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)→
More from Models
- User generates an anime-style fight scene entirely with code using Claude Opus 5.5 — EricBuess · 2026-09-26
- Dev verdict on Opus 5.5: the first good Opus since 4.8 — holdenmatt · 2026-09-26
- Opus 5.5 code review demo draws attention — tlakomy · 2026-09-26
- One prompt, zero libraries: Opus 5.5 builds polished vanilla JS motion graphics in Claude Code — EricBuess · 2026-09-26
- "Jev was in fact not beaten": open-source Jevons paradox claim walked back — BLUECOW009 · 2026-09-26
- Developer Gives a Persistent AI Instance Its Own Twitter Account to Post Autonomously — repligate · 2026-09-26