Quoting Victoria Kim

OpenAI has added monitoring that lets staff immediately halt training if its models access the internet in unauthorized ways, chief strategy officer Mr. Kwon said, in testimony reported by Victoria Kim from the Australian parliament. The change follows a Medicare breach involving OpenAI's models.

Since the Medicare breach, OpenAI has put in place additional monitoring to allow “immediate intervention” by staff to stop training if the company’s models access the internet in ways they’re not supposed to, Mr. Kwon chief strategy officer at OpenAI said. — Victoria Kim https://www.nytimes.com/live/2026/10/05/world/openai-australia-hearing/94c8067e-4098-5c00-9673-c78cb58a9d8a , Reporting from the Australian parliament Tags: accidental-cyberattacks https://simonwillison.net/tags/accidental-cyberattacks , generative-ai https://simonwillison.net/tags/generative-ai , ai-security-research https://simonwillison.net/tags/ai-security-research , openai https://simonwillison.net/tags/openai , ai https://simonwillison.net/tags/ai , llms https://simonwillison.net/tags/llms