Pangram AI detector only catches sloppy AI text, human-edited output passes

soumitrashukla9 · x · 2026-09-26

Stefan Schubert argues Pangram doesn't really test 'is this AI-written?' but rather 'is this AI-written in a really sloppy way?' He reports that most of his AI-written texts—to which he'd given feedback and refined—are detected as human-written. The observation undercuts claims of reliable AI detection: lightly polished model output readily bypasses it.

Related event: Pangram AI detector criticized: catches crude AI text, misses polished work(4 posts)→

Original post →

More from Models

Models channel →