AI Foundationspredict · compress · act

concepts → Quantity

Quantity

KL divergence

also called Kullback–Leibler divergence · relative entropy

timeless2 connections

extra bits wasted by believing q when the truth is p — never negative, never symmetric

the formal statement
D_KL (bits)
D_KL(p ‖ q) = Σ p(x) log(p(x) / q(x))

Where it sits

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

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.

EntropyKL divergencenothing depends on it yet — a leaf in the reading order

Before it: Entropy

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

It is a kind of: Divergence.

Where to read it

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

07Distance Between Beliefsact 1 · The Substrate

Where it comes from

paperA Mathematical Theory of CommunicationClaude E. Shannon · 1948

Every connection

All 2 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
is a kind ofDivergenceProperty
Order · 1
requiresEntropyQuantity

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.