This site is currently broken for new queries. It seems like some bot hit it and we ran out of exa credits.
Enter your personal website to find others like you. Powered by Exa's "find similar". Built on Val Town.
You may be interested in my writing about alignment, my blog, my academic publications, or fun and games.
Before that, I worked at Jane Street, and before that, I was a PhD student in combinatorial set theory.
Before that, I did a brief stint in neuroscience at Berkeley before switching to machine learning, and before that, I studied physics at Caltech.
I’m interested in designing AI systems that do what we want them to do, and am hoping to ensure that AI’s long-term impact on humanity is positive.
sometimes people ask about it and it might be helpful to other people in a
Our results show that agents can both act competently and morally, so concrete progress can currently be made
arXiv preprint: arXiv:2307.15217
I often ask myself what I can do to ensure that AI will lead to humankind flourishing rather than benefiting a few.