Hi! I’m Aniruddh Pramod (or Ani). A childhood obsession with machine intelligence and brain uploading along with an undergraduate degree in mathematics, a master’s (ongoing) in computer science and a lot of different interests along the way has made me a budding AI safety researcher. I’m still interested in machine intelligence, but now this interest is grounded in the social impact alongside my own curiosity.

I’m interested broadly along two directions—a) what kinds of goals do these systems have, and how robust are they and b) supposing we can’t avoid misalignment, what can we do about it regardless?

I’m currently a Pivotal Fellow working on AI Control with Redwood Research.