AI Foundationspredict · compress · act

concepts → FailureMode

FailureMode

Overfitting

timeless2 connections

memorising the training set instead of learning the pattern

Where it sits

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

Overlays: Evaluation & methodology.

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.

nothing comes first — this is a starting pointOverfittingnothing depends on it yet — a leaf in the reading order

How it goes wrong — and what answers that

answers to those failures
Regularizationany penalty that keeps a model simple so it stops memorising

Where to read it

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

11Why Memorizing Failsact 2 · The Instruments

Where it comes from

paperScaling Laws for Neural Language ModelsJared Kaplan, et al. · 2020

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.

Failure · 2
is a failure mode ofGeneralizationProperty
is mitigated byRegularizationMechanism

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.