Paul Colognese

I am an independent researcher working on AI safety.

Recently I've been building AI control evaluations for organizations such as the UK AI Security Institute and Anthropic. Before this, I worked on risk modellinng for UK AI Security Institute, independent research related to goal detection via interpretability, and other AI safety related projects.

Prior to working on AI safety, I did a PhD in math (see link in left panel for more details).

Aside from the above, I'm interested in Tibetan Buddhism, math, the technological singularity, consciousness, understanding utopias, and other such topics.

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

Contact: firstname.lastname@gmail.com