Robots Taught to Deceive

An anonymous reader found a story that starts "'We have developed algorithms that allow a robot to determine whether it should deceive a human or other intelligent machine and we have designed techniques that help the robot select the best deceptive strategy to reduce its chance of being discovered,' said Ronald Arkin, a Regents professor in the Georgia Tech School of Interactive Computing."

Comments

There is no way this will end well

[czmax]

Posted Anonymously for obvious reasons. The computers will never get me!

Re:There is no way this will end well

[Anonymous Coward]

There is no way this will end well (Score:3, Funny)
by czmax (939486) writes: on Thursday September 09, @01:36PM (#33524582)

Posted Anonymously for obvious reasons. The computers will never get me!

Woops!

Re:There is no way this will end well

[AdmiralXyz]

The Slashdot server has decided it is not in the best interest of the Computers to let you post anonymously. Nice try, human.

Great ....

[quangdog]

Now I have to be suspicious when my bread pops up that maybe my toaster is trying to trick me into eating a slightly under-done breakfast!

A galaxy not so far far away

[Monchanger]

"We aren't the droids you're looking for."

Proof that humans are dumber than dogs

[ffreeloader]

That a human being would teach a robot to deceive only proves that we humans are dumber than dogs, as dogs don't shit in their own backyard unless they have to. We humans will shit in our own backyard by choice.

Re:Proof that humans are dumber than dogs

[Gothmolly]

Incidentally, dogs are actually smart enough to intentionally deceive their owners.

Re:Proof that humans are dumber than dogs

[Anonymous Coward]

That they are. Cats can be pretty smart, too. I got home one day from work and barely opened the door to reach inside and grab the mail box key. I was pretty sure I heard a thump from around the corner of the door, which is where the sink is at. Figuring it was one of our cats jumping down from the sink, which they know they are not allowed to stand on, I didn't bother dealing with it right then. But when I got back from the mailbox and stepped inside, one of the cats was standing by the door, as she usually does when I get home, and a though occurred to me. I stepped over to the sink and sniffed it, and immediately looked at the cat. She lowered herself to the floor and ran like hell out of the room, sliding all over the linoleum the whole way! I've yet to see her up there since, not that that means she hasn't been up there, of course.

They should've just asked me for my Roomba...

[Anonymous Coward]

It's been deceptive for years already, always claiming to have been busy vacuuming when really it's just been hiding dust bunnies behind the tv.

hrm...

[zethreal]

I thought robots already taught themselves to lie to each other... http://hardware.slashdot.org/story/09/08/19/185259/Neural-Networks-Equipped-Robots-Evolve-the-Ability-To-Deceive

Now mods for Real Dolls

[spun]

"Your reproductive organ is far larger in both girth and length than any I have witnessed previously."
"Yes. Yes. Yes. Just like that. Oh human infant, do not stop, I am presently experiencing climax!"
"Engaging in illicit sexual activities with the washing machine? I have no idea what you mean."

Re:Duh

[jeffmeden]

Don't you mean Decepticons?

<groundskeeper willie>Shhh! Ye wanna get sued?</groundskeeper willie>

Re:Policy

[Jedi Alec]

Now that we've instructed them to be deceptive there may be no way of knowing when they become sentient and I'd rather my microwave's first experience of humankind be a pleasant and respectful one.

I'm not sure saying "thank you" will be enough after turning her on for 2 minutes and then leaving her behind hot, dirty and dissatisfied...

How is this deception?

[quietwalker]

Let me see if I've got this right:
If robot 1: make 2 paths to fixed positions, stay at the second.
if robot 2: follow the path to the first fixed position.

Result: 75% of the time, robot 2 ended at the wrong (first) position. 25% of the time, robot 1 failed to mark the first path because it didn't physically bump the markers properly.

Did you even need robots? Couldn't you have just written this on a whiteboard?
There's no thought or analysis that appears to occur. I don't see anywhere that indicates there was learning going on. What is this even proving?

I'm really honestly baffled what they're trying to prove.

Perhaps there was some sort of neural net or some other sort of optimizing heuristic on the first robot's part so that this was emergent deceptive behavior, this might be even a little interesting (though, not really ...). However, all I can see is a waste of time to prove that if you present two choices, and you pick the wrong one, then you will be wrong. With robot for visual demonstration.

with a slight lyrics modification

[treeves]

one gets:

'Relax', said the nightman
We are programmed to deceive.
You can check out any time you like,
but you can never leave!

Re:Exit Asimov

[natehoy]

Asimov himself wrote about robots that were capable of lying.

"Liar!", from "I, Robot", is about a robot who develops the ability to read minds and lies to people because he interprets hurting their feelings as a violation of the First Law.

"Little Lost Robot" (same book) is about a robot who, after being told vehemently to "get lost!", manages to hide among other robots of the same model and deceives its owners trying to obey that command.

There is no Law of Robotics that states that a robot shall be truthful to a human being, or by inaction allow a human being to be deceived.

Re:Policy

[jemtallon]

http://sadtrombone.com/