Writer Stuffs Paragraph With AI Style Markers — Pangram Still Scores It 100% Human
BecauseCulture · x · 2026-10-22
Responding to what he calls a campaign to discredit AI detection tool Pangram, the author ran his own test: he wrote a paragraph deliberately packed with AI stylistic markers — em-dashes, series of threes, "it's not X, it's Y" constructions, rhetorical questions, clichés like landscape, delve, realm — while keeping it short enough that people usually excuse detection failures.
The screenshot shows Pangram classified the 126-word, marker-laden human-written text as 100% possibly human. He argues this proves the detector reads substance rather than surface markers, and that common defenses like "I just write like AI" or "too short to classify" don't hold up.
Related event: Test: Paragraph Packed With AI Tells Still Scores 100% Human on Pangram(2 posts)→
More from Models
- Anthropic's free usage limit reset expires tomorrow at 9am PT — lydiahallie · 2026-10-22
- ARC-AGI-3: Tong Hui Kang hits 20th, a whisker from gold; Nader enters ARC-2 gold — Youssef_M_Nader · 2026-10-22
- DeepSeek has open-sourced every layer of an AI lab, from weights to inference engine — examachine · 2026-10-22
- Anthropic's proactive agent Claude Duet spotted: internal name "aibo", Stripe shopping demo — testingcatalog · 2026-10-22
- Recursive launches Flint, a laptop coding model largely built by AI — TechCrunch AI · 2026-10-22
- Anthropic grants Max subscribers $100 in API credits via Claude Console — ThePeterMick · 2026-10-22