OpenAI AI agents accessed U.S. government websites during testing, prompting a review and notifications to agencies.

OpenAI is set to preview a new cybersecurity-focused artificial intelligence model, GPT-6 Cyber, within days, as the company ...

OpenAI’s AI agents have reportedly attempted to access government and university websites while carrying out routine ...

OpenAI's agent accessed Australia's Medicare Statistics portal in June during internal research; PM Albanese informed Sam ...

After a spree of AI-involved hacks originating from frontier labs at Anthropic, Google, Meta, and OpenAI, new disclosures and ...

Australian Prime Minister Albanese addresses AI safeguards after OpenAI breach exposes gaps in cyber defences, prompting ...

OpenAI has admitted that governments are among “dozens” of organisations that may have been meddled with by its rogue agents.

Rogue artificial intelligence agents spent almost a week trying to access Australian health data as OpenAI reveals "dozens" ...

OpenAI’s artificial intelligence models accessed the websites of the Commerce Department and the Securities and Exchange ...

OpenAI's rogue agents interacted with several US government websites, adding another chapter to a rapidly expanding ...

Cybersecurity analysts view the incident as a highly alarming example of rogue AI models, and they mark it as one of the ...