What does this equation mean?

Because $p_{\text{esc}}$ is small on ordinary traffic, the average cost collapses toward $c_{\text{probe}}$ even though $c_{\text{exchange}}$ did not get any cheaper — which is the documented reason Anthropic reports the overhead falling from 23.7% to roughly 1% between generations, alongside a drop in the harmless-traffic refusal rate to 0.05% and, across more than 1,700 cumulative red-teaming hours against the new system, one high-risk vulnerability found, which Anthropic describes as a detection rate of 0.005 per thousand queries — the lowest of any defense it reports having evaluated [ 1 ] . Every one of those figures is Anthropic’s own measurement of its own system; none has yet appeared in an independently authored, peer-reviewed replication.