My goal is to better understand human nature, and use that knowledge to help shape a more flourishing future for everyone. To do this, I build interpretable AI systems capable of understanding and forecasting human behavior, aiming to automate and scale the scientific study of human behavior itself. By generating reliable and interpretable insights, I hope to equip decision-makers with tools to make better judgements.

I am pursuing this work as a PhD student in the Machine Learning Group at the University of Toronto, where I am fortunate to be advised by Roger Grosse and Jimmy Ba. I also work with the Forecasting Research Institute on AI judgemental forecasting and hypothesis generation projects, working with Philip Tetlock, Ezra Karger and Chris Karvetski.

My current research builds on my earlier fundamental research in deep learning and AI safety, and past training in behavioral sciences. My experience with the fundamental principles of optimization, statistics, and information theory provides the solid technical foundation central to my work today. You can find an overview here.

I believe in building communities around this mission. I co-founded UTMIST and for.ai (acquired by Cohere to become Cohere Labs) which have since grown into vibrant communities that provide foundational opportunities for aspiring AI researchers and engineers. As an active mentor, I also highly recommend several University of Toronto programs to current undergraduates, which you can find on this list.

I’m always excited to learn and grow, and I welcome your thoughts and invite you to leave (anonymous) feedback.