RC RANDOM CHAOS

OpenAI Adds Invisible Watermarks to EU ChatGPT, Codex Text

· via BleepingComputer

Original source

OpenAI is adding invisible watermarks to ChatGPT and Codex text in the EU

BleepingComputer →

OpenAI is introducing invisible watermarks for ChatGPT and Codex outputs in the EU using textGrain technology. The watermark subtly alters word choices to create a detectable statistical pattern. While API developers globally can opt in, the feature is disabled by default. OpenAI is also opening applications for its watermark detector, but access is limited to approved researchers. The company acknowledges limitations, noting that editing can reduce detection accuracy significantly. Watermarking does not reveal authorship details or human editing contributions, and its effectiveness varies by text length and subject matter.

Read the full article

Continue reading at BleepingComputer →

This is an AI-generated summary. Read the original for the full story.