Holy crap! The Age of The Machines is nigh: a bunch of scientists in Switzerland have created learning robots that can lie to each other. Okay, so they don't swill beer or put bends in girders—they just communicate to each other with benign flashing lights, thank goodness, instead of using lasers to destroy humans:
The team at the Laboratory of Intelligent Systems at the Federal Institute of Technology created the little experimental learning devices to work in groups and hunt for "food" targets nearby while avoiding "poison." Imagine their surprise when one generation of robots learned to signal lies about the poison, sending opponents to their doom.
The little wheeled robots had neural circuitry with about 30 "genes" that determine their behaviour, and how much they react to light in the environment. The food sources charged up the robots' batteries while the poison drained them, and by using the genes of the most successful feeders in 50 successive generations, the team was hoping to select the fittest.
Three colonies of bots in the 50th generation learned to signal to other robots in the group when then found food or poison. But the fourth colony included lying cheats that signalled food when they found poison and then calmly rolled over to the real food while other robots went to their battery-death. Eerily wicked, to say the least. Saving the robots' honour, luckily, there were also a few "hero robots" that signalled danger and then rolled to their death to save the others.
Will technology like this make its way into consumer robots sometime? We kind of hope not: not sure I'd like to argue with a Roomba about whether it had or hadn't swept up that mess behind the sofa.