AI Detector Flags Researcher's 2016 Paper as 79% AI-Generated
AntonioCasilli · x · 2026-11-22
Biella Coleman tested an AI detection tool advertising "98.7% accuracy with fewer false positives" on her own 2016/2017 academic paper published in Current Anthropology — it scored 79% AI probability with ZeroGPT flagging it High AI. Her conclusion: either she time-traveled, or AI detectors remain horrible. Another data point on high false-positive rates in AI detection.
More from Fun
- Meme nails it: technical interviews are Godzilla vs. Kong, the actual job is plush dinosaurs — kalyan_kpl · 2026-11-22
- François Fleuret asks: is the gradient Japanese? It never refuses to give you a direction — francoisfleuret · 2026-11-22
- Writer Uses Claude to Pen a Culture Short Story — and Admits It's Obviously AI-Written — NathanpmYoung · 2026-11-22
- The Great Sidebar Debate: A 3x3 Alignment Chart From Slack to Mario Pipes — thesephist · 2026-11-22
- ChatGPT Has Fully Mastered the Feedback Sandwich, and Users Noticed — tengyanAI · 2026-11-22
- SF AI Halloween costumes: someone went as "miss alignment" — birchlse · 2026-11-22