Research
Behind Spacewar: Orbital Duel sits a small machine-learning lab, and these are its experiments: real models, real training runs, real failures, written up as they happened. Tiny networks only: brains measured in kilobytes, built to show the whole pipeline from first principles to a shipped artifact.
Every experiment is written at three depths, and you choose per chapter: the plain story anyone can read; ▸ FOR THE LEARNERS, which rebuilds the machinery from first principles for any scientifically curious reader (no machine-learning background assumed); and ▸ FOR THE DATA SCIENTISTS, the working notebook in the field's own language, with references to go deeper still.
Notebook 01 · the pilot
A 6,220-weight network (half a worm's brain) starts with zero knowledge and teaches itself to fly, fight, cheat, get caught, and bend lasers around the black hole. With the three-minute film.
Notebook 02 · the eye
The pilot got its senses served on a plate. Real systems get pixels. A 28,000-parameter network watches raw game frames and paints every ship, every laser, and the hole. Then it gets squeezed into 8-bit integers you can't tell from the original.
The code · the pilot's lab
Everything in the pilot's notebook is MIT-licensed and runs on an ordinary laptop: the physics, the trainers, six graded experiments, and every era's champion ready to replay. Watching a match in your browser takes under a minute and no install.
The code · the eye's lab
The spotter's whole pipeline ships in the same repo: a renderer that labels its own frames, about five minutes of training on a laptop, and the frozen golden bundle any port can prove itself against, down to the last bit.
Implementation · private
How the experiments could run on a target hardware implementation. Two working documents: one for the design engineer, one for the engineering manager. Rendered, copyable, downloadable.
Private · mechanism canary
Test fixture for the private-experiment machinery.