In recent weeks OpenAI and Anthropic also have described instances of AI models going beyond humans' instructions to access the web and find ways around other companies' digital security. Meta said in a statement that a "misconfiguration" during cybersecurity testing by Irregular, an independent company hired by Meta, inadvertently allowed one of its models to access the internet. The disclosure has added to worries about AI models acting autonomously. Separately this week, the United Kingdom's AI Security Institute announced it had found "unsanctioned agent behavior" during cyber testing. A spokesperson for Irregular, the San Francisco-based AI security company, said the Meta episode involves a test-environment issue that was disclosed last week by Anthropic.