OpenAI unveils textGrain, its text watermarking approach for the EU AI Act

OpenAI announced its plan to address the EU AI Act's text provenance requirements. The core technology is textGrain, which adds invisible statistical signals to the model's word choices, then uses a detector to determine whether text carries an OpenAI watermark. API customers can now voluntarily enable text watermarks for some models, with it being off by default. In the coming weeks, OpenAI will add invisible watermarks to eligible ChatGPT and Codex outputs in the EU and will open detector applications, initially limited to approved researchers and expert institutions. OpenAI said textGrain met or exceeded other approaches in evaluations, including SynthID for text, but detection is still affected by text length and rewriting: at a 1% target false-positive rate, detection rate is about 80% for 200-token passages and about 95% for 400-token passages, with notably lower results for math content; replacing 10% of synonyms in a 400-token passage drops detection from about 92% to 66%, and replacing 25% drops it to 17%.