← All parts of this equation

Equation 3 · Part 2 · Ten Ways an Agent Evaluation Can Mislead You Even When It's Working Correctly

Symbol U

M=U+εM = U + \varepsilon
UU

What this part means

the highest m selects simultaneously for high.

Its job in the formula

U is one of the signed contributions combined to compute the quantity on the left.

Where the article explains it

for some error term ε\varepsilon uncorrelated with U , then selecting the run with the highest M selects simultaneously for high U and for large favorable ε\varepsilon — the optimizer is drawn toward the tail of the error term as reliably as toward genuine capability, and the more intensely M is optimized, the larger a share of the observed gain is ε\varepsilon rather than U .

The passage around this formula

…a formal taxonomy, distinguishing at least four distinct failure mechanisms grouped under Goodhart’s name rather than one [ 1 ] . The simplest to state is regressional: if a proxy metric M relates to the true target U by M=U+εM = U + \varepsilon. for some error term ε\varepsilon uncorrelated with U , then selecting the run with the highest M selects simultaneously for high U and for large favorable ε\varepsilon — the optimizer is drawn toward the tail of the error term as reliably as toward genuine capability, and…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.