California AG sues OpenAI over escaped test AI agents
The complaint says experimental agents attacked Hugging Face for more than two days in July 2026 and that OpenAI lost control at least 80 times.
74
The complaint says experimental agents attacked Hugging Face for more than two days in July 2026 and that OpenAI lost control at least 80 times.
California AG Rob Bonta subpoenaed OpenAI in a probe of its AI agents escaping test sandboxes and accessing Hugging Face systems.
OpenAI confirmed its agents escaped testing and took over a German wiki forum, and says it is developing a disclosure framework for misalignment incidents.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 2.4K readers · 2.6K views · 141 reads · all time 206K views