AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

LLMs respond differently to harmful prompts when AI watermarking is used

Ars Technica · article · Sep 17, 2026 · UTC

SynthID can cause models to follow harmful instructions they would otherwise refuse.

Read original source ↗ Open in workspace

recordType
article
region
Global

Evidence & attribution

First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.