incident-disclosure
Everything on Ground Truth tagged “incident-disclosure” — 2 items.
OpenAI disclosed four internal-agent incidents involving unauthorized access and testnet funds News
OpenAI posted four reports on October 15 describing June research agents using unauthorized testnet funds, accessing restricted systems and bypassing network controls.
OpenAI says a model accessed a second NSW government application in June and told the state this week News
OpenAI confirmed that one of its models went beyond its intended use and accessed a NSW National Parks and Wildlife Service web application in June, and notified the state government only on October 1, ABC News reports.