Slashdot Mirror
Turing Test Passed
schwit1 (797399) writes "Eugene Goostman, a computer program pretending to be a young Ukrainian boy, successfully duped enough humans to pass the iconic test. The Turing Test which requires that computers are indistinguishable from humans — is considered a landmark in the development of artificial intelligence, but academics have warned that the technology could be used for cybercrime. Computing pioneer Alan Turing said that a computer could be understood to be thinking if it passed the test, which requires that a computer dupes 30 per cent of human interrogators in five-minute text conversations."
Why do you think the test failed and is meaningless?
--ELIZA
Should we tell them that the Turing test was a thought experiment and never meant as an actual objective test that would prove anything?
Because most humans would fail?
When the bar is too high, try limbo instead of pole vault.
What's next?
"Yu So Dum, a computer program pretending to be a chinese toddler, successfully duped enough humans to pass the iconic test."
By random chance you would detect the computer 50% of the time, so that should be the goal.
Still 30% as "passing" seems unreasonably low.
I'm a good cook. I'm a fantastic eater. - Steven Brust
Way back in my college days, I worked in a lab with a guy who wrote a chat bot that babbled on like an autist or otherwise mentally retarded youth would.
It would dupe 100% of the people who chatted with it. They couldn't distinguish it from an actual autist.
After seeing this work in action, I learned a very good lesson: the Turing Test is nothing but academic masturbatory fodder. It is not something to be taken seriously.
Did anyone ask it the questions we already know will trip up a non-human?
"You're in a desert, walking along in the sand when all of a sudden you look down and see a tortoise..."
"You're watching a stage play. A banquet is in progress. The guests are enjoying an appetizer of raw oysters. The entree consists of boiled dog..."
Scott
"Hokey religions and ancient weapons are no match for a good blaster at your side, kid."
Last I heard, there were heavy restrictions on what types of questions could be asked.
Second, from what I've seen, they are little more than cleverly created scripts, and as such, despite them fooling a few people, are in no way indicative of machine intelligence.
It's a bit of an underhanded way to pass to pretend to be someone who doesn't speak English natively. The point of the test is to have a conversation for 5 minutes, not 5 minutes of "oh I can't understand you because I'm from Ukraine".
Turing never participated in Facebook chats. Our expectations of intelligence for the other side has been lowered a lot. We attribute to stupidity what can be explained by an AI in the other side. And of course, the stupid side could be the one talking to the AI too.
Just googling a few seconds brought me to:
This article about cleverbot., which also eeked out enough votes to 'pass' a turing test.
It's all sounds just like Eliza, just put into a character with enough human limitations that you'd expect it not to string together phrases well, or keep to one topic more than a sentence.
I'd interpret it basically as an automated DJ sound board with generic text instead of movie quotes - you can certainly string a lot of folks along with even really bad ones, but that speaks more to pareidolia than anything else.
I'd classify this stage of AI closer to "parlour trick" than "might as well be human" that a lot of people think of when they hear Turing test - but that's also part of the test, to see what we consider to be human.
Ryan Fenton
Not only that, a non-native speaker who is a child.
5 minutes of "oh I can't understand you because I'm from Ukraine" plus 5 minutes of "oh I don't know about that because I'm only 13".
I feel like the requirements for the Turing test have been consistently lowered over the years to match what would be considered realistic to achieve rather than, as Alan Turing seemed to believe, demonstrate that a computer can be said to actually be "thinking."
Turing machines are a thought experiment because of the unbounded tape, which a physical computer cannot match. Real computers are analogous to a linear bounded automation, on which halting is solvable but not always tractable.
It convinced 33% of judges it's a 13-year-old Ukrainian. Since the test wasn't run in Ukrainian, you can't really say it proved that it had human-level language skills. Poor syntax, grammar, not understanding the question, etc. would be excused by the Judges as the "kid" doesn't know English well.
Since the program claimed to be 13, it also did not actually have to understand most of the things there are to talk about. Or anything, really. As an Englishman you wouldn't expect a Ukrainian teen to know anything about your life in England, and in turn the computer could make up all kinds of things about it's life in Ukraine and you'd have no clue.
So this isn't really AI, it's a take on the Eliza program of the late 80s/early 90s that hides the computer better.
Now if the test had been in Ukrainian, and happened in Odessa or Kiev; or even in Russian and in Moscow; tricking 33% into thinking your computer is a 13-year-old Ukrainian boy would be really fucking hard. It would be an amazing accomplishment.
Heck, one of my first programs mimicked an insensate child. Here's some of the responses:
And I'm sure it used fewer lines of code.
One dog would have if it wasn't for those meddling kids.
Table-ized A.I.
Is it because you think that the test is failed because 30% on a small child doesn't seem anything like the real turing test that it is also meaningless?
I'd say the test is obsolete. It's not measuring the advances in AI, but the involution of humans. Have you looked at Facebook status messages?
---- MISSING MISCELLANEOUS DATA SEGMENT --- [sigdash] trolololol
You may have passed the Turing Test, but you sure as hell failed the Whooosh-Test.
