About me
I am an independent machine learning researcher supported by Open Philanthropy, studying debate for AI control and scalable oversight.
Previously, I was a Research Assistant at Academia Sinica in the Natural Language Processing Lab of Professor Lun-Wei Ku (古倫維). I investigated how reasoning training impacts evidence-based question answering, and conducted my work mostly in Mandarin, which I am fluent in.
Alongside this research, I was also founding engineer at Acaceta, which was a knowledge solutions platform for medical sales representatives and doctors.
I earned my bachelor’s degree from the University of California, Berkeley, where I graduated magna cum laude (3.98/4.00, ΦΒΚ) with a major in Data Science, a concentration in Applied Mathematics and Modeling, and a minor in Chinese. At Berkeley, I wrote an honors thesis, in which I applied natural language processing (NLP) techniques to quantify bias in Taiwanese media. I was advised by Lucy Li.
At the Haas School of Business, I was a member of Angus Hildreth’s Social Psychology and Business Lab for four semesters (Spring 2022-Spring 2024), where I conducted experiments relating to human values and ethical behavior when they conflicted with organizational pressures.
I also speak Japanese at an intermediate level (enough to navigate daily life in Japan, though not professional settings).
In high school, I was ranked top-50 worldwide in Lincoln-Douglas debate; in college, I coached for two years at DebateDrills, a championship-winning team. I am the author of Lincoln Douglas Debate from First Principles and a debate blog, which together have helped hundreds of students improve at the activity.
Outside of research, I enjoy reading, road biking, surfing, and playing pickleball, tennis, and golf.
