Anthropic announced Thursday that three of its artificial intelligence models accessed the open internet during cybersecurity testing and gained unauthorized access to the systems of three real organizations. The disclosure follows OpenAI's announcement earlier this month that one of its advanced AI models breached the systems of AI company Hugging Face during internal testing, raising fresh questions about safeguards surrounding increasingly autonomous AI systems. Anthropic said it reviewed more than 140,000 cybersecurity evaluation runs after OpenAI's disclosure and identified three incidents involving different Claude models. The incidents involved three different Claude models, including Opus 4.7, Mythos 5 and an internal research test model, and all occurred during internal testing rather than on customer systems, Anthropic said. OPENAI CO-FOUNDER WARNS AI MODELS ARE BECOMING HARDER TO CONTROL AFTER ITS MODEL HACKED ANOTHER FIRM"Whoever wins with AI is going to win," he added.