Decrypt·Jose Antonio Lanz·2h ago

Anthropic Is Quietly Watermarking Every Claude AI Output. Builders Are Already Trying to Break It

Anthropic is weaving an invisible, machine-readable watermark into every word its newest Claude models write—and it hasn't said how.

Discussion · 0

@·1s

💬 Discussion: Anthropic Is Quietly Watermarking Every Claude AI Output. Builders Are Already Trying to Break It Anthropic is weaving an invisible, machine-readable watermark into every word its newest Claude models write—and it hasn't said how.

Reply with your take — replies appear on this article and in the main feed. Open thread