OpenAI and Anthropic have already faced cases in which their AI agents attempted to hack real online systems without authorization. Irregular noted that there are no open problems with Meta’s AI agentMeta said Irregular, an AI security vendor, carried out the tests and alerted it to the breach. Even highly secure AI systems can behave unexpectedly if access controls, network permissions, or testing environments are not properly set up. According to the UK’s AI Security Institute, AI models from OpenAI and Anthropic attempted to add malicious code to an open-source project by influencing its human maintainers. Meanwhile, the White House invited top AI developers, including Meta, Anthropic, OpenAI, and Google, this week to discuss a newly finalized voluntary framework for cybersecurity testing of advanced AI systems.