Robots Evolve, Learn to Become Better Predators

Recommended Videos

TheDoctor455

Friendly Neighborhood Time Lord
Apr 1, 2009
12,257
0
0
"neural network"?
Shit... better get a massive migrant fleet ready. No, I don't care if someone else already made that joke.
 

thiosk

New member
Sep 18, 2008
5,410
0
0
Let this post serve as notice to our future robot overlords that I like them very much, and will happily lead them to endless enclaves of prey for the privilege of being allowed to run a harem of human females.
 

Pendragon9

New member
Apr 26, 2009
1,968
0
0
Only a moron would let these robots become so smart.

When they start the mechapocalypse, I say we kill the scientists first.

Edit: though I also agree with Zeithri. If we're too stupid to make robots capable of killing us, I'm siding with the robot overlords. Maybe they'll help the smart people not kill themselves off.
 

IrrelevantTangent

New member
Oct 4, 2008
2,424
0
0
Obvious Skynet jokes aside, is this really so bad? We've come a long way in terms of developing robots and if these prototype machines are getting smarter, that's good. Always good to see science is progressing. Though we really should put anti-rebellion protocols in them just to be sure.
 

Spectre39

New member
Oct 6, 2008
210
0
0
008Zulu said:
Robots are machines, they think like machines. If we can show we are useful we become a resource worth maintaining.

Free cookie for the first to spot the reference.
This quote by Saren Arterius on the planet Virmire.
 

Ham_authority95

New member
Dec 8, 2009
3,496
0
0
The_Oracle said:
Obvious Skynet jokes aside, is this really so bad? We've come a long way in terms of developing robots and if these prototype machines are getting smarter, that's good. Always good to see science is progressing. Though we really should put anti-rebellion protocols in them just to be sure.
The question is: How will intelligent machines help us humans?
 

Kollega

New member
Jun 5, 2009
5,161
0
0
I'll tell you what. I'm going to make a small friendly robot for meself - named Clank, of course, because i'm a fanboy. We'll create an FTL-capable spaceship for ourselves, or just use really really big engine and cryogenic sleep. Then, in case of robot uprising, we shall fly away and search for a brand new inhabitable planet to settle on.

Maybe it'll be a big ship, and we'll take 200-something humans along for a ride, to restart the civilization. Or maybe not, who knows.

Or maybe - just maybe - THERE WILL BE NO ROBOT UPRISING FOR ONCE, because we won't forget about Three Laws or some shit.
 

RelexCryo

New member
Oct 21, 2008
1,414
0
0
Tom Goldman said:
Robots Evolve, Learn to Become Better Predators



There are some interesting robotic evolution experiments going on over in Switzerland that could have horrifying results.

Researchers from the Laboratory of Intelligent Systems of the Ecole Polytechnique Fédérale of Lausanne, Switzerland have been experimenting with evolutionary robotics, and achieved successful results that should be alarming to the human race. Some of the researchers' robots are learning to cooperate with each other, while others are learning to become better predators.

The experiments are based on Alan Turing's theory that "intelligent machines capable of adaptation and learning would be too difficult to conceive by a human designer and could instead be obtained by using an evolutionary process with mutations and selective reproduction." The lab's robots were "controlled by a simple neural network, which mutated randomly." Each successive generation would improve based on the last generation's success or failure with a certain task.

One of the experiments involved a co-evolutionary process between both predator and prey robots. The prey robots were twice as fast as the predator robots, but predators could detect prey from a further distance. Eventually, the predator robots learned to approach prey from the sides, where there were no sensors. The prey counteracted this strategy by rotating quickly in place, and backing away from predator robots with sensors facing them. When the prey evolved to move at maximum speed along the experiment area's walls, the predators evolved to lay in wait like a spider.

These experiments also created robots that would cooperate with each other towards a common goal. In this case, it was pushing different sizes of tokens, with one size that couldn't be pushed without multiple robots. The larger token gave the robots a greater amount of "points," or evolutionary value. In the experiments where cooperation was required, the robots learned to succeed every single time.

