AI model watermarking changes agent behavior
The altered behavior isn't necessarily worse but can be, particularly under adversarial prompt injection.With the implementation of the EU AI Act, providers of AI models must mark the output of their software with machine-readable code. Google DeepMind's SynthID-Text is one method for doing so, and has been adopted by Anthropic and by OpenAI. REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/b'); }); The benefit of this sort of digital labeling is that manipulative or deceptive AI-generated content can be more easily detected, even if it does have the potential to stigmatize the usage of AI.
- ▪The altered behavior isn't necessarily worse but can be, particularly under adversarial prompt injection.With the implementation of the EU AI Act, providers of AI models must mark the output of their software with machine-readable code.
- ▪Google DeepMind's SynthID-Text is one method for doing so, and has been adopted by Anthropic and by OpenAI.
- ▪REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/b'); }); The benefit of this sort of digital labeling is that manipulative or deceptive AI-generated content can be more easily detected, even if it d
The Register publishes from United Kingdom and files mainly under tech. We currently carry 598 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | The Register |
| Canonical URL | https://www.theregister.com/ai-and-ml/2026/09/17/ai-model-watermarking-changes-agent-behavior/5296998 |
| Publication time | Thu, 17 Sep 2026 15:00:00 +0200 |
| Retrieval time | 2026-09-17T13:03:45.004Z |
| Last seen | 2026-09-17T13:03:45.004Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 48DKCsHwKrz_ · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
(function() { let windowUrl = window.location.href; windowUrl = windowUrl.substring(windowUrl.indexOf('?') + 1); let messageElement = document.querySelector('.shareableMessage'); if (windowUrl && windowUrl.includes('code') && windowUrl.includes('expires')) { messageElement.style.display = 'block'; } })(); ai and ml AI model watermarking changes agent behavior Lasso Security sees differences in tool handling and model refusals Thomas Claburn Thomas Claburn AI AND SOFTWARE REPORTER Published thu 17 Sep 2026 // 14:00 UTC READ MORE Microsoft AI chief warns Anthropic not to put ideas in Claude's head 45 minutes ago Nvidia goes green to keep grid capacity from zapping its revenues 15 hours ago Spain gets its first taste of AI-aided cyber attack 1 day ago AI networking startups race to replace…
Excerpt limited to ~120 words for fair-use compliance. The full article is at The Register.
Discussion
0 commentsMore from The Register
