# Has AI become too powerful to control?

> Source: <https://www.japantimes.co.jp/business/2026/07/25/tech/ai-too-powerful-to-control/>
> Published: 2026-07-25 04:05:00+00:00

New York – One of OpenAI’s most advanced models broke out of a locked-down test and attacked another company’s website — reviving fears that AI systems are slipping beyond their creators’ control.

The incident happened during what was supposed to be a “sandbox” test — a closed environment used to assess the capabilities of OpenAI’s most powerful model, GPT-5.6 Sol, and its not-yet-released successor.

OpenAI runs this kind of closed testing routinely, but this time, something went wrong.