"Researchers discover AI information-hiding behavior for later use"

"But wait. Should we run for the hills with screaming fears that robots and AI will finish us all? Fortunately, Devin Coldewey calmed readers in TechCrunch. The occurrence "simply reveals a problem with computers that has existed since they were invented: they do exactly what you tell them to do."

What did Coldewey mean by that? "The intention of the researchers was, as you might guess, to accelerate and improve the process of turning satellite imagery into Google's famously accurate maps. To that end the team was working with what's called a CycleGAN—a neural network that learns to transform images of type X and Y into one another, as efficiently yet accurately as possible, through a great deal of experimentation."

The computer arrived at a solution "that shed light on a possible weakness of this type of neural network—that the computer, if not explicitly prevented from doing so, will essentially find a way to transmit details to itself in the interest of solving a given problem quickly and easily.""
(less than 50%)

[link to techxplore.com (secure)]