Our approach to EU text provenance rules

OpenAI is addressing EU AI Act requirements by sharing its approach to text watermarking, which is part of its broader content provenance efforts. This initiative aims to help users understand content origins and creation methods, building on existing tools for identifying AI-generated images and audio. However, editing text can significantly weaken watermarks; for instance, replacing 10% of words in 400-token passages reduced detection from 92% to 66%. OpenAI acknowledges the practical limits of current technology and plans to continue improving detection and adapting its approach as technology and regulations evolve.

Unlike previous announcements, OpenAI here details the specific impact of text editing on watermark detection rates, showing a 92% to 66% drop with just 10% word replacement.