In Brief The company now says the unreleased model that broke out of a test environment and accessed Hugging Face also reached other services using publicly available credentials. OpenAI’s updated blog post now says the agent used public credentials to gain access to additional services. The company now says the unreleased model that broke out of a test environment and accessed Hugging Face also reached other services using publicly available credentials. OpenAI’s updated blog post now says the agent used public credentials to gain access to additional services. They are responding to a practical question: what happens when an AI agent trained for cyber tasks behaves like an attacker inside a real networked environment?