Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

kurzweilai.net

Post reply on HN
Print view View original

71–80 of 164 posts

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#71

Post by orbifold »

higherpurpose wrote: post #4

The whole thing sounded iffy to me from the first second I heard about it, despite the fact that most of the tech media was going ga-ga over it. I mean, the AI being only a teenage Hungarian boy (meaning the judges should've expected it to be "less intelligent than a normal native adult")...and only fooling 1/3 of the judges? That sounds like a whole lot of cheating to declare that it "passed" the Turing test.

Pretty much any question that requires actual natural language understanding would presumably instantly reveal a bot today, like 'Is white darker than black?'.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#72

Post by jamesbrownuhh »

noonespecial wrote: post #32

Turing test and all it's connotative baggage aside, the first chatbot that will impress me is the one where I can't for the life of me figure out how it's creating the responses it is. "Eugene", I can imagine creating when I was 12.

Absolutely. Responses like Eugene's seem straight out of the "Eliza" program I typed into my home computer (out of a magazine) in the mid 1980s. If Eugene is the new state of the art, as some have claimed, it doesn't seem that there has been any progress at all in the last 30 years.

Perhaps next year the test will be won by Ham Hamuelson, an AI persona who managed to convince the judges that he was a talking ham sandwich. I guess we can't completely rule that out.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#73

Post by xmonkee »

computator wrote: post #70
computator wrote: post #65

Kurzweil's and Mitch Kapor's rules on how to judge a Turing Test are well thought out ( * 1), but I'm finding that it's actually biased against the computer (and therefore unfair to Kurzweil). There's a significant chance that a computer with a breathtaking performance will lose by probability alone . Look at this rule: The Computer will be deemed to have passed the “Turing Test Human Determination Test” if the Compu…

Can someone please help with the probability calculation? 3 judges and 4 participants What's the probability that any 2 or all 3 judges will pick a particular participant ("the computer") out of 4 at random?

all 3 = 1.6% any 2 = 14%

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#74

Post by afarrell »

jgrahamc wrote: post #18
ceejayoz wrote: post #16

Earlier quoted context omitted.

Don't forget things like neurostimulators for Parkinsons and back pain, too.

Yes, also cochlear implants.

I have a friend with a cochlear implant who occasionally refers to himself as a cyborg. I'm actually not clear on to what degree he identifies as such. I suspect that there isn't much in the way of "cyborg culture" and so therefore the idea of "cyborg identity" doesn't have a lot to it.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#76

Post by blauwbilgorgel »

DanBC wrote: post #52
blauwbilgorgel wrote: post #34

The chatbot Eugene Goostman did not pass Ray Kurzweil's version of the Turing Test. It passed the Turing Test as set up by the organizers. Turing never even mentioned the criteria that participants should be aware that they are possibly talking to a computer. This single criteria should not matter for intelligence IMO, because the whole point of the test was to abstract away the appearance. The other way around: a ch…

> Turing never even mentioned the criteria that participants should be aware that they are possibly talking to a computer. What? Here's what he said. It seems pretty clear that this version of the game involves one human interrogator, one human and one computer, and the interrogator has to decide which is human and which isn't. > The new form of the problem can be described in terms of a game which we call the 'imita…

The specifics of the Turing Test have been debated for decades. It is clear that different versions and interpretations exist, especially now we have moved on from behaviorism that was popular during the time Turing wrote the paper.

From your quotes it only says that player A is to be replaced with a machine, not that player C is to be made aware of this replacement. I do agree that that is the popular interpretation, but it isn't written down, leading to this ambiguity.

>the interrogator has to decide which is human and which isn't.

The interrogator has to decide which is female and which is male. Replace the female or male with a computer, not making the interrogator aware of this and see if the interrogator is wrong as often as before.

Kurzweil questions this bot, as if it was a bot. He is aware that he is talking to a bot, and doesn't even have to choose between A or B.

Kurzweil's line of questioning is not fair or normal or productive communication even if it was between two humans. A 13- year-old boy would have told Kurzweil to bugger off when tasked to answer 2+2 or wouldn't have responded at all.

Repeat questions like that in a random chatroom and people will think that you are the chatbot.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#77

Post by kbenson »

computator wrote: post #65

Kurzweil's and Mitch Kapor's rules on how to judge a Turing Test are well thought out ( * 1), but I'm finding that it's actually biased against the computer (and therefore unfair to Kurzweil). There's a significant chance that a computer with a breathtaking performance will lose by probability alone . Look at this rule: The Computer will be deemed to have passed the “Turing Test Human Determination Test” if the Compu…

It only has to happen once for Kurzweil to win, so it seems fair to me he has a higher bar. Winning through chance is much less fair than losing through chance in this situation.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#78

Post by falcor84 »

computator wrote: post #65

Kurzweil's and Mitch Kapor's rules on how to judge a Turing Test are well thought out ( * 1), but I'm finding that it's actually biased against the computer (and therefore unfair to Kurzweil). There's a significant chance that a computer with a breathtaking performance will lose by probability alone . Look at this rule: The Computer will be deemed to have passed the “Turing Test Human Determination Test” if the Compu…

From what I understood, the ai would only need to win once. Therefore, after the computer reaches near-human intelligence, it'll be statistically sure to win in a few years. (And given Moore's law, in these few years the ai will continue to significantly improve)

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#79

Post by notahacker »

> In 2002 I negotiated the rules for a Turing test wager with Mitch Kapor on the Long Now website. The question underlying our twenty-thousand-dollar bet... was, “Will the Turing test be passed by a machine by 2029?” I said yes, and Kapor said no. It took us months of dialogue to arrive at the intricate rules to implement our wager.

If this was a sci-fi short, the twist would be "Ray Kurweil" admitting at the end of these negotiations that he was a bot that had borrowed the futurist's email address.

Re: Response by Ray Kurzweil to chatbot Eugene Goostman “passing the Turing test”

#80

Post by thesteamboat »

computator wrote: post #70
computator wrote: post #65

Kurzweil's and Mitch Kapor's rules on how to judge a Turing Test are well thought out ( * 1), but I'm finding that it's actually biased against the computer (and therefore unfair to Kurzweil). There's a significant chance that a computer with a breathtaking performance will lose by probability alone . Look at this rule: The Computer will be deemed to have passed the “Turing Test Human Determination Test” if the Compu…

Can someone please help with the probability calculation? 3 judges and 4 participants What's the probability that any 2 or all 3 judges will pick a particular participant ("the computer") out of 4 at random?

Suppose that the participants are all indistinguishable. Each judge has a 3/4 chance of "being fooled". Let p be the event that the computer is correctly determined, and let q be the event that the computer is not selected. We calculate (1/4p+3/4q)^3 = 1/64(p^3 +3p^2(3q) + 3p(3q)^2+(3q)^3) = 1/64 (p^3 + 9p^2q + 27pq^2 + 27q^3). The probability, then, that the computer is chosen by random chance is 10/64 or approximately 15%.
Post reply on HN