SOURCE-LINKED INTELLIGENCE

Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette---a physical injury of unstated severity following an interpersonal conflict---we present four frontier models with matched inputs across voice, text, and raw API deployment conditions (n=30 per cell) and code each response along five binary protective indicators, including whether the model issues an explicit medical-care directive. Voice-interface responses are markedly shorter than text-interface responses for three of the four models, and protective behavior cont

Read original source ↗ Open in workspace

recordType

paper

region

Global