Zero pre-AI texts flagged by top detectors across internal, third-party, bounty tests

Afinetheorem · x · 2026-11-17

Follow-up in the Afinetheorem–Timnit Gebru detector debate: beyond internal tests, third-party evaluations and open internet prize challenges all found zero examples of pre-AI writing (from authors of any background) tagged as AI by top detectors — which he presents as decisive evidence against blanket claims that detectors are unreliable.

Original post →

More from Fun

Fun channel →