← Back to article

Equation 2 · Small and On-Device AI in 2035: Scenarios and Falsifiers

What does this equation mean?

L(t)L(t)

Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.

This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.

Read it piece by piece

LL

Symbol L

L is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Understand this part →

tt

Symbol t

t is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Understand this part →

How to interpret it

Read this expression with the definitions, units, and assumptions supplied by the article.

What the article says around this equation

Whether on-device AI becomes the default computing substrate for everyday tasks — the thing a phone or a laptop does locally as a matter of course, with the cloud as the exception rather than the rule — is not a third axis; it is what the other two jointly produce, and testing that jointness is exactly what the room’s validation bench exists to do. Write P(t) for the share of everyday-task requests an on-device model can handle at rough parity with a cloud-frontier model — Axis A’s own proxy — and L(t) for the share of deployments where on-device personalization is reliable enough that a user or an operator trusts it without a cloud fallback — Axis B’s own proxy. A device that is fast but…
Read the full surrounding passage
Whether on-device AI becomes the default computing substrate for everyday tasks — the thing a phone or a laptop does locally as a matter of course, with the cloud as the exception rather than the rule — is not a third axis; it is what the other two jointly produce, and testing that jointness is exactly what the room’s validation bench exists to do. Write P(t) for the share of everyday-task requests an on-device model can handle at rough parity with a cloud-frontier model — Axis A’s own proxy — and L(t) for the share of deployments where on-device personalization is reliable enough that a user or an operator trusts it without a cloud fallback — Axis B’s own proxy. A device that is fast but generic still routes anything that needs to know the user to the cloud; a device that personalizes beautifully but cannot match cloud capability on hard tasks still routes those tasks out. Becoming the default substrate needs both conditions at once, not an average of them:

Read the equation in its article →

Sources cited in the article section

These citations give research context. Read each source to check which claims it supports.

Return to Small and On-Device AI in 2035: Scenarios and Falsifiers

See this formula across 2 published contexts →

Browse the mathematical compendium →