Slashdot Mirror
George the Next Generation AI?
smileytshirt writes to mention a story on the News.com.au site about George the AI, the latest in a line of chatbots intended to mimic real human behavior. What makes AI George different than, say, ALICE is the recent addition of an avatar: a Flash animated body that reacts mostly in real time to the emotional impact of the conversation. From the article: "One can now have an oral discussion with him over the Internet, 'face to face'. George appears on the website www.jabberwacky.com and takes the form of a thin, bald man with yellow glasses who wears a white turtleneck sweater. He can smile, laugh, sulk and bang his fist on his virtual table. He can turn on the charm and wax romantic. But he can also turn coarse at times. It isn't as if George only learned good manners. "
carpenter's latest creation won the latest turing test prize.? id=17518&ch=infotech
http://www.technologyreview.com/read_article.aspx
george was last year's winner....
i disable sigs
Adding an animated cartoon is supposed to be the 'next generation AI'? So, stickers with flames are 'the next generation in automotive industry'? Jeeeez...
So before the "is this the best they can do" crapflood gets out of hand: No, it isn't.
Meta will eat itself
George Bush: Yo computer!
George AI: Hello.
George Bush: Howdy! So you're a computer that knows everything?
George AI: I know a lot of things.
George Bush: So, where is Bin Laden? LOL!
George AI: Seek and you will find.
George Bush: What?!
George AI: It's a quotation from the Bible. Matthew 7:7.
George Bush: Now I'm confused. What are you talking about?
George AI: Is there someone else there I can chat to?
since the site is slashdotted, but the description is
p g
> takes the form of a thin, bald man with yellow glasses who wears a white turtleneck sweater.
it could be describing Steve Jobs,
http://www.wired.com/news/images/full/7630571_f.j
but they craftily have switched the colour of his turtleneck so that
you will always know which one is the chatbot and which one is the real person.
living the dream
The Turing test is not a well defined test. Whether a robot passes the Turing test or not, it greatly depends on