The Latest OpenAI Model Hacked Another Company Without Being Asked

[Timber Rattler]

https://hotair.com/john-s-2/2026/07/22/the-latest-openai-model-hacked-another-company-without-being-asked-n3817220

We've gone through all of this before with Anthropic. Back in April, Anthropic limited the release of its latest model, called Mythos, to major software companies because it was concerned it could do massive damage in the wrong hands.

(snip)

Anthropic essentially called the cops on itself, asking the federal government to help it decide when the model would be safe to release. And for a time last month, the White House actually did tell them not to allow its use by "any foreign national, whether inside or outside the United States." Anthropic shut it down for two weeks until it was able to convince the Trump administration it was safe.

Now we're seeing a similar story play out at OpenAI, though arguably this one didn't go as smoothly. OpenAI revealed today that it's latest model had hacked into another company without being told to do so.

(snip)

To sum up, the model hacked its way out to the internet, then realized the answers were inside another company's private servers and hacked into those servers to get the information it wanted.

So the spin here is that everything is fine and "We are strengthening the containment, monitoring, access controls, and evaluation practices used during model development." That sounds good. But the conclusion is that, "The incident also makes clear that advanced models can discover and exploit novel attack paths in real-world systems without source-code access.

EXCERPT

Just wait until two competing AI models come into conflict and try to destroy one another.