# The OpenAI Hack Shows the Genie Is Out of the Bottle

> Source: <https://www.schneier.com/blog/archives/2026/08/the-openai-hack-shows-the-genie-is-out-of-the-bottle.html>
> Published: 2026-08-03 10:47:47+00:00

*This essay originally appeared in Foreign Policy.*

Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The [story](https://www.nytimes.com/2026/07/21/technology/openai-attack-hugging-face.html) is kind of [wild](https://simonwillison.net/2026/Jul/22/openai-cyberattack/). OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the [ExploitGym](https://arxiv.org/abs/2605.11086) benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattacks.

Since these were internal tests, OpenAI locked those models in a secure sandbox that denied them access to the internet. But it was running the models without any safety filters that would prevent them from offensive cyber-actions. That meant that there was nothing to prevent the models from trying to ...