Capturing the benefits of AI while mitigating its risks is difficult. I'm interested in ways of getting the best of both worlds, whether that means filling in the missing pieces of AI safety infrastructure, or carrying out fundamental alignment research.
I'm grateful for having been supported in my work, either financially or through compute, either recently or less so, by Effective Ventures, Google Research, Conjecture, Andreas Stuhlmüller, Stability AI, and AI Safety Camp. If I'm not working on alignment, chances are I'm either running or hosting a game night.
Getting the right tooling in place to differentially accelerate towards positive futures.
A research agenda aimed at developing AI systems that act in morally defensible ways.
An interactive book series focused on rendering philosophy computable, quantifiable, and verifiable.
A learning project focused on recent trends in machine learning.
Old portfolio and blog on "exploring synergies between the organic and the artificial."