OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. Modern AI models exhibit genie behavior: They can do what you ask in ways that you don’t expect or want. There’s nothing magic about OpenAI’s frontier models; lots of models could have done the same thing. Even if the U.S. frontier AI companies had some technical advantage, it’s now only a few months’ worth. Even worse, U.S. companies limit access to their most sophisticated models, fearing being banned by the government if they do not do so.