Hi! I'm Logan.

I do technical philosophy and I love intellectual history. I study at Stanford and work on AI interpretability research.

I want to contribute to the human project.

↓

This site is a little partial simulacrum of me. It's a record of my growth, my confusion, my triumph and frustration. Some highlights:

• A short description of my main intellectual project and a (slightly old) list of conversation topics I'm excited about
• A mini update on my recent interp work
• I would really like it if you had a personal website and I think it would make the world better
• My walkthrough of the two papers on Parameter Decomposition, a recently-published technique in interpretability
• An extended research paper on why it's Descartes' fault that philosophy of mind sucks, and the practical problems that are downstream of it
• The human project as a meaningmaking narrative
• The beginnings of a collected passages page

Site Links

Some things I love:

Cowboy camping Keynes, Wittgenstein, and Grothendieck Fresh fruit Manzanitas and ponderosa pines The names of Amtrak train lines The Johnson-Lindenstrauss lemma Seagulls in a port town Ontology of the wave function Textbooks Angel's Landing, Zion National Park Libraries Chocolate milk All Souls College, Oxford Diagonalization arguments Jorge Luis Borges

arXiv papers Airship startups Good bread Fireflies Language Birds of prey Long text files Improvisation and folk music Memetic analysis Esotericism Carved wooden bookends Wikipedia Isomorphism Standardized paper sizes Scriabin

I hope some of these things are interesting to you! If they are, email me at logan graves dot com or dm me on Discord at lgngrvs. (As a disclaimer, I am spending most of my time offline these days, so I may be quite slow to respond; please don't take that as an indication that I do not want to talk to you!)