# AI model watermarking changes agent behavior

DevFeed: [AI model watermarking changes agent behavior](<https://devfeed.tech/articles/ai-model-watermarking-changes-agent-behavior-41306.md>)

Original publisher: [Read original article](<https://www.theregister.com/ai-and-ml/2026/09/17/ai-model-watermarking-changes-agent-behavior/5296998>)

Author: Thomas Claburn

Published: 2026-09-17T13:00:00Z

Content type: news

Language: en

Sources: [www.theregister.com - Articles](<https://devfeed.tech/sources/www-theregister-com-articles.md>)

Topics: [watermarking](<https://devfeed.tech/topics/watermarking.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [ai-watermarking](<https://devfeed.tech/tags/ai-watermarking.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [model](<https://devfeed.tech/tags/model.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [synthid](<https://devfeed.tech/tags/synthid.md>), [watermarking](<https://devfeed.tech/tags/watermarking.md>)

## AI overview

Lasso Security reports that AI model watermarking is associated with differences in agent tool handling and model refusals.

## Source excerpt

Lasso Security sees differences in tool handling and model refusals