Notes & essays
Writing
A place for technical essays, research notes, implementation walkthroughs, and questions I’m still working through.
Nothing published yet.
I’m preparing this space for writing about mechanistic interpretability, AI safety, mathematical foundations of machine learning, reproducing research papers, representation learning, and lessons from experiments.
I’d rather publish something carefully worked through than fill the page with placeholder articles.
Topics I hope to explore
Mechanistic interpretability · Generative models · Representation learning · Research reproductions · Mathematical intuition · Experimental methodology