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
- Indie dev flips from $20 Pro back to $200 Gemini Ultra after two days of deep use — yihui_indie · 2026-11-11
- Leak: Google's upcoming model lineup includes Hydrogen, Krypton, Helix and a video model — koltregaskes · 2026-11-11
- Rumor: OpenAI's Astra 6.2 near, spotted in Codex logs and Google Cloud quotas — haider1 · 2026-11-11
- Same prompt head-to-head: Fable 5.2 spends 3x time, 2x cost for auteur flair — iamfakhrealam · 2026-11-11
- Krafton open-sources Raon-1 nano, a 1.5B on-device LLM distilled from MoE — DimitrisPapail · 2026-11-11
- Do typos discomfort LLMs? Tokenization quirk sparks debate — menhguin · 2026-11-11