Slashdot Mirror
Variations On the Classic Turing Test
holy_calamity writes "New Scientist reports on the different flavors of Turing Test being used by AI researchers to judge the human-ness of their creations. While some strive only to meet the 'appearance Turing Test' and build or animate characters that look human, others are investigating how robots can be made to elicit the same brain activity in a person as interacting with a human would."
Arrgg... I just took the test and failed. Does this mean that I'm ready to run Linux, and when I die I'll be running FreeBSD?
FORMALISTS' MOTTO: Take care of the syntax and the semantics will take care of itself.
Also, if you are animating a dude, he is thinking about sex. If you are animating anyone else, they are thinking about shopping.
Technically AI is not hard, you just need to lower your mind-mechanics bar and focus on trailer parks, and folk psychology.
The dangers of knowledge trigger emotional distress in human beings.
It really is kind of creepy how close they've come to actual life-like robotics... but my question is, how life-like should a robot really be? I mean, are we going to be replacing friends with these guys, or are they meant to serve us? Don't get me wrong, I have a great respect for these scientists, I just wonder how these sorts of real robots will fare on the market.
The Turing test is for apparent 'human' intelligence, where robotics adds communications via 'expressiveness'. These are two different vectors: rote intelligence and capacity to communicate (via body language, and the rest of linguistics/heuristics).
The article doesn't abstract the basic cognitive capacity because it entangles it with the communications medium. The Turing Test ought to be done in a confessional, where you don't get to see the device taking the test. It would also provide a feedback loop on the test as well.
---- Teach Peace. It's Cheaper Than War.
I dunno, but I get the feeling that Solaris 10 must somehow be involved.
My blog
Ninnle Linux is not only capable of independent thought, but is also completely self aware. This is the latest development from Ninnle Labs.
... is going to come when we need to program computers to test humans for being machines. I know it's probably been written about in some forgotten sci-fi book somewhere, but what if we actually forgot that some of us weren't human and once we realized that mistake there was no way to tell who was artificial and who was the real deal. I guess that's not really much different than The Matrix, or Blade Runner, but still it would be an interesting twist to see how humanity could forget that they had made something like themselves.
The eternal struggle of good vs. evil begins within one's self.
We do interviews via IM and if the interviewee cannot convince two out of three of the interviewers they are not a bot, they don't make it to the second round.
Kwisatz Haderach
Sell the spice to CHOAM
This Mahdi took Shaddam's Throne
The wife and I were looking for ways to spice up the ol' Turing Test.
Escape Pod Films: Sketch Comedy and Web Series
I'd be really surprised if something that appeared to be X caused a different pattern in the brain than X. If X causes a certain response in the brain, and Y does not, how can you say that Y appears to be X? "appearing" is something that happens entirely in the brain. There has to be at least some common response in the brain if two things appear to be similar.
Give me Classic Slashdot or give me death!
Given the level to which conversation has sunk, they ought to flip it around - prove that you are human via chat or IM.
I'm betting a significant percentage of the populace would fail.
(now, if only we could make that a requirement for voting...)
"As God is my witness, I thought turkeys could fly." A. Carlson
The best chatbots I've come across are at www.a-i.com
Not quite good enough to pass the turing test yet, but some are quite witty.
Have fun. Or failing that, be miserable with style.
I understand people's fear of machine intelligence exceeding that of humans, but it is actually more dangerous to have machines merely mimicing human-ness than to have machines that are intelligent enough to actually understand what we say better than another human could.
That means more than merely having some mockery of mirror neurons for "empathy". It means genuine understanding: The ability to model.
The reason this is central to our relationship to our machines should be obvious: Friendly AI really boils down to the problem of effectively communicating our value systems to the AIs.
That's why natural language comprehension is the first step to friendly AI.
HENCE:
Seastead this.
voit-comp?
While some strive only to meet the 'appearance Turing Test'
I don't come here to be insulted, you insensitive clod!
No trees were harmed in the posting of this message. However, a great number of electrons were terribly inconvenienced.
