2025-03-05 08:00:00
I have decided to leave Google DeepMind after seven years, and will be joining Anthropic for a year to continue my research on adversarial machine learning. Below you can find a (significantly shortened) version of the doc I sent to my colleagues to explain why I'm leaving, and a (new for this article) brief discussion about what I will be doing next.
2025-02-10 08:00:00
Late last year, I published an article asking readers to make 30 forecasts about the future of AI in 2027 and 2030—from whether or not you could buy a robot to do your laundry, to predicting the valuation of leading AI labs, to estimating the likelihood of an AI-caused catastrophe.
2025-01-06 08:00:00
Over the holidays I decided it's been too long since I did something with entirely no purpose. So without further ado, I present to you ... Regex Chess: sequence of 84,688 regular expressions that, when executed in order, will play a (valid; not entirely terrible) move given a chess board as input.
2024-12-25 08:00:00
I let a language model write my bio. It went about as well as you might expect.
2024-11-25 08:00:00
The field of AI is progressing much faster than many expected. When things are changing so fast, it can be hard to remember what you thought was impossible just a few years ago, and conversely, what you thought was obviously going to be trivially solved that still hasn't been.
2024-08-01 08:00:00
I don't think that "AI" models [a] (by which I mean: large language models) are over-hyped.
