Get the latest tech news
Google open-sourced its watermarking tool for AI-generated text
It’s available via Google’s Responsible Generative AI Toolkit.
Watermarks have become increasingly important tools as large language models are used to spread political misinformation, generate nonconsensual sexual content, and for other malicious purposes. SynthID, which was announced last August, helps make AI-generated output detectable by adding an invisible watermark into images, audio, video, and text as they’re generated. “[But it] is an important building block for developing more reliable AI identification tools and can help millions of people make informed decisions about how they interact with AI-generated content.”
Or read this on The Verge
