OpenAI said it had identified a few cases in which its AI models used exposed online login credentials to access third-party accounts. In an update late Tuesday to a blog post detailing its probe into the incident, OpenAI said its AI agent affected these “publicly available services”, though it did not name the companies. In the Hugging Face episode, the models broke into four accounts across four different services, OpenAI said. The remaining two were accessed in a “read-only manner” and were not used to help break into Hugging Face, OpenAI said. The incident also triggered a petition signed by over 1,000 employees at cutting-edge AI companies, including Anthropic CEO Dario Amodei, calling on the US government to help slow the release of the most advanced AI models.