← Back to article

Equation 7 · What We Still Cannot Do: Open Problems in Frontier Model Systems

What does this equation mean?

nmax⁡≈ln⁡τln⁡q.n_{\max} \approx \frac{\ln \tau}{\ln q}.

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 equation gives an approximation: it relates the quantities while allowing an approximation. 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

nmax⁡n_{\max}

Symbol n_max

the derivative of.

Understand this part →

τ\tau

Symbol τ

the target success rate.

Understand this part →

qq

Symbol q

the respect to.

Understand this part →

fraction

fraction

Divide the expression above the line by the one below it.

Understand this part →

See an illustrated explanation →
≈

≈

Approximately equal to; the equality is not exact.

Understand this part →

subscript

subscript

The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.

Understand this part →

ln⁡τ\ln \tau

Numerator: ln τ

The complete quantity above the fraction bar.

Understand this part →

See an illustrated explanation →
ln⁡q\ln q

Denominator: ln q

The complete quantity below the fraction bar; it must be nonzero for this division.

Understand this part →

See an illustrated explanation →

How to interpret it

With a fixed numerator, increasing a nonzero denominator reduces the fraction. Its accuracy depends on the assumptions and range of use described in the article.

What the article says around this equation

so the horizon that can be sustained at a target success rate τ\tau is nmax⁡≈ln⁡τln⁡qn_{\max} \approx \frac{\ln \tau}{\ln q}. The derivative of nmax⁡n_{\max} with respect to q is steep near q = 1 , which is the good news — small per-step gains buy disproportionate horizon. The bad news is the same expression read the other way: sustaining an order of magnitude more steps requires driving per-step error down by an order of magnitude, and every one of the six problems above is a term in that per-step error which scale is not reducing. Verification, calibration, and memory are precisely the mechanisms that break the exponential by resetting accumulated uncertainty. Without them, capability gains are spent buying a slowly lengthening…
Read the full surrounding passage
so the horizon that can be sustained at a target success rate τ\tau is nmax⁡≈ln⁡τln⁡qn_{\max} \approx \frac{\ln \tau}{\ln q}. The derivative of nmax⁡n_{\max} with respect to q is steep near q = 1 , which is the good news — small per-step gains buy disproportionate horizon. The bad news is the same expression read the other way: sustaining an order of magnitude more steps requires driving per-step error down by an order of magnitude, and every one of the six problems above is a term in that per-step error which scale is not reducing. Verification, calibration, and memory are precisely the mechanisms that break the exponential by resetting accumulated uncertainty. Without them, capability gains are spent buying a slowly lengthening horizon rather than a qualitatively longer one.

Read the equation in its article →

For background, read the article’s source list.

Return to What We Still Cannot Do: Open Problems in Frontier Model Systems

See this formula across 1 published context →

Browse the mathematical compendium →