Welcome to my website! I am an MEng student at MIT studying Artificial Intelligence and Decision Making (Course 6-4). I am in the Cyborg Pyschology group under Prof. Pat Pataranutaporn in the Media Lab.
My primary research interests lie in mechanistic interpretability for both scientific understanding of LLMs and improving their safety. I also am interested in how we can apply mechanistic interpretability to create interfaces that allow us to better monitor and control AI, for both technical and non-technical users.
Outside of work, I enjoy traveling, and learning other languages, hiking, videogames, and everything science fiction.
Email - CV - LinkedIn - Google Scholar - Github
Selected Works
Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
Sheer Karny*, Anthony Baez*, and Pat Pataranutaporn
*Equal Contribution
ACM Conference on Intelligent User Interfaces 2026
Code
Guaranteeing Conservation of Integrals in Physics-Informed Neural Networks
Anthony Baez, Wang Zhang, Ziwen Ma, Subhro Das, Lam M Nguyen, and Luca Daniel
Arxiv Preprint
Code