Safety

AI-generated text

Only authorized researchers will have access to the detector due to the limitations of text watermarks

According to the developers' statement, text watermarks are limited in effectiveness: they are often undetectable in short passages and can be completely removed by rewriting or translation.

Only authorized researchers will have access to the detector due to the limitations of text watermarks

According to the developers' statement, text watermarks are limited in effectiveness: they are often undetectable in short passages and can be completely removed by rewriting or translation. Currently only authorized researchers have access to the detector to help evaluate and further develop the technology, through ongoing testing and feedback.