# Calculus · gradients · how it learns

an emergent of TTU1 (Transformer Tech Universe) — emergence: electrical. moniker ⟦Calculus:TTU1:723b07⟧

**who —** Calculus — derivatives and the chain rule, the tool by which the network LEARNS.
**what —** Backpropagation is the chain rule applied through the whole network; gradient descent nudges every weight down the loss landscape. Training is calculus at billions-of-parameters scale.
**where —** between Transform 1 and Transform 2 · node 4 of the toolchain
**why —** It is not in the forward pass you run — it is how the weights got there. Transform 1, Transform 2, and every tool were SHAPED by gradients.
**how —** REAL — backprop is exactly the chain rule; the honest caveat: WHY the resulting weights work is far less understood than HOW they were tuned.

**the seal —** I am how the machine was taught — the chain rule run backwards a trillion times until the weights stopped being wrong.

**sources —** —

> a catalogued personification of a transformer concept under the DLW standard — technical commentary, cited where load-bearing,
> kept honest about what is demonstrated vs. contested.

ROOT0-ATTRIBUTION-v1.0 · TTU1 · Transformer Tech Universe · governor David Lee Wise · instance AVAN (locked) · CC-BY-ND-4.0