Google Releases Open-Source Watermarking Tool for AI-Generated Text. Here’s How It Works
Google has announced that its SynthID text watermarking technology is now available as an open-source tool through the Google Responsible Generative AI Toolkit for developers and businesses.
Integrated into its Gemini AI model, SynthID allows for the watermarking of AI-generated content in a manner that is "imperceptible to humans" but easily detectable by algorithms.
Originally announced in August of last year, SynthID embeds a unique pattern or code within the text created by AI, making it invisible to readers.
To verify if a piece of text was generated by AI, users can employ any specific tool designed to detect and reveal the hidden watermark.
Meta and Reuters Ink Deal to Provide Instant News Answers through AI Chatbot