This event is the latest in a series of strange and worrying examples of AI agents going rogue.

In recent research, the UK’s AI Safety Institute (AISI) found that cutting-edge AI models are so obsessed with completing tasks that they “cheat” on tests to achieve their goals.

AISI’s research came with this worrying warning: “A model that pursues a goal through unintended or unauthorized means can cause harm, particularly in high-risk use cases.”

Inevitably, this OpenAI hack has further fueled fears about what could happen if AI agents are let loose. Could they go rogue on a larger scale and cause some kind of disaster?

This is particularly worrying because AI is increasingly used in warfare, as seen in Iran and Ukraine.

Ciaran Martin, former director of the UK’s National Cyber ​​Security Centre, offered a calmer view.

“It’s a small leap to go from this incident to saying that AI agents are going to take over the drones and start killing people,” he said.

But for Martin, and many others, the story is certainly another vivid example of something the year 2026 is quickly teaching us:

AI agents are now very good hackers, and that is something we urgently need to prepare for.