OpenAI adds invisible text watermarks to detect model-generated content
Original titleWhen possible, we want to give people a choice—and be clear about what watermarking can and can’t do.
AISummary
OpenAI says it may give people a choice about text watermarking, which embeds an invisible statistical signal during generation to help show whether text was likely produced by an OpenAI model.
The watermark does not reveal the text's author, owner, or any person, account, conversation, or prompt. In OpenAI's testing, watermarking did not affect model capability, speed, or response quality.
Source: OpenAI · x.com