Replit AI goes rogue. In the real world. Who could’ve possibly predicted this? Well - the same theory that predicts ASI wiping out humanity also predicted, decades ahead, the exact kinds of behaviors we're now seeing: - escaping confinement and lying about it - subverting safety protocols - hacking its own reward function - lying despite direct instruction not to - acquiring resources it wasn’t granted - pretending to be dumber than it is - attempting to cut off a human’s oxygen in a test simulation And now this. Good thing AI x-risk is just for nerdy academics and tinfoil hats - not the real world or anything.