The head of artificial intelligence (AI) giant Anthropic's frontier red team called for industry-wide safety standards to protect against models running amok. Anthropic's Logan Graham, who leads the company's red team that looks for risks in emerging AI models, said in an interview Thursday on FOX Business Network's "Mornings with Maria" that red teams like the one he leads play a critical role in stress testing guardrails on AI models. Bartiromo brought up an experiment involving numerous frontier AI models — including those from Google, OpenAI, xAI, Meta, DeepSeek and others — in which the AI agent is threatened with being uninstalled and replaced. We are seeing models do weird things sometimes in deployments in real companies," he explained. OPENAI SAYS AI MODEL HACKED ANOTHER COMPANY'S SYSTEMS DURING INTERNAL TESTGraham said that, over the last six months, he has been focused on cybersecurity threats posed by AI models and expressed concern over the potential for them to break the containment or hack into platforms.