OpinionReality Check
OpenAI’s text watermark is a signal, not proof of authorship
At a 1% false-positive target, OpenAI says its detector found marks in about 80% of 200-token psychology passages; synonym edits lowered detection sharply.
Topic
Text Watermarking
2 stories
Models
OpenAI’s planned EU text watermark: what to know
OpenAI’s tests found detection fell sharply after synonym edits; the company has not specified which EU models or Codex outputs qualify.