50 pre-ChatGPT novels tested against Pangram AI detector: zero false positives
TuhinChakr · x · 2026-10-24
Amid debate over AI detector Pangram's false-positive rate, Tuhin Chakrabarty (Stony Brook), author of the study on AI-generated books on Amazon, ran a reverse test: 50 self-published novels released before ChatGPT were submitted to Pangram. Since none could be AI-generated, any flag would be a false positive — and all 50 came back negative. Novelist Vauhini Vara had also reported being unable to trick the system. An initial, though limited, data point supporting Pangram's accuracy claims.
More from Models
- Leaked Claude UI screenshot shows unannounced Opus 5.5, Opus 5 and Fable 5.1 models — adonis_singh · 2026-10-24
- Developer on Claude Opus 5.5: "nothing else even comes close right now" — prasenx · 2026-10-24
- NYU/UT Austin paper: LLMs write convoluted text due to length-penalty optimization — menhguin · 2026-10-24
- Seven independent tests find AI detector Pangram false-positive rate near zero — TuhinChakr · 2026-10-24
- Dev compiles incident-triage SOP into a fine-tuned 3B model: 93% accuracy at 8.4x lower cost — arpit_bhayani · 2026-10-24
- Human-written article fails multiple AI detectors — several sell 'humanizer' services — aisatsana__ · 2026-10-24