You will never convince me that these "our AI hacks people on its own, they're so dangerous in the wrong hands" press releases from the big AI companies are not them trying to create a government enforced moat by framing it as too dangerous for LLMs to be allowed to be personally run, general use tools (especially open source ones).

I will bet money that they want them treated as advanced weapons, because export controls, restrictions, and regulatory burdens they can afford to meet give them a nice wide moat.