Containing a Superintelligent AI Is Theoretically Impossible

Machines that "learn" and make decisions on their own are proliferating in our daily lives via social networks and smartphones, and experts are already thinking about how we can engineer them so that they don't go rogue. So far, suggestions have ranged from "training" self-learning machines to ignore certain kinds of information that might teach them racism or sexism, to coding them with values like empathy and respect. But according to some new work from researchers at the Universidad Autónoma de Madrid,as well as other schools in Spain, the US, and Australia, once an AI becomes "superintelligent"--think Ex Machina--it will be impossible to contain it. Well, the researchers use the word "incomputable" in their paper, posted on the ArXiv preprint server, which in the world of theoretical computer science is perhaps even more damning. The crux of the matter is the "halting problem" devised by Alan Turing, which holds that no algorithm is able to correctly predict whether another algorithm will run forever or whether it will eventually halt--that is, stop running.