AI Foundationspredict · compress · act

concepts → Property

Property

Inference scaling

timeless2 connectionsdraft

trading more thinking at answer time for better answers

Where it sits

The prism has six jobs across and eight layers down. Its primary cell ismeasure × L5. 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.

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

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

It is made of: Test-time compute.

Where to read it

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

41Thinking Before Answeringact 9 · The Frontier

Where it comes from

paperScaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model ParametersCharlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar · 2024

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
has as a partTest-time computeQuantity
Contrast · 1
trades off withScaling lawResult

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.