Hey there!
My name is Coby, and I’m a student researcher with interest in mechanistic interpretability and a broader interest in most things related to technical AI safety and alignment. In my free time, I love composing and performing classical music, hiking, and skiing. I’m currently doing my undergrad at Yale.
See my research or personal writing.
Construction Zone!
This website is very much so in progress. I plan to write much more, flesh things out, and fix things in the near future. Forgive me if you encounter anything that is buggy, incomplete, or unprofessional.
News
- August 2025 — I completed the Yale Effective Altruism introductory fellowship.
- May 2025 — I finished SPAR and presented our findings (so far) at the poster session. We are continuing to work on the project beyond the program
- February 2025 — I was accepted to the SPAR program under Dr. Ronak Mehta to research models that are inherently interpretable.
- November 2024 — Our activation steering data extraction project placed 7th in the LLM Privacy Contest at NeurIPS