Shouldn't we make something that passes the original Turing Test first, before we go moving the goalposts?
Having chatted with elbot, I have to say that they must have had some pretty dense testers.
They're using CNS activity in the humans as their metric? Really? Then they're not getting it. The test is behavior. Internal events may be interesting but they're not part of the test. Otherwise we'd also be using internal events in the machine as part of the test. It really is amazing; it's like Ryle never happened. You imagine the researchers next examining Holmes's words with a magnifying glass to learn more about Doyle.
Did they include extra points?
Sure.
Friends past college aren't up to go to Taco Bell at 12:37 at night anymore. Or carry on a really tough conversation about 4 editions of Dante's inferno.
My first Journal Entry ever, in 8 years! http://slashdot.org/journal/365947/aphelion-scifi-fantasy-horror-poetry-webzine
He's joking, but I'm not.
It's been discovered that the truncated knowledge domain of Cybering has led it to be exploited as phishing. It's damn tough to tell between a phish bot and someone with terrible typing skills and worse computer knowledge.
My first Journal Entry ever, in 8 years! http://slashdot.org/journal/365947/aphelion-scifi-fantasy-horror-poetry-webzine
My solution for that is simple: Ignore them both.
Seriously, if you can't bother to type English correctly, I can't be bothered to read what you are saying. In addition, I've found that most of those posts are people asking for help, not providing information, so I really lose nothing by ignoring them.
It's no different than meatspace, really. If someone came up to me, shoved their phone in my face and said 'Fix.' I'd ignore them, too. Even my boss doesn't do that and he holds my paycheck in his hands.
I have a small amount of sympathy for people who are just learning English, but even they don't get to forget that sentences and proper nouns get capital letters. And every sentence has punctuation.
"If you make people think they're thinking, they'll love you; But if you really make them think, they'll hate you." - DM
If human-like appearance is a kind of Turing Test, how come Madame Tussauds hasn't gotten an ACM Award yet? Or Al Gore.
The turing test always struck me as ridiculously anthropomorphic. Clearly the existance of non-humanlike intelligence can be envisaged. But no matter how smart, it would fail this test.
Furthermore, in an in-depth conversation, surely an AI would have to lie (talk about its family, its working life, etc)...
If we continue to enshrine the standard of the Turing test, we're aiming for a generation of inherently untruthful fake-people machines. If it 'knows' that many/most things it tells us are lies, it may well have to assume the same for us. At this point, I suspect its time to drop in a skynet reference or two.
Lastly, its worth pointing out that for a 2 minute conversation, a randomly selected response of "lol" "haha" and "rofl" would match, if not out-score many people on the Turing test.
See Universal Intelligence: A Definition of Machine Intelligence.
Seastead this.
I'm still waiting for a computer to convince me it's as smart as a parrot.
--
RIP Alex
I just came back from my last exam, on AI, including stuff like the turing test, chinese room etc...
I come back and log onto Slasdhdot and see this! You insensitive clod! :-(
Hello, I am wearing tight pants and would like to remove them in a suggestive manner, using only noble gases and UNIX. Any suggestions?
iWork 09 and a large consumption of cabbages?
The Turing test isn't like a litmus test - you don't get a clear and definite result either way.
Failing to pass the Turing Test doesn't mean a thing isn't intelligent, but if we make something that can pass, then it's something to take notice of.
Artificial intelligence came a step closer this weekend when a computer came within five percent of passing the Turing Test, which the computer passes if people cannot tell between the computer and a human.
The winning conversation was with competitor LOLBOT:
The human tester said he couldn't believe a computer could be so mind-numbingly stupid.
LOLBOT has since been released into the wild to post random abuse, hentai manga and titty shots to 4chan, after having been banned from YouTube for commenting in a perspicacious and on-topic manner.
LOLBOT was also preemptively banned from editing Wikipedia. "We don't consider this sort of thing a suitable use of the encyclopedia," sniffed administrator WikiFiddler451, who said it had nothing to do with his having been one of the human test subjects picked as a computer.
"This is a marvellous achievement, and shows great progress toward goals I've worked for all my life," said Professor Kevin Warwick of the University of Reading, confirming his status as a system failing the Turing test.
http://rocknerd.co.uk
The classic Turing Test is not so good because it focuses on the appearance of intelligence rather than the mechanism for it. People design systems to do well at the test, thus evolving current AI work towards mimicking human conversation (including potential thought involved) rather than actually creating new thoughts.
I think a much harder test for machine intelligence would be passed when the *machine* cannot reliably tell itself from a human!
its out there, you're just not looking. or your standards are too high (which seems to be a bit of a contradiction given what OP implies)
(posting AC for obvious reasons, LOL)
FTFA:
Quite how such a military Turing test might be validated safely is a moot point. But Arkin believes that such machines could even be more ethical soldiers than humans - free as they are from emotions and prejudice over human traits such as race.
Indeed, all the puny weakling fleshy meatbags are reprocessed regardless of race or creed.
Upon reading the military Turing test, it occurred to me that this is the ultimate soldier. It can always fall upon this famous quoted line to indicate why it did why it did. This brings more bearing in modern times when soldiers are being prosecuted for their battle decisions.
In an in-depth conversation with a stranger, I would most likely lie in response to certain questions (where do you keep your money?). In addition, there would be any number of requests that I might be either unable to answer (please recite the first hundred digits of e), might give inappropriate responses to (would you care for some bangers and mash?), or that I would refuse to discuss outright (what are your feelings about abortion?). That being said, the stranger could most likely satisfy his or her doubts as to my sentience rather readily, because my truth-deficient answers made "sense," given the context. Lies might not be necessary; in the example of a computer queried about its personal life, it could respond, depending on the context, in a variety of ways: "It's none of your business," or, "I work for Proctor & Gamble, performing accounting services," or, "I believe that you are attempting to ascertain my humanity, a factor which has no bearing upon the topic at hand; let us please continue upon our primary line of inquiry."
In any case, it is asinine to believe that we can craft functional, communicative intelligence without including the potential to lie and to equivocate. It's a necessary condition, frankly. Self-awareness implies intentionality, and the rational pursuit of goals in a competitive environment entails various forms of prevarication. The frightening aspect of this is that computers would presumably be far better than us at lying, were they so inclined.
This article really doesn't have that much to do with the Turing test for most of its extent. The point of the Turing test isn't merely that under some circumstances machines can be confused with humans. The whole point of the Turing test is that it takes something that we think is essential to being intelligent or being conscious, and has the machine replicating that exactly. Or at least, that's how Turing intended it. Building sophisticated mannequins doesn't cut it - hopefully no-one thinks that merely looking like a human being means that something is intelligent and/or conscious, no matter how good they look.
(if the automata Ishiguro has produced also answer students' questions intelligently, then the situation is different, and more like that of the original Turing test).
Similarly, what opponents humans like to play against doesn't really show us anything. If anything, it shows that Turing-like tests are unreliable because people tend to think that if it has a human face it's more 'interesting'.
The business with computers and war crimes simply begs the question. Certainly a computer that releases nuclear missiles in response to certain conditions is possible now - in fact, I'd be surprised if such a dead-man's switch doesn't exist already. But even though no person has pulled the switch doesn't mean that the computer is guilty of war crimes, any more than a car left in gear that runs over someone is guilty of a traffic violation. You need rationality and knowledge of consequences of actions to be guilty of anything. Note also that there's nothing about deceiving humans here, so I'm not really sure why this is even in the same article.
The only thing in here which comes close to something that sounds anything like intelligence (let alone consciousness) is the jazz-playing robot.
So it's a bit of a hodgepodge mess of completely different issues. It would be better (but less breathlessly exciting) to take out the stuff about war-crimes and any mention of the Turing test and call it 'computers with human faces' or something. At least then it would have a unified subject-matter.