About

My name is Dave Banerjee, and I am an associate researcher at the Institute for AI Policy and Strategy, where I research AI security and extreme power concentration.

Previously, I did the following stuff:

• I was a summer fellow at the Centre for the Governance of AI, where I threat modeled risks from secretly loyal AIs and investigated whether the US or China could hide data centers (AKA Dark Compute).
• I was a participant in ARENA 5.0, a 5-week ML alignment bootcamp. In my ARENA capstone project, I investigated whether self-perceived superintelligent LLMs (LLMs convinced that they are superintelligent via prompting) exhibit misalignment.
• I was a research fellow in the SPAR program, where I forecasted how much it costs to hack an Nvidia H100 (i.e. how much money, time, equipment, and expertise is required to leak various cryptographic keys off the chip).
• I was a security engineer at a hedge fund, where I did security things.
• I graduated from Columbia University, where I studied computer science with a focus on cryptography, reverse engineering, and machine learning.

If you would like to receive emails whenever I post: Subscribe Here!

— Dave