I'm an AI policy resarcher at Apollo Research where, among other things, I've contributed to work on AI incident regimes, the internal deployment of AI systems, and a literature review of the field of mechanistic intepretability.
In a past life, I was an avid quizzer and student of Physics and Philosophy at Bristol.
If you're reading this, I'm probably interested in hearing from you. You can contact me at [alexor487][at][gmail][dot][com].