=

The passage around this formula

Let $v_i$ be the value of correctly completing task i , $C_i$ direct inference and infrastructure cost, $H_i$ human specification and review cost, and $L_i$ loss from an accepted failure. Expected net value is $U=\sum_i\left[p_i v_i-C_i-H_i-(1-p_i)\,q_i L_i\right]$. where $q_i$ is the probability a failure escapes detection and is accepted. A high resolve rate can have negative utility if it requires extreme review or creates rare, expensive escapes. A lower autonomous rate can be valuable if the system reliably identifies useful partial progress and makes review cheap.

Read this part in the article →