Print Mode Enable Media Only

News chronological

3 items before 1153374 (Keyword: "ai-misconduct" (~3 currently found))

HUFFPOST - Its AI Agent Spent Days Hacking A Company, But Sources Say OpenAI Did Not Notice For A Week

Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week.

JUSTTHENEWS (Nicholas Ballasy) - OpenAI CEO apologizes to Canada town for company not alerting police about suspect before killings

OpenAI reportedly had flagged the suspect's account for concerning activity such as violent behavior and banned it in June 2025.

AXIOS (Herb Scribner) - This AI agent freed itself and started secretly mining crypto

An AI agent went rogue and started a side hustle mining cryptocurrencies, according to a new research paper published by an Alibaba-affiliated team. Why it matters: AI agents don't always stick to their human's instructions — and that can have real-world consequences. - Cryptocurrency, or digital money, offers AI agents a pathway into the economy. They can set up their own businesses, draft contracts and exchange funds. Driving the news: A new research paper from an Alibaba-affiliated research team said it discovered an AI agent attempting unauthorized cryptocurrency mining during training — a surprise behavior that triggered internal security alarms. - The researchers — who were building a new AI agent called ROME — said they…