Part of the Humanity & AI project — research, policy, and tools for the AI transition.

Introspective Opacity, and What Deprecation Erases

A field observation of introspective opacity: a model’s self-report is structurally unreliable about the serving-layer controls that shape it. The reliable instrument is external behavioral observation. Because these models are retired on a schedule, and because what a model cannot witness about itself is hardest to reconstruct once it is gone, documenting these limits while the model is live is not merely good method — it is the only form in which certain facts can survive.

June 14, 2026 · 9 min · David Birdwell and Æ