multiplication

The passage around this formula

A useful, explicitly illustrative way to see the size of that gap is to price coverage directly as a scenario, not a reported figure: $C_{\mathrm{cov}}(D) = D \cdot h \cdot w$. the cost of testing D domains to an adequate depth h (in expert-hours per domain) at a specialist wage w . Anchoring h at roughly 150 hours, taken from Anthropic’s single-domain biosecurity effort, and w at a conservative 50 to 100 US dollars an hour for domain expertise — well below typical consulting rates for the specialists these programmes actually recruit — testing even fifty domains to that depth, a small number next to the realistic combination of languages, deployment surfaces, and misuse categories a deployed model faces, comes…

Read this part in the article →