About

I studied pure mathematics at the University of Melbourne, and I now work on AI-safety problems independently.

I work on this because of roughly the case made in The Most Important Century: there's a serious argument that the people alive right now sit at an unusually pivotal moment — plausibly among the most consequential who will ever live. There's an obvious hubris in taking that personally enough to act on it. The reason I work technically: on my priors about my own ability and aptitudes, it's the best bet I have for making real progress on these questions rather than just having opinions about them.

What I'm looking for

Research and engineering roles where I can work as close to the frontier as possible and really understand how the whole system fits together. Whether that's interpretability and safety or building and shipping capable systems, the throughline is the same: getting close enough to real systems to know what they're actually doing. I'm as happy doing the careful experimental work as building the machinery a problem needs.

Outside of work

I'm probably playing with my cat Charli (yes, named after Charli XCX) or thinking about Kant. I'm constantly amazed by the possibility of the synthetic a priori — kind of crazy that we can know something about the universe without looking at it, just by thinking.