Prakrat Agrawal

Research

I aim to work on important and interesting problems by doing good science. I’m currently focused on helping make AI go well for humanity.

• Investigating model propensity for self-preserving behaviours. Work done during SPAR under Robert McCarthy.
• Developed a novel distance function for Boolean Circuits. Work done during SRS under Todor Markov.
• Wrote some Python for ECOLE Lab and collected some data for the Social and Moral Judgment Lab.