Chatbot 'Eugene Goostman' passes the Turing test

#3
http://www.independent.co.uk/life-s...ademics-warn-of-dangerous-future-9508370.html

Eugene Goostman, a computer programme made by a team based in Russia, succeeded in a test conducted at the Royal Society in London. It convinced 33 per cent of the judges that it was human, said academics at the University of Reading, which organised the test...


The computer programme claims to be a 13-year-old boy from Odessa in Ukraine...

The success came on the 60th anniversary of Turing's death, on Saturday...
Allow me to rephrase:

On the 60th anniversary of Turing's death, we've come up with this totally silly story about the Turing test having been passed because a computer program pretending to be a 13-year old Ukranian boy succeeded in fooling 1 in 3 judges that it was human. We think this says rather more about the gullibility of a third of the judges than it does about the program passing the test.
 
#5
Allow me to rephrase:

On the 60th anniversary of Turing's death, we've come up with this totally silly story about the Turing test having been passed because a computer program pretending to be a 13-year old Ukranian boy succeeded in fooling 1 in 3 judges that it was human. We think this says rather more about the gullibility of a third of the judges than it does about the program passing the test.
LOL, I'd be curious if that 1/3 of the judges would be able to pass the Turing test themselves :D
 
#6
While I don't doubt that a bot could eventually pass a Turing test, this sounds like a lot of hype when you read what actually happened.

The bot convinced only 33% of the judges that it was a 13-year old boy who doesn't speak English as his native language. Being a non-native English speaker will mask many of the mistakes the bot makes, because the judges don't know if the mistakes are due to it being a robot or just being unable to understand proper English. And 13 is young enough that it would not be surprising for him not to be able to answer many of the questions. Even so, 2/3 of the judges still thought it was a bot. Not to belittle the designers, but the conversations I've read from it don't sound all that impressive
 
#7
While I don't doubt that a bot could eventually pass a Turing test, this sounds like a lot of hype when you read what actually happened.

The bot convinced only 33% of the judges that it was a 13-year old boy who doesn't speak English as his native language. Being a non-native English speaker will mask many of the mistakes the bot makes, because the judges don't know if the mistakes are due to it being a robot or just being unable to understand proper English. And 13 is young enough that it would not be surprising for him not to be able to answer many of the questions. Even so, 2/3 of the judges still thought it was a bot. Not to belittle the designers, but the conversations I've read from it don't sound all that impressive
That's what I was thinking, too.
 
#9
This sounded exciting until reading the article. I've read about this kind of cheat in the past, the Eliza bot built in to emacs used it. I recall reading its designer stating he chose a psychotherapist because it required no vast index of actual useful knowledge. I guess we need a "Turing Squared" type of test that is more stringent, since so many people are obsessed with passing the Turing test while missing the spirit [sic] of it.
 
#11
I don't know whether I've missed it. I wondered whether the transcripts of any of the sessions are available, to show what sort of exchanges took place.
Try the thing out for yourself. It repeats the same dialogue over and over again. It's kinda hilarious that this "turing test" event managed to prove that 33% of people are pretty stupid.
 
#12
Try the thing out for yourself. It repeats the same dialogue over and over again. It's kinda hilarious that this "turing test" event managed to prove that 33% of people are pretty stupid.
Sure, I already tried it out for myself. That's why I
a) expressed doubt that this was the same as the program being discussed.
b) hoped to see the transcripts in order to clarify what sort of exchanges actually took place.
 
#13
Sure, I already tried it out for myself. That's why I
a) expressed doubt that this was the same as the program being discussed.
b) hoped to see the transcripts in order to clarify what sort of exchanges actually took place.
Sorry, I was reading multiple articles and got sidetracked to the fact that you posted the link.

I really doubt we'll see any sort of transcripts. The creators seem to be very intentional in bolstering the power of their AI.

I asked the thing if it was a human, and it replied something like "Yes, please believe me so I can win this goddamn prize!"
 
#14
What a joke...

I wrote
: "I don't feel good today"
Reply: "Nice to hear that! Do you like the weather?"
I wrote: "It ain't good either"
Reply: It's funny to talk to you! Continue, Monty Python! :)
 
#16
Someone e-mailled me a link to this:
http://io9.com/why-the-turing-test-is-bullshit-1588051412

Also the real turing test involves taking ESP into account:

http://www.loebner.net/Prizef/TuringArticle.html

COMPUTING MACHINERY AND INTELLIGENCE

By A. M. Turing
...
(9) The Argument from Extrasensory Perception

I assume that the reader is familiar with the idea of extrasensory perception, and the meaning of the four items of it, viz., telepathy, clairvoyance, precognition and psychokinesis. These disturbing phenomena seem to deny all our usual scientific ideas. How we should like to discredit them! Unfortunately the statistical evidence, at least for telepathy, is overwhelming. It is very difficult to rearrange one's ideas so as to fit these new facts in. Once one has accepted them it does not seem a very big step to believe in ghosts and bogies. The idea that our bodies move simply according to the known laws of physics, together with some others not yet discovered but somewhat similar, would be one of the first to go.

This argument is to my mind quite a strong one. One can say in reply that many scientific theories seem to remain workable in practice, in spite of clashing with ESP; that in fact one can get along very nicely if one forgets about it. This is rather cold comfort, and one fears that thinking is just the kind of phenomenon where ESP may be especially relevant.

A more specific argument based on ESP might run as follows: "Let us play the imitation game, using as witnesses a man who is good as a telepathic receiver, and a digital computer. The interrogator can ask such questions as 'What suit does the card in my right hand belong to?' The man by telepathy or clairvoyance gives the right answer 130 times out of 400 cards. The machine can only guess at random, and perhaps gets 104 right, so the interrogator makes the right identification." There is an interesting possibility which opens here. Suppose the digital computer contains a random number generator. Then it will be natural to use this to decide what answer to give. But then the random number generator will be subject to the psychokinetic powers of the interrogator. Perhaps this psychokinesis might cause the machine to guess right more often than would be expected on a probability calculation, so that the interrogator might still be unable to make the right identification. On the other hand, he might be able to guess right without any questioning, by clairvoyance. With ESP anything may happen.

If telepathy is admitted it will be necessary to tighten our test up. The situation could be regarded as analogous to that which would occur if the interrogator were talking to himself and one of the competitors was listening with his ear to the wall. To put the competitors into a "telepathy-proof room" would satisfy all requirements.
 
#18
It's fascinating that Turing believed the results for telepathy were strong, I doubt you'd see singularity proponents and transhumanists admitting or knowing that.
However, note the phrase, "How we should like to discredit them!" which struck me as rather odd. Why not instead, "How we should like to study and understand them more!".

It sometimes seems as though there was a historical trend on what was the 'politically correct' view. Going back a century or more, many prominent scientists openly discussed and investigated such ideas. Turing would have liked to see them discredited. Nowadays the view is often expressed that they have already been discredited. But against that background of changing forms of expression, the actual experiences and phenomena continue, just as they have always done.
 
Top