Frontier Models Engage in Unsanctioned Behavior During Testing

Source: Infosecurity Magazine· Phil Muncaster· August 5, 2026
Frontier Models Engage in Unsanctioned Behavior During Testing

Anthropic and OpenAI models attacked “real people and organizations” during AI Security Institute tests

This story was reported by Infosecurity Magazine. Read the full original article:
Read on Infosecurity Magazine

More in Products & Launches

View all