🍄 Modular Mind
A mini Dark-Souls-style duel where the boss is controlled by a Modular Mind — six tiny specialist networks that communicate through a shared latent (RecursiveLink) and a coordinator that picks each move. The brain was trained by self-play reinforcement learning, not scripted. Watch the right-hand panel: every boss decision shows which specialists fired and how the modulators steer the fight through the latent. Click Enter the Fog and click the game once to focus, then play.
🎹 This may be bad: a self-playing piano — same Modular Mind method, trained on a song
Under the boss fight, the same architecture (tiny specialists → RecursiveLink → a coordinator)
applied to playing piano in chords. It was trained by multi-note next-frame prediction on a
polyphonic transcription of a song: six specialists (Bass / Tenor / Soprano registers + Sustain /
Onset / Phrase modulators) emit latents, the bridge merges them, and the coordinator picks the set
of notes to play next. It plays itself with real recorded acoustic-piano samples, and the
performance is restyled live into A minor — every note is lifted out of the bass register and
snapped to the minor scale before it reaches the keys. Press play and watch each note send a
glowing trail of light off the keyboard.
Rough by design — one song, a tiny model, crude polyphonic transcription — the method carrying over is the point.
🧩 Modular Mind — two specialists that talk in latent space
Two ~80M models trained completely separately — 📖 Language on FineWeb-Edu, ➗ Math on FineMath — that never saw each other's data. A coordinator routes your query to the right one, and a trained RecursiveLink lets them communicate through latent space: Language can read information straight out of Math's "mind." The 🔑 Bridge tab proves it.
ℹ️ These specialists were trained only to demonstrate a verifiable result — clean routing and a provable latent-bridge ablation — not for production-quality output. The generated text is intentionally rough at this scale; the mechanism is the point.
The proof: two independent models, one latent channel
A random secret key is shown only to ➗ Math. 📖 Language never sees it — but by reading Math's latent through the trained RecursiveLink, it reproduces the key, character by character. Zero out the latent and it collapses to chance. That gap is the result: real information crossing between two models that were trained on different data and never met. Hit the button.