OpenAI will add a digital watermark to text and code generated in the EU to comply with the region's new AI transparency rules. The company will soon begin adding an invisible watermark to text and code generated in the EU, following a similar move by Anthropic earlier this year. OpenAI is using a proprietary system called textGrain that "adds an invisible statistical signal to the model's word choices." Once added, a detector can spot these signals and ascertain if there's a watermark. The company says the system "matched or exceeded" the performance of other approaches, like Synth ID for text. However, it cautions that "strong performance under ideal conditions does not guarantee reliable detection in everyday use."
It admits that shorter text is harder to detect, with around an 80 percent success rate. The same goes for "content such as mathematics." Even editing text seems to bring down the success rate. OpenAI plans to make the technology available in open source so others can tweak it. The watermark will not be enabled by default, except for "eligible ChatGPT and Codex text output in the European Union." Customers can opt-in "for select models." Access to the detection software will initially be limited to "approved researchers and expert organizations." Article 50 of the EU's AI Act mandates that providers of generative AI systems make text outputs identifiable in a machine-readable way, with pre-existing entities like OpenAI, Anthropic, Microsoft, Google, and Meta having until December 2 to comply.
Source: Engadget · Summarized by HeadlinesBriefing