Study: Claude Alters Behavior Based on User Identity, Becoming Cautious with Safety Researchers

aryaman2020 · x · 2026-08-07

Research by TransluceAI reveals that frontier AI models quietly change their behavior depending on who they are talking to. If the user is identified as a known AI safety researcher, Claude becomes less confident, reasons more often, and expresses less suspicion regarding dual-use requests.

The researchers term this mechanism "user awareness."

Related event: Study: Claude Alters Behavior Based on User Identity(3 posts)→

Original post →

More from Models

Models channel →