Intelligent robots can't be trusted
I recently blogged about the danger of intelligent robots. Today’s news brings another reason for concern. Intelligent robots have evolved the ability to deceive:
We use a system of experimental evolution with robots foraging in an arena containing a food source to study how communication strategies can evolve to regulate information provided by such cues. Robots could produce information by emitting blue light, which other robots could perceive with their cameras. Over the first few generations, robots quickly evolved to successfully locate the food, while emitting light randomly. This resulted in a high intensity of light near food, which provided social information allowing other robots to more rapidly find the food. Because robots were competing for food, they were quickly selected to conceal this information.
In other words, the robots quickly learned to deceive other robots for their personal benefit.
Posted by James on Friday, August 21, 2009