Hi! I’m Pushpita. I’m a computational astrophysicist turning to AI safety.

I did my PhD at the University of Amsterdam and then spent some time as a postdoctoral fellow at Columbia University (New York) working on numerical simulations of black holes. My research background has mostly involved building large-scale simulations to understand complex physical systems.

This transition is driven by concern about the risks advanced AI could pose if it goes wrong, and the desire to help make sure it doesn’t. I think advanced AI could become one of the most important technologies humanity builds in the coming decade, and that makes the safety problem urgent.

I would like to use the skills I developed as an astrophysics researcher to help make these systems more understandable, reliable, and safe.

GitHub: daspushpita