indeed he will, unless we learn how to manipulate him. This is why I'm confused as to why rationalists seem to have done basically no research into complexity theory (systems/cybernetics). Scott Alexander's done the Moloch pieces, and this one article on dynamical systems [1] but aside from that the closest they get is machine learning, which is a descendant.
[1] https://astralcodexten.substack.com/p/ontology-of-psychiatri...