AI Foundationspredict · compress · act

concepts → Field

Field

Control theory

timeless3 connectionsdraft

the mathematics of steering a system toward a target without it wobbling

Where it sits

The prism has six jobs across and eight layers down. Its primary cell isno mode × L0. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

Overlays: Safety & alignment.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

FeedbackControl theoryReinforcement learning

Before it: Feedback

Unlocks: Reinforcement learning

What kind of thing it is — and what it is made of

It is made of: Cybernetics.

Where to read it

The chapter that introduces it, and any chapter that uses it again.

18Feedbackact 4 · The First Attempts

Where it comes from

Every connection

All 3 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 1
has as a partCyberneticsField
Order · 2
requiresFeedbackMechanism
must come beforeReinforcement learningField

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 230 declared edges produce all 236 of these pages. Edit an edge and both endpoints change.