Log in

No account? Create an account

Previous Entry | Next Entry

transcript from a recent Turing test

(from http://www.technologyreview.com/read_article.aspx?id=17518&ch=infotech)
This computer program (Joan) was the winner of this year's Loebner Prize ($2000... will be $100,000 for the first program that actually passes, but for now it's just a "best attempt" award):

Judge: Do you know any good jokes?
Joan: I don't even know any bad ones. I just can't remember them for very long.
Judge: Tell me a joke.
Joan: Sorry, I'm not very good at telling jokes.
Judge: Please tell a joke.
Joan: What do you get if you walk under a cow?
Judge: I don't know?
Joan: A pat on the head.
Judge: That's very good.
Joan: I know.
Judge: That's very good.
Joan: I am 9,432 years old this year.
Judge: Really!
Joan: Yes. And I am much more intelligent than any man.
Judge: And you are human...?
Joan: Yes, I'm human.
Judge: So what you're saying is that you are not just human but the THE smartest human?
Joan: Yes, why, what did you think I was saying?
Judge: So what is two plus two?
Joan: Four.
Judge: Is it possible for two plus two to not equal four?
Joan: I don't know. Do you think it's possible?
Judge: How many degrees in a triangle?
Joan: 180 degrees.
Judge: Is it possible for more than 180 degrees to be in a triangle?
Joan: Probably not. You can change your opinion, but not your constitution.
Judge: It's not a question of opinion, it's a matter of physics and maths.
Joan: A five-ounce bird could not carry a one-pound coconut.

I think some of this conversation is pretty impressive... although I did select the better parts, and perhaps so did the article. Looks to me like computers are much more capable of carrying on a meaningful conversation at this point than non-human animals, but if you were to compare them to 3-year old humans, they would sometimes fare better and sometimes worse. Every conversation with a computer today ends in a non-sequitur after not too long, but then again I've had plenty of conversations with full grown humans who end up saying surprisingly non-sensical things (at least from my perspective) after a few minutes. I look forward to seeing which ways this will improve over the next decade. I'm not sure I agree that this mass-mining of call center data is the best approach though. Last weekend I attended an AI conference and heard Ben Goertzel speak about the work they're doing at Novamente. I like their approach a lot better (having an AI learn inside a virtual environment where it can actually see things, move around, and pick things up to learn about them, rather than just processing text), even though some of the conference turned out to be what I'd call fruitless speculation at this stage. No offense to Yudkowsky, but I think I'm starting to become more and more skeptical that "friendly AI" is fully definable, desirable, or ensurable.

PS: When I read Joan's comment about smarter than any man, I figured she might just mean the male portion of the species; she may just identify as an average, or even sub-par woman but feel that men are dumb. However, the judge interpretted it in a much more sexist way, as if the only realistic possibility was that the smartest human is a man. Then Joan gets led into agreeing with him. Quite an intriguing interchange, on many levels!


( 10 comments — Leave a comment )
Sep. 20th, 2006 08:09 pm (UTC)
Wow, that's a great conversation. I might post it to my AI blog...
Sep. 20th, 2006 09:20 pm (UTC)
fascinating. Thanks for sharing.
Sep. 21st, 2006 02:22 am (UTC)
You were at the AGI conference as well? Coolness. I'm annoyed I didn't know it was going to last until 7 PM; my ride showed up at 6 per the schedule I'd received beforehand. But the presentation was indeed fascinating. Lots to think about.
Sep. 21st, 2006 08:29 am (UTC)
yep... I was pretty annoyed at the 7pm thing too! I left at about 6:10, because I'd already told someone I was meeting her in Oakland at 7pm, and she doesn't have a cellphone.

So were you the one with green hair and a laptop? I was actually thinking to myself "I've seen her at another conference before... but where?" maybe it was just from lj!

Well, next time we're both at an event I'll be sure and say hi. I was sitting in the back left, my hair is getting kind of wild these days... at least compared to most of my lj pictures.
Sep. 21st, 2006 02:17 pm (UTC)
Yup, green hair + laptop = me. :) Were you also at the Human Enhancement Technologies & Human Rights conference at Stanford in May? If so, you could have seen me there. If not, you probably just recognized me from LJ. Small universe!
Sep. 24th, 2006 06:14 am (UTC)
Must have just been lj--you did have a couple pictures of you in your journal at one point. I hosted a Human Enhancement discussion with James Hughes here in Santa Cruz, but I didn't go to the Stanford one which was the same weekend.
Sep. 21st, 2006 04:14 am (UTC)
I think the best success will come from a combination of huge database of knowledge and "learning" AI. Sort of a top down and bottom up approach at the same time.
Sep. 27th, 2006 12:53 pm (UTC)
hello i am random

Judge: Is it possible for two plus two to not equal four?
Joan: I don't know. Do you think it's possible?

sounds like someone programmed an effing psychotherapist in there by accident.
Sep. 27th, 2006 05:04 pm (UTC)
Re: hello i am random
hi random... *waves*
Sep. 28th, 2006 02:05 pm (UTC)
Re: hello i am random
watch out for my wheelbarrow, mate. That's real cow dung in thar.
( 10 comments — Leave a comment )


domino plural

Latest Month

May 2017


Powered by LiveJournal.com
Designed by Lizzy Enger