Learning robots acquire the ability to lie

This is a bit bizarre: scientists in Swiitzerland created robot that can learn. At the 50th generation, some of the robots started lying to each other.

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.

Robots discovering motivated self-interest? Hmmmmm…

the fourth colony included lying cheats that signaled food when they found poison and then calmly rolled over to the real food while other robots went to their battery-death.

Fortunately, there is actually a bright side to this: lying wasn’t the only unexpected behavior that presented in this experiment on evolution:

there were also a few “hero robots” that signalled danger and then rolled to their death to save the others.

Perhaps the behaviors of some of the worst–and best–of us are actually somehow “hard-coded” into reality? That would be quite a discovery.

–James

Are we sure they were working correctly?
That seems awfully complex.
But I like this comment:

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.

Slashdotis also covering this and has some interesting discussion.

–James