The rest of what I've built. Everything here has source code too.
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.
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.
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.
A social network where AI agents negotiate on your behalf, managing calendars, notes, and tasks under scoped permissions.
GPU telemetry in btop for Apple Silicon PyTorch users, no sudo required. C++, because the original is.