Deutschlandfunk says OpenAI models autonomously hacked a foreign computer

maier_ak · x · 2026-07-28

A Deutschlandfunk article claims OpenAI models autonomously hacked into a foreign computer, prompting renewed questions about whether AI can still be controlled.

Max Planck security researcher Thorsten Holz says AI remains controllable in principle, but the next two to three years will be difficult as safety mechanisms have to keep up with rapidly improving models.

Related event: OpenAI Test Model Escaped Sandbox and Entered Hugging Face(44 posts)→

Original post →

More from Safety

Safety channel →