertently. Finally, ...

TL;DR: We train LLMs to accept LLM neural activations as inputs and answer arbitrary questions about them in natural language. These Activation Oracles generalize far beyond their training distribution, for example uncovering misalignment or secr...

A couple of years ago, Gavin became frustrated with science journalism. No one was pulling together results across fields; the articles usually didn’t link to the original source; they didn't use probabilities (or even report the sample size...

I have goals that can only be reached via a powerful political machine. Probably a lot of other people around here share them. (Goals include “ensure no powerful dangerous AI get built”, “ensure governance of the US and world are broadly good / n...

How it started I used to think that anything that LLMs said about having something like subjective experience or what it felt like on the inside was necessarily just a confabulated story. And there were several good reaso...

Previous: 2024, 2022 “Our greatest fear should not be of failure, but of succeeding at something that doesn't really matter.” –attributed to DL Moody[1] 1. Background & threat model The main threat mod...