(Kaileh57)
I co-founded Sculptor AI, a Seattle nonprofit doing open-source AI research, where I am Chief Scientist and sit on the board. My work covers language models, autonomous-vehicle perception, and scientific machine learning, including simulation-based inference for brown-dwarf atmospheres.
I study computer science at the University of Washington Paul G. Allen School, class of 2030. Next summer I’m joining comma.ai in San Diego as a machine learning intern.
I train neural posterior estimators to account for uncertain molecular opacities in brown-dwarf spectra. On perturbed simulated spectra, opacity marginalization improves nominal 90% C/O interval coverage from 61.4% to 89.4% in matched three-seed ensembles. On JWST spectra of 14 brown dwarfs, the final ensemble contains the published C/O of a T8 benchmark that every fixed-opacity network misses.
I write about model behavior, AI safety, and evaluation on my blog. I also gave the TEDx LakesideSchool Youth talk “The Cracks in AI Safety” in March 2026.
My hardware projects include an RP2040 development board (datasheet) and an NFC PCB business card.
I also make games and small interactive experiments: Graftmancer, Arcade Multiplayer Racing, and falling squares.