Top postsTop post
Daniel Tan
Message
1 July 2026 - I have not signed any contracts that I can't talk about. I'll update this periodically as long as it's true. The next planned update date is: 1 Jan 2027.
2647
Ω
1
14
367
This is a link post for the paper preprint: Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors from the Center on Long-Term Risk. Selective generalization. Training can teach desired and undesired traits at once. Selective generalization aims to preserve the generalization of desired traits while preventing the...
Tl;dr I've been thinking hard and experimenting with how to best take advantage of AI for my work. I've developed some practices, mostly through trial and error. These have helped me spend less effort doing work while getting more done, and so I'm writing them up to share them. A...
I've been wearing an Oura ring 4 for about a month now, and I love it! It tracks several statistics related to sleep, activity, and overall health. Simply looking at these numbers motivates me to make decisions that will increase them. As a result, I've been sleeping and exercising way...
This work was done by Advik Raj Basani with Daniel Tan and Chloe Li as part of SPAR Spring 2026. tl;dr: Finetuning-based auditing methods for model organisms may unintentionally erase the deceptive behavior we are trying to measure, leading to an illusion of success. We study secret side constraint (SSC)...
I've been playing Coup for a long time now. I keep a copy in my backpack and bring it everywhere. It's definitely earned the space - I have an absolute blast every time I play this game, with new friends or old! A few reasons it's so good: * It's...
Recently I've been working in one-week sprints, and I've really enjoyed it! Tl;dr I need to do a lot of creative knowledge work, and have recently fallen into a routine which IMO is pretty good at facilitating that. The week Monday and Tuesday — intense new work. I'm recharged and...
Context: We are the ‘model motivations’ team at Arcadia Alignment. We aim to build a science of ‘model intentions’, unifying insights from personas and other empirical evidence. This is an informal research note that has come out of the first 2-3 weeks of exploratory work. In this post, we’ll outline...