Vs. Pangram Detector: AI Watermarking Limitations on Human-Sourced Edits

RyanGreenblatt · x · 2026-08-12

Comparing current AI text detection tools, researcher Ryan Greenblatt noted that detectors like Pangram tend not to flag heavy AI transformation of fully human source material (e.g., turning dictated notes into a formal document without generating significant new text).

However, with built-in model watermarking, such heavily edited or transformed human-original content would still carry the watermark. This highlights a granularity issue for watermarking in distinguishing between "purely AI-generated" and "AI-assisted refinement."

Related event: Researcher Analyzes LLM Watermarks: Low-Entropy Outputs Hard to Tag(3 posts)→

Original post →

More from Safety

Safety channel →