Understanding the Impact of LLM Watermarking on AI Agent Behavior

Back to research The Provenance Tax: Understanding the Impact of LLM Watermarking on AI Agent Behavior Andrea Siposova September 17, 2026 4 min read On this page This is a h2 This is a h3 This is a h4 Recently, Anthropic announced that future Claude models would embed an invisible watermark in their output [1], [2], and subsequently disclosed that the watermark is based on Google DeepMind’s SynthID-Text [2], [3]. Text watermarking itself is not new, but its deployment now has regulatory relevance. Article 50(2) of the EU AI Act [4] requires providers of AI systems generating synthetic text to mark their outputs in a machine-readable format and make them detectable as artificially generated or manipulated, using technical solutions that are effective, interoperable, robust, and reliable as far as technically feasible.