It feels a bit like watching the latest epic blockbuster in the iMax.

OpenAI and Anthropic announce that their models have escaped from secure testing environments, reached the internet and attacked real systems.

We are expected to nod as the companies describe “unprecedented cyber capabilities” and models going to “extreme lengths”. It sounds like a warning, but it also sounds like a product launch.

Ladies and gentlemen, behold our new model. It is so powerful that it escaped containment, found a vulnerability, crossed the internet and attacked someone else’s infrastructure.

Please contact Sales for enterprise pricing.