About

I am an Independent researcher working on AI Alignment with a background in math.

My primary research aims to develop a theory of agents and their goals. One hope for this agenda is that it can inform the development of tools and methods for detecting, interpreting, and controlling an agent’s goals. This has natural applications to the AI alignment problem and, in principle, would offer a solution to the problem of deceptive alignment.

Other topics that currently interest me include theories of AI interpretability, meditation, math, compassionate agents, and various ideas surrounding the technological singularity.

For fun, I enjoy learning, exploring cities & nature, dancing, spending time with friends & family, watching films, meditation & relaxation, and (contemporary) art.

Before working on AI Alignment, I completed a PhD in math from the University of Warwick, UK.

Contact me at: <first name>.<last name>@gmail.com