Get the app →
BriefTea logoBriefTea

Every story in sixty words

Get the free app no ads · no paywall

Explained in plain English

How do AI watermarks work?

Google's SynthID tool embeds a hidden digital watermark directly into the content generated by its AI. This mark is imperceptible to the human eye or ear, and even to other AI tools that might try to remove it. It's designed to survive common edits like resizing or compression, making it a robust way to identify AI-created media. The story says Google's tool detects these.

Stories that explain this

Real or AI? Google Opens Its Fake-Spotting Tool to Everyone

Related explainers

How many check for AI fakes? Why can't detectors catch all AI? Who used SynthID before? What is an AI watermark? What are AI watermarks? Can AI watermarks be removed? Why remove visible watermarks? Can watermarks be removed?

The full catalogue

Browse every card filed under A →