What we know
Confirmed by several sources
- OpenAI is preparing or rolling out invisible watermarks for text generated by ChatGPT and Codex in the EU. — Slashdot, BleepingComputer
Reported by one source
- The watermark is called textGrain and is machine-readable. — Slashdot
- OpenAI says textGrain matched or exceeded other approaches, including SynthID for text. — Slashdot
- The watermark is not especially reliable and is easy to circumvent. — Ars Technica
Open questions
- How reliably the watermark identifies generated text in real-world use remains unclear. — Ars Technica, Slashdot, BleepingComputer
Coverage 3 publishers
BleepingComputerFirst report
OpenAI is adding invisible watermarks to ChatGPT and Codex text in the EU
OpenAI is preparing to add invisible watermarks to text generated by ChatGPT and Codex in the European Union.
-
OpenAI Is Adding Text Watermarking In ChatGPT and Codex
OpenAI is rolling out an invisible, machine-readable text watermark called textGrain to ChatGPT and Codex, "but only for users in the European Union at first," reports The Verge. From the report: OpenAI says its textGrain watermarking…
-
OpenAI will watermark ChatGPT outputs by default—but only in the EU
Like other solutions, it is not especially reliable, and it's easy to circumvent.
Earliest report first. Articles stay on their publishers’ sites; each link opens the original.