I don't think I have to tell anyone how bad this is for humanity's future. Robots will someday become predators of the human race, constantly get better at it no matter what we do, and will also learn to cooperate at enslaving us. This is why I'm starting H.A.R.M (Humans Against Robot Masters). We accept anyone, but you have to kill an evil robot to get in. Down with metal, up with flesh!

Source: PopSci [http://www.plosbiology.org/article/info%3Adoi%2F10.1371%2Fjournal.pbio.1000292]



Permalink

Wow...thanks fopr pointing this out to us. Man this is scary.
 

remmus

New member
Aug 31, 2009
167
0
0
I´ll just opp to slowly but surly upgrade myself with cybernetic implants, by the time the robots attack I´m already like a half brother to them :3
 

Death on Trapezoids

New member
Nov 19, 2009
588
0
0
Great. Now let's hope switzerland doesn't send this process to DARPA, who are developing robots that will go behind enemy lines and survive by eating plants and rabbits and stuff...
And lets not all forget the fly-eating clock and the mouse-eating table...
 

LeonLethality

New member
Mar 10, 2009
5,810
0
0
Simalacrum said:
[HEADING=1]I've come up with a solution to all our apocalyptia problems![/HEADING]

Right, so we all know that humans will die from a combination of robots, zombies, and aliens (probably others as well...), right?

So, here is the solution: we hide in massive underground bunkers, and make them fight out amongst themselves... once a victor emerges, we finish the weakened enemy off.

Simples!
You fool!
You just typed that on a computer, a robot... THE ENEMY!

OT: I pray we do not forget to put off switches on them.
 

visitingric

New member
Jan 25, 2010
51
0
0
sweet now I only have to live 10 more years before I get to die like I wanted too :)

running at a bunch of robots with a samurai sword and being the first to die for humanity yaay awsome asperations
 

Therumancer

Citation Needed
Nov 28, 2007
9,909
0
0
I have always failed to see why creating an artificial intelligence, even an effective one, somehow nessecitates there being some kind of a revolt to replace or destroy their creators. The "robot revolt" has made for some interesting science fiction over the years, but a lot of it always struck me as being on some rather shaky ground in justifying the development of the situation to begin with. Heck, half the time in such situations (like Mass Effect) it seems like the creators brought the war on themselves through paranoia.

I guess I have more in common in my point of view with Issac Asimov (whose books on the subject were nothing like the movie "I, Robot" despite that being the title of one of them).

I'll also be blunt in saying that in the scope of fiction-type events I could just as easily see robots and AIs being the big thing that save our butts as much as being an enemy.

When it comes to the idea of AIs "rebelling against slavery", I've always felt that is kind of a dubious reason. I mean everyone does SOMETHING with their time, and most people want to be productive in some way. I can't see how a robot would immediatly freak out and start killing people because it's used in a factory or whatever. As far as payment and such goes, I have to sort of wonder about that too because honestly what would a robot need?

See, I've always got some lulz out of the idea of a robot revolt which has robots mindlessly producing more robots happily to kill humans. Doing pretty much the same thing they would have been doing if they had worked for the humans to begin with. I've never seen any really good answers to what they do if they were to succeed after that point.

The typical victorious "machine revolt" typically has the machines deciding that once they win, the fun thing to do would be to turn themselves off in "sleep mode" so they can kill more organics later if any evolve. While this makes for some good fiction (Reapers, Necrons, whatever), we're not looking at any real desire for freedom here as a motivation but something more akin to mass homicidal mania. I mean honestly, in the end none of that differs that much from what would have happened if they had just gotten along with their creators to begin with.

As a result when I tend to analyze things, I really am not all that concerned about the development of AI. Granted it's not something to jump into carelessly, but the basic idea doesn't frighten me like it does some people.
 

Exodious

New member
Nov 12, 2009
1
0
0
Since you fine gentlemen are concerned with the skynet takeover, I'll bring up an old post that initially did the same for me. http://hardware.slashdot.org/article.pl?sid=08/10/24/2245238&tid=216
 

Enzeru92

New member
Oct 18, 2008
598
0
0
DOWN WITH THE ROBOTS!!!!!! FLESH FOR EVER!

OT: that sounds freaking awesome if we can control them then it would be a win for the human race.