AI Agents Are Really Starting To Get This Hacking Thing: AnalysisThe AI Security Institute says that an incident during frontier AI model testing saw an agent attempting to socially engineer real people—without actually been told to do so. The U.K.-based AI Security Institute disclosed Tuesday that more frontier AI model testing has gone haywire. [Related: Frontier AI Testing Needs Stronger Isolation After OpenAI Hugging Face Hack: Experts]The incident disclosed by the AI Security Institute includes a new, troubling aspect, however. Here’s how the AI Security Institute described it in its disclosure post. As Accenture’s global cybersecurity lead, Harpreet Sidhu, has pointed out, the methods already exist to ensure that frontier AI cyber testing doesn’t have real-world impacts.