GoKawiilOpenAI Implements Invisible Watermarks on ChatGPT and Codex Text in EU
OpenAI announced plans to embed invisible watermarks into text produced by ChatGPT and Codex within the European Union, using its new textGrain technology that subtly alters word choices to create detectable patterns. This feature will be available in the EU first, with API developers worldwide able to opt in, though it remains off by default. The company also opened applications for its watermark detection tool, which is initially limited to approved researchers. Tests show that editing generated text can significantly diminish watermark detectability, especially with minor modifications or shorter responses.
GoKawiil's interpretation of the reporting above, not reported fact.
This move indicates OpenAI's effort to address concerns about AI-generated content and improve traceability, particularly within the EU's regulatory environment. However, the limitations in detection accuracy and the potential for editing to bypass watermarks suggest that this technology may only serve as a partial solution, highlighting ongoing challenges in reliably identifying AI-produced text.
- OpenAI is adding invisible watermarks to EU-generated AI text.
- Watermark detection can be compromised by editing or short responses.
- The technology aims to support AI content verification but has limitations.
Source: bleepingcomputer.com, 2026-10-05
Published there as: “OpenAI is adding invisible watermarks to ChatGPT and Codex text in the EU”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.