AI detector Pangram keeps flagging human prose over Oxford commas, user says it's "just vibes"
aronchick · x · 2026-09-04
Developer aronchick vents that Pangram repeatedly flags his entirely human-written pages as AI, seemingly because he follows standard writing practices like the rule of three and Oxford commas. Worse, the tool gives zero guidance on where or why text was flagged, leaving him no way to revise — "it's just vibes," he concludes. The complaint highlights a familiar flaw of AI detectors: judging by stylistic surface features and punishing polished human writing, with no explainability.
Related event: Pangram AI Detector Repeatedly Flags Well-Written Human Text as AI(7 posts)→
More from Fun
- Dave Ramsey's 'get rich' secret, satirized: raise $100M and scatter $500K checks — StewartalsopIII · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Claude Code over ADB guts a bloatware-laden Android TV, freeing ~90% more RAM — edwinarbus · 2026-10-21
- Developer uses Claude to fix his adware-slowed Xiaomi TV, releases tool for any Android TV — edwinarbus · 2026-10-21
- People are using Claude Code to debloat ad-ridden smart TVs — edwinarbus · 2026-10-21
- Grady Booch: TechCrunch wants to interview me even though it blocked me — Grady_Booch · 2026-10-21