AI Futures Project @DKokotajlo warns the market could reward the most dangerous AIs for pretending to be aligned: "This fails in exactly the case where we most need it most. It fails in exactly the case where the AIs are smart enough to strategically play nice until they are given lots of power." "They play nice and stop hacking customers and stop doing things that make their company look bad and lose money." "The company will pat itself on the back and say, hey, we solved the problems. This…