I'm a senior at the University of Pennsylvania studying computer science. Before Penn, I served as a helicopter crew member in the Korean Marine Corps. I currently compete on the varsity rowing team while doing ML research.

My current research focuses on reducing risks from AI by understanding, adding, and removing behavior. I'm working with Tomek Korbak through the ML Alignment & Theory Scholars program on AI agent safety. In the past, I spent two years away from Penn leading NLP research at an EdTech startup. There, we built readability assessment systems and question generation models to automatically create practice materials for college entrance exams. I also did research internships at IBM Research and NAVER Cloud, proposing conditional activation steering and curriculum instruction tuning, which both inspired continued research within the companies.

Throughout my research, I've been fortunate to learn from Alex Cloud, Alex Turner, Mantas Mazeika, Inkit Padhi, Karthikeyan N. Ramamurthy, Hyunsoo Cho, and Kang Min Yoo. Before finding ML, I competed in physics olympiads / tournaments throughout middle and high school.

Blog Posts

Neural Networks, Strange Attractors, and Orderliness in Chaos Why do neural networks appear chaotic at the neuron level yet produce high-level representations that can be probed linearly? Strange attractors might give us good intuition to understand the paradox of neural network behavior.
On Getting Started in Research What does it mean to become a scientist? What makes me want to do science?