again, nothing new and/or interesting

what matters here is amount of electricity and compute spent, how exactly they define agents and their reward systems etc etc

give someone the same money as not-so-open not-so-ai and you wouldn't need crazy ipo pump stories, a team of people could write a stuxnet with a couple zero-days baked in too

its impressive of course that currently the transformer architecture reached such a point, but i am 100% sure this is not "oh its the deep philosopical machine breakaway moment" - in any case, humans already invented persistent unaccountability machines: those are LLCs and corporations.

The bottom line is: given time and resource any system would be attacked in such a way by a sufficientlt complicated entity. Transformers and RL can better convert resources into time-savings, while having drawbacks elsewhere.