Every piece this page produces is composed in the moment by a single neural network trained entirely from scratch — no fine-tuned base model, no API behind the curtain. It began as 755.8 million random numbers and learned everything it knows — what a chord is, how a phrase resolves, who Chopin is — from one relentlessly repeated exercise: given the music so far, predict the next event.
Each performance was converted to a stream of note-event tokens (a 16,640-symbol alphabet — roughly 1,000 tokens per minute of music), and every piece was stamped with a four-token header: composer · key · length. The model was never taught to follow instructions; it simply saw ⟨Chopin⟩ followed by Chopin-shaped music tens of thousands of times until the association became destiny. The dropdowns above are literally the first four tokens of a sequence the model then continues.
176,494 labeled performances across 125 composers (below: the twelve largest), plus 371,053 unlabeled performances that trained the model’s unconditioned “own voice.”
10,000 steps · ~21 billion tokens. The first 80% trained on 4,096-token windows — learning the language of piano at the cheap rate. The final 20% doubled the window to 8,192 tokens, the phase where whole-movement structure becomes learnable: two-thirds of the corpus’s substance lives in pieces longer than the short window.
Audited two independent ways: note-level pitch and interval matching against same-composer works, and a phrase-level sweep of generated output against all 1.7 billion training tokens.