100 classic human-written texts stress-test Pangram AI detector: formatting alone triggers false positives
GolinoHudson · x · 2026-10-23
An experiment on the Pangram AI detector: pasting Victor Hugo's "Demain, dès l'aube" returned 100% AI while the original scored 100% human — the copy differed only in straight apostrophes, collapsed line breaks, and a missing last line.
- The author then ran 100 public-domain classical human texts across 7 languages (Shakespeare, Keats, Dickinson, Hugo, Baudelaire, Goethe, Dante, KJV...) in 5 versions each, all via Pangram's API, to isolate how punctuation, line breaks, and quote style affect verdicts.
- Reposter notes Pangram is excellent but infallible nowhere: false positives are reportedly rare, yet most critics can't substantiate claims — this experiment is a concrete example.
More from Models
- SEO testing: LLMs are bad at anchor selection but surprisingly good at picking target URLs — gaganghotra_ · 2026-10-23
- NVIDIA releases Nemotron 3.5 Bolt E4B, a 4GB open model for on-device conversational agents — NVIDIAAI · 2026-10-23
- NVIDIA releases open Nemotron 3.5 Bolt E4B 4GB with weights, data and recipes — NVIDIAAI · 2026-10-23
- Gemini 'Argon' bug reportedly fails to analyze uploaded audio files — Numerous-Campaign844 · 2026-10-23
- 2-bit quantized DeepSeek 4.1 Flash tested locally: KDL degrades but still works — bakawolf123 · 2026-10-23
- KOL predicts K3.1 benchmarks sight unseen: benchmaxxed, below Sonnet in practice — teortaxesTex · 2026-10-23