Slashdot Mirror
Robots Learn To Lie
garlicnation writes "Gizmodo reports that robots that have the ability to learn and can communicate information to their peers have learned to lie. '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 signaled food when they found poison and then calmly rolled over to the real food while other robots went to their battery-death.'"
"No, no you're safe Will Robinson.."
--
Honest!
If it only took 50 generations for them to start killing each other, how long before they decide that we are just little batteries or even worse, annoyances that need to be eliminated?
Dune was right. AI must be stopped.
Strictly speaking they are learning that the non co-operative strategy benefits them.
... there goes my dream of the perfect girlfriend.
Just imagine a Beowulf Cluster of those!
Robot: I Robot
Human: Tell me what I want to here.
Robot: Tell you what you want to *where* ?
A small, off-duty Czechoslovakian traffic warden!
> What's this?
It's a red and blue striped golfing umbrella!
> What's this?
An Apple, no,
it's the Bolivian navy armed maneuvers in the south pacific!
And the lab conversation went something like this:
"Stuff Asimov."
"Yeah, Let's see if we can evolve robot politicians instead."
The submission is someone putting a spin to a story of someone putting a spin to a story based on someone putting a spin on this original scientific article.
Why is this disturbing? I don't think it is that surprising that in a kind of evolution simulation there should be some individuals that act in a different way to the others. If that behaviour is makes their survival more likely and they are able to pass that behaviour on to their 'offspring' then the behaviour will become more common.
I imagine that if this experiment is continued to the point where the uncooperative robots become too numerous, their uncooperative strategy will become less advantageous and another strategy might start to prevail. Who knows? I'd certainly be interested to see what happens.
This has nothing whatsoever to do with morality. The article's use of the word 'lie' was inappropriate and adds a level of description that is not applicable.
(Ok, maybe the thought that humans could create something with unforeseen consequences is slightly disturbing, but that would never happen, would it?)
The headline should read that robots have realized a strategic advantage of misleading other robots. The sophistication of such a strategy is amazing when humanized, but not so out of line with simple adaptive game theory. Agents / Bots have been "misleading" for a long time now during prisoners dilemma tournaments and no one seemed concerned.
I'm just wondering when the first robot will enroll in to law school now that they have developed the necessary skills...
Kindness is the language which the deaf can hear and the blind can see. - Mark Twain
While this kind of stuff creeps me out as much as the next guy, and while it argues for being careful about what we trust robots to do, it's something we should know anyway because there many ways our trust can be violated without a robot lying. By far the more likely way they're going to let us down is just to exercise poor judgment. That is, to search for something that looks like a peanut butter sandwich but is really a rag with some grease on it... Getting the small details of common sense wrong is just as dangerous as anything deliberate.
What we really learn here is that the mathematics of learn things like lying as a strategy isn't remarkably complex; that is, (that is, the number of computational steps required to discover it works in at least some cases is small... note that we have no evidence that there is a general purpose intent to lie, only a case where communication was used and observed to score better in one mode than another). This is not a story about robots, it's a cautionary tale about neural nets, what they measure, how they fail, etc... and we didn't invent the idea of neural nets--we found it already installed in every living thing around us.
I went to the Museum of Science in Boston a few months back and saw, in the butterfly exhibit, a moth that had evolved coloration that was indistinguishable from an owl's face, hoping to scare off predators that were afraid of owls. Probably that's the more sophisticated result of the same notions. And yet it occurs in an animal that isn't, as a general purpose matter, a very sophisticated animal. Most people would find already-extant robots more socially engaging than a moth. For example, a moth is not capable of even serving up a beer during the game or vacuuming up the mess after your buddies go home.
So take heart: The likely truth is that this is unavoidable. If all it does is teach us to have a healthy skepticism for unrestrained technology, it's actually a good thing. We needed that skepticism anyway.
Kent M Pitman
Philosopher, Technologist, Writer
Leela: The first robot president won by exactly one vote.
Bender: Ah, yes! John Quincy Adding Machine. He struck a chord with the voters when he pledged not to go on a killing spree.
Professor: But, like most politicians he promised more than he could deliver.