Safety · Ars Technica ·

Google's SynthID watermark is hard to break, but it doesn't solve AI misinformation

Google's SynthID watermark is hard to break, but it doesn't solve AI misinformation

Google’s SynthID watermark is designed to remain detectable even after common edits to AI-generated content. However, watermarking alone cannot determine whether online information is true or prevent AI-generated misinformation.

Read the full story at Ars Technica →