Posts tagged Goodhart S Law — AI × software engineering, made practical.
You'll learn how a coder agent and a reviewer agent can drift into satisfying each other instead of shipping working code, why per-agent evals miss it, and which signals and design changes catch it.
A number can climb every single week and still tell you nothing — here's the one-question test that separates a real signal from a vanity metric your agents are quietly gaming.
A rising acceptance-rate chart looked like proof our AI coding agent was working, until an hour sitting next to one engineer showed the number couldn't tell 'this helped' apart from 'this got reverted two days later.'