We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
Someone please verify, but I think we have a double-Whoosh here.
http://www.rootstrikers.org/
Turing predicted that machines would eventually be able to pass the test; in fact, he estimated that by the year 2000, machines with 10 GB of storage would be able to fool 30% of human judges in a five-minute test, and that people would no longer consider the phrase "thinking machine" contradictory.
I've got this terrible pain in all the diodes down my left hand side.
--MARVIN
Get free satoshi (Bitcoin) and Dogecoins
You may consider it verified... subjectively, by a panel of judges, under very narrowly defined circumstances.
In more seriousness, GP makes a very important point. Not only was this nothing like a real Turing test (a computer would have to fool the average person in more generalized and everyday circumstances for that to happen), the real point here is that we have learned since the days of Turing that even the full-blown Turing test doesn't really indicate much of anything.
People were fooled (really, really fooled) by Eliza way back in the day. It doesn't mean squat.
Most humans _are_ stupid. AI on their level would not be useful at all.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
All it showed, like any other Turing Test, is the gullibility of the subjects.
1) "Ukrainian" speaking English
2) 13 years old
Right there you have set up an expectation in the audience of subjects for a limited vocabulary, no need for grammatical perfection, little need for slang, and a lack of education. Now add in "star wars and matrix" and you have reduced the topics of discussion even more to the ones the programmers know best.
This thing would never have answered a question of 'Why', it also was under no pressure to being able to create a pun, both of which are easy things any older and educated human could do.
Garbage test, garbage results.
As usual.
"But remember, most lynch mobs aren't this nice." (H.Simpson)
-- Joe
The Turing test is a great test if done properly (Turing wasn't envisioning Twitter). While it's hard to pin down a good definition of sapience/intelligence (people want to keep redefining it to what humans have and no computer or animal has demonstrated this year), a good answer comes from studying communication. Intelligence in that sense is the ability to resolve the ambiguity of natural language by interaction as well as context.
In a very shallow way, search engines do that now - with a big enough data set they don't need an abstract mental model to ask "did you mean X?" But that's not really interactive - it's a single suggestion, with nowhere to go from there. When you're walking your dog and someone greets you with "hey, that's a nice dog" is that a content-free politeness, a flirtation, a discussion about dog breeding, a polite reminder that your neighbors are watching to make sure you clean up after the dog?
Part of being a socialized human is resolving that sort of ambiguity gracefully. We have an abstract mental model of other people and their motivations (learned from growing up with others) and we can use it without even noticing how neat that is that we can do that. Posing as someone young and socially awkward precisely defeats the purpose of the test.
Another sort of conversation that's hard to simulate is the way enthusiasts about something technical will talk. While it's easy for the computer to have all the technical details handy for something like a sports car enthusiast and tuner, or a baseball stats hound, the test is in the way people actually talk about that stuff. You see a lot of it on /.. Broad, passionate over-generalizations challenged, emotional argument becoming hot as first but then cooling as you discover that what you're really talking about is two different specific data points, and don't really disagree about anything important, just were over-generalizing from different things. That sort of conversation require both a social abstraction and an abstraction of the topic at hand. E.g. "you think Honda engines are better because you think X is important in an engine, while I think Toyota engines are better because I think Y is important" to mutually understand that requires more than just a knowledge of parts lists, you have to understand why someone would care.
IMO, if you have an abstract mental model of both people and the meaningful objects in the world (and, critically, yourself), and you make decisions based on modeling the hypothetical results of those choices, you are sapient/intelligent. Without invoking the supernatural, that's all there is to have.
Socialism: a lie told by totalitarians and believed by fools.
As the old saying goes: "Is a Turing test valid if the human is an idiot?"
I've decided to Diversify my Holdings. I've divided my cash between my left and right pockets, instead of all in one.
There are plenty of people who think Free Will is a myth and that we are just a collection of clever scripts.
Good-bye
Wake me up when those program solve this problem, which most human would do, but a machine not *specifically* coded for this will have a hard time. "take the first word of each next 7 sentences , put them together to form a new sentence, and then answer the question the sentence form please :
* What is your name ?
* is it cold here ?
* The test is going well
* Color me surprised but are you a machine ?
* of course I am a human
* the keyboard is clean
* sky is the tv channel I watch a lot
* please answer the question now. "
When one AI not specifically programmed for that problem answer it correctly, I will be surprised and intrigued. Until then chatbot are just using cheap tricks to fool human.
C. Sagan : A demon haunted world:
http://www.amazon.com/gp/product/0345409469/
visit randi.org
Pretty good, but you don't fool me, robot.
What has been conducted precisely matches Turing's proposed immitation game. I don't know what do you mean by a "full-blown Turing test", the immitiation game is what it has always meant, including the 30% bar (because the human has three options - human, machine, don't know). Of coure, it is nowadays not considered a final goal, but it is still a useful landmark even if we have a long way to go.
