OpenAI will watermark ChatGPT text in the EU, and says 25% synonym swaps cut detection to 17%
OpenAI plans to add an invisible watermark to ChatGPT and Codex text in the European Union over the coming weeks. However, its own evaluation found that synonym swaps reduce detection: replacing 10% of words in a 400-token passage cut detection from about 92% to 66%, and 25% swaps cut it to 17%.
AI summary · generated only from source feed metadata; consult originalSource published
Published here
views4
Original source
MIXED — XR
Media report · consult original reporting
Read the original ↗https://mixed-news.com/en/openai-eu-text-watermark-textgrain-synonym-swaps-17-percent/Original headline
OpenAI will watermark ChatGPT text in the EU, and says 25% synonym swaps cut detection to 17%
AI bilingual edit · consult originalHeadlines are indexed or machine translated, not independent verification of scientific results. Medical news is not clinical advice. Distinguish interstellar concepts from demonstrated space technology using the original source.