I'm a PhD candidate at the University of Toronto and Vector Institute, supervised by Roger Grosse and Geoffrey Hinton. I am also part of Anthropic's Alignment Science team.
I work in the intersection of deep learning and AI Safety. I'm interested in studying the robustness and generalization patterns of large language models. I also work on deriving scaling laws to forecast the development of potentially dangerous capabilities.
Engineering Science, University of Toronto; Bachelor of Applied Science and Engineering
- Specialized in Robotics.
- 3.98 CGPA, First in Graduating Class in Engineering Science, 2019.