← Back to article

Equation 2 · What We Still Cannot Do: Open Problems in Frontier Model Systems

What does this equation mean?

Pr⁡(correct∣c^=c)≈c\Pr(\text{correct} \mid \hat{c} = c) \approx c

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.

Inputs and operationsc) ≈ c
Result or conditionPr(correct mid hatc
How to read the two sides of this formula. Follow the article passage for the meaning of each quantity.

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

c^\hat{c}

Symbol hatc

hatc appears in the conditional probability being evaluated. The vertical bar identifies the information or condition supplied to that probability.

Understand this part →

cc

Symbol c

c appears in the conditional probability being evaluated. The vertical bar identifies the information or condition supplied to that probability.

Understand this part →

=

=

The expressions on both sides represent the same quantity under the stated assumptions.

Understand this part →

See an illustrated explanation →
≈

≈

Approximately equal to; the equality is not exact.

Understand this part →

Pr⁡\Pr

Probability operator

The probability operator gives the chance of the event named inside its brackets or parentheses.

Understand this part →

How to interpret it

Its accuracy depends on the assumptions and range of use described in the article. Read it with the definitions, units, and assumptions supplied by the article.

What the article says around this equation

The structural difficulty is that a next-token distribution is not an epistemic state. A model trained to maximise likelihood over text produces a confident-sounding continuation because confident-sounding continuations are what the corpus contains, not because it has assessed its own evidence. Calibration can be measured — for a predicted confidence c one can ask whether Pr⁡(correct∣c^=c)≈c\Pr(\text{correct} \mid \hat{c} = c) \approx c. holds across bins — and it can be improved by post-hoc adjustment. What has not been demonstrated is a mechanism by which a model represents its own ignorance in a way that survives fine-tuning, distribution shift, and the pressure of an objective that rewards answering.

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

See this formula across 1 published context →

Browse the mathematical compendium →