In an experiment that shouldn't surprise anybody with half a brain that sleeps with a giant robot-burning laser under their pillow, scientists have shown that robots have the ability to evolve and lie. And this is to one another -- imagine what they'd tell a human! Also, this quote is kind of long, but it's interesting and important to read if you want to understand the experiment. However, if you just want to type FIRST! in the comments and not learn anything, you should probably skip it (and then off a building). Did I say skip? I meant dive. Just kidding, I don't care.
In an experiment run at the Laboratory of Intelligent Systems in the Ecole Polytechnique FÃ©dÃ©rale of Lausanne, Switzerland*, robots that were designed to cooperate in searching out a beneficial resource and avoiding a poisonous one learned to lie to each other in an attempt to hoard the resource.
The experiment involved 1,000 robots divided into 10 different groups. Each robot had a sensor, a blue light, and its own 264-bit binary code "genome" that governed how it reacted to different stimuli. The first generation robots were programmed to turn the light on when they found the good resource, helping the other robots in the group find it.
The robots got higher marks for finding and sitting on the good resource, and negative points for hanging around the poisoned resource. The 200 highest-scoring genomes were then randomly "mated" and mutated to produce a new generation of programming. Within nine generations, the robots became excellent at finding the positive resource, and communicating with each other to direct other robots to the good resource.
However, there was a catch. A limited amount of access to the good resource meant that not every robot could benefit when it was found, and overcrowding could drive away the robot that originally found it.
After 500 generations, 60 percent of the robots had evolved to keep their light off when they found the good resource, hogging it all for themselves. Even more telling, a third of the robots evolved to actually look for the liars by developing an aversion to the light; the exact opposite of their original programming!
Notice how I bolded that last line? Reread it. Anybody else see something inherently wrong with that? Now, if you will recall the first law of robotics: A robot may not injure a human being or, through inaction, allow a human being to come to harm. See where I'm going with this? OUTERSPACE BITCHES, I'M NOT WAITING AROUND FOR THIS SHIT TO GO DOWN.
Thanks to Sarah, biggity2bit, greg, Phil, John, Pepper, Sven, Shawn, Rossco, Terrance, timpeva, ffffffffffffffffffffffffffff, SharaSue, Sn0zz, SeanJon, billcollider, Tyrogyro and yayinternets, who only lie about their age and marital status.