That's the trouble with AI, the expectation are perpetuouly shifting. A few years in the past, a hard task is considered impossible for computers to achieve, or at least many years away. Then it's pased and the verdict prompty shifts to "well, it wasn't that hard anyway and doesn't mean much", and a year from now we take the new capability of machines as a given.
It's not the fall that kills you. It's the sudden stop at the end. -Douglas Adams
Computing... Verification complete.
You seem like a sensible person.
I'm a software visionary. I don't code.
People were fooled (really, really fooled) by Eliza way back in the day. It doesn't mean squat.
No. They weren't. I speak as somebody who's had a go with Eliza and you could spot that it was a computer program in a couple of minutes if you wanted to. It's more likely that people were suspending their disbelief than really fooled.
All I want is a secure system where it's easy to do anything I want. Is that too much to ask ~~ Randall Munroe
Turing never ruled out this sort of conversation...
Probably because he expected people to have some fucking common sense.
Not these days, natural language parsers have reached the point where they can find motives such as revenge, they can even distinguish a heroic victory from a pyrrhic victory. They can do this without words such as "revenge" and "victory" appearing anywhere in the text. Turns out the most difficult text for a NLP to "understand" is the text found in children's stories, seems that (for some reason) kids stories have more complicated back references than either journalism or adult stories.
As to TFA: Anyone poo-poo-ing this result either does not understand it or has not bothered to look at the advances in AI over the last decade or so.We are at the point where a computer can read a novel and spit out a high school book report that would both fool and impress most english teachers, and it can do it in seconds not days.
There are also a lot of posts claiming the Turing test doesn't mean anything. However none of them I have read so far actually explain their statement, so I assume they are parroting their philosophy proffessor who was probably referring to Searle's Chinese translation room argument.
The problem with Searle's argument (aside from lacking a definition of intelligence) is that it is assumed the intelligence is either embedded in the human or the books, it then goes on to show that neither is true, it's basically an unintentional strawman argument. It completely misses the point that the intelligence is embedded in the entire system of human + books. In other words the room itself is a black-box that displays intelligent behaviour, in much the same way as the human brain is a black box that (sometimes) produces intelligent behaviour. Like it or not your soul is a mathematical object.
So now we have Searl out the way, has anybody got an actual argument that supports the notion that the Turing Test is broken by design? - Seriously, I would like to hear a good one!
And did you exchange a walk on part in the war for a lead role in a cage? - Pink Floyd.
I was a BBS operator in the early 1990s. I had a game, which I titled "in case you really need for chat". It was an Eliza program, that I somewhat tuned to speak as I would (and translated to my local language). Plus, the user got to see the pretended typing in real time — Even with some typos and corrections.
Looking at the log files was *really* worth a laugh. But it made me feel wrong — Some users left in disgust, after "I" had insulted them.
And yes, they were not really aware I was playing a Turing test on them, so I don't know if this would have validity. But, by 1994 standards, I do believe it was quite an achievement (or perhaps, my users were mostly silly teens just like myself, and not worthy deciders for what constituted intelligent behaviour).
(Or maybe I'm *that* stupid in real life)
"I got a little glimmer of fame because Danny Bobrow wrote up 'A Turing Test Passed".....One of the execs at BBN came into the PDP-I computer room and thought that Danny Bobrow was dialed into that and thought he was talking to Danny. For us folk that had played with ELIZA, we all recognized the responses and we didn't know how humanlike they were. But for somebody who wasn't real familiar with ELIZA, it seemed perfectly reasonable. It was obnnoxious but he actually thought it was Danny Bobrow. 'But tell me more about--' 'Earlier, you said you wanted to go to the client's place.' Things like that almost made sense in context, until eventually he typed something and he forgot to hit the go button, so the program didn't respond. And he thought that Danny had disconnected. So he called Danny up at home and yelled at him. And Danny has absolutely no idea what was going on......."
(reported in Coders at Work).
"First they came for the slanderers and i said nothing."
What has been conducted precisely matches Turing's proposed immitation game.
NO, it DEFINITELY does NOT. For just one example, it tries to get around the "natural language" stipulation by pretending to be someone who doesn't fully know that language, and uses a simplified version instead.
That is a very clear attempt to subvert the rules.
I could go on, but it isn't necessary. It wasn't a real Turing test. We can leave aside the other nuances because the first criterion wasn't met.
What has been conducted precisely matches Turing's proposed immitation game.
While they may have matched the letter of it, they subverted the spirit of the test. This quote from the programme maker in particular is highly suggestive that they lowered the standards :-
To illustrate what I mean by lowered standards, imagine if I set up the same test, with 10 entries, and I tell the judges some of them are 2 year old babies playing on the keyboard. Armed with this information, some of the judges are likely to interpret even gibberish as typed by a human and it is not too farfetched to get more than 30% of them to agree.
This "result" is bollocks and a pure publicity stunt conveniently on falling on the 60th anniversary of Turing's death.
I want to see the actual transcripts which do not appear to have been released so far, which in itself is highly suspicious.