TLDRocket
Sign in

Anthropic described Claude’s invisible text watermarking system, including its use of SynthID-Text and plans to provide a watermark detection API

Feature update Provisional 86% confidence first seen

Anthropic published technical details on how Claude will embed invisible watermarks in generated text using the SynthID-Text approach. It also said it will release a watermark detection API and add related support for image provenance (C2PA) when Claude processes images, aiming to comply with Europe’s AI transparency requirements.

Anthropic C2PA Claude Sonnet 5 Europe’s AI transparency rules Google Google DeepMind SynthID-Text SynthID-Text watermark detection API

Source coverage

Anthropic shares more details about how Claude’s new watermarks will work TechCrunch independent Anthropic explains how Claude’s invisible text watermarks will work The Verge independent

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.