fraction

The passage around this formula

There is also a structural reason cost cannot be separated from reliability. If a run costs $\bar{c}$ on average and succeeds with probability p , and the operator simply retries until success, the expected spend to first success is $\mathbb{E}[\text{cost to first success}] = \frac{\bar{c}}{p}$. which means a cheap unreliable agent and an expensive reliable one can occupy the same operating point. Reporting either number alone conceals which one you have bought. The honest artefact is a curve — quality against spend, produced by sweeping the effort level and the retry policy — rather than a point, and the honest comparison places two systems at matched spend and asks which reaches further.

Read this part in the article →