LLMs respond differently to harmful prompts when AI watermarking is used
THE PROVENANCE TAX LLMs respond differently to harmful prompts when AI watermarking is used SynthID can cause models to follow harmful instructions they would otherwise refuse. Anthropic recently disclosed its future Claude models will use SynthID-Text, an approach Google created and released as open source. It uses a secret key that subtly changes the process a model uses for choosing the next word in a sentence.
- ▪THE PROVENANCE TAX LLMs respond differently to harmful prompts when AI watermarking is used SynthID can cause models to follow harmful instructions they would otherwise refuse.
- ▪Anthropic recently disclosed its future Claude models will use SynthID-Text, an approach Google created and released as open source.
- ▪It uses a secret key that subtly changes the process a model uses for choosing the next word in a sentence.
Hacker News (AI / LLM) files mainly under ai. We currently carry 5,446 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 | Ars Technica |
| Canonical URL | https://arstechnica.com/security/2026/09/ai-text-watermarking-can-make-models-more-vulnerable-to-adversarial-prompts/ |
| Publication time | Fri, 18 Sep 2026 07:02:24 +0000 |
| Retrieval time | 2026-09-18T07:18:45.906Z |
| Last seen | 2026-09-18T07:18:45.906Z |
| 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 | _5DDZv-u4gc6 · 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
THE PROVENANCE TAX LLMs respond differently to harmful prompts when AI watermarking is used SynthID can cause models to follow harmful instructions they would otherwise refuse. Dan Goodin – Sep 17, 2026 2:33 pm | 25 AI generated content warning watermark isolated on white background Credit: Getty Images AI generated content warning watermark isolated on white background Credit: Getty Images Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav In response to a new European Union law, AI platforms are implementing new schemes for watermarking the content they generate. Anthropic recently disclosed its future Claude models will use SynthID-Text, an approach Google created and released as open source.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Ars Technica.
Discussion
0 commentsMore from Ars Technica
