Research into how models actually learn — architecture, training, memory — and an attempt to build something that learns like a child. Draw an architecture out of tensor primitives, compile it straight to the GPU, and watch the neurons light up.
Most people use models. This is about understanding them — from the tensor up. If you can draw an architecture, compile it, and race it against another, you build real intuition for why one design wins and another doesn't.
A tiny transformer’s neurons placed on a sunflower (Fibonacci) sphere, lighting up as it reads a sentence. Turning the vectors inside a model into a picture you can actually watch.
A deterministic, human-owned loop that keeps a model learning: it trains, tests itself, rolls back mistakes, prunes memory, and sleeps to consolidate — while the loop itself can never be rewritten by the model.
Attention drawn by hand from three matmuls and a softmax, raced against the same network without it. On matched compute, attention won — val loss 2.40 vs 2.50. A real result from a hand-drawn network.
The pieces are being assembled into one living system — a “brain” and its organs. The rule that keeps it safe: three kinds of memory (the shared model weights, private per-user memory, and short-term working memory), and only the human-owned Control Plane ever writes to the shared weights.