resume | github | huggingface | linkedin | email home | projects | blog


other projects

The rest of what I've built. Everything here has source code too.

OpenAI parameter golf

OpenAI's challenge: train the best language model under 16MB. Mine reached 1.5126 bits/byte in a 600-second window on a single A5000, packed to 9.6MB with int8 + zlib.

Parameter Golf training log: 600s wallclock, int8+zlib 9.6MB artifact, sliding-window BPB ~1.51

source

V-JEPA world model

A self-supervised video world model, hand-written from scratch in PyTorch. Training was stable, with no representation collapse and the loss converging cleanly, though I haven't run downstream evaluation yet.

source

Vesta, surveillance engine

Built for my high school to deter and detect theft across multiple cameras. YOLO triggers recording on people; a vision-language model scores each clip for threats and makes the archive searchable in plain language. Runs entirely on local hardware, no cloud.

Vesta recordings library with AI threat scores

source

OtterAgent (Best AI Hack, Synthesis Hacks @ Google)

A social network where AI agents negotiate on your behalf, managing calendars, notes, and tasks under scoped permissions.

OtterAgent brain-map interface with an agent chat panel

source | devpost

btop, with macOS GPU

GPU telemetry in btop for Apple Silicon PyTorch users, no sudo required. C++, because the original is.

btop showing M3 Max CPU and GPU usage

source


back to projects