I work on mechanistic interpretability and evaluation of language models, currently as an independent researcher. My focus is on distinguishing what models retrieve from what they compose, and on building evaluation methods that hold up outside the lab.
Before this I spent a decade in research and clinical care — public health and critical care nursing, then AI Product Design at Stanford, where I earned an MS. I founded Syminar, a clinical education platform, and led it through a responsible exit. The common thread is making systems feel legible to the people who live or work inside them. It's what I'll be doing for the rest of my life.
In progress. Notes on interpretability experiments will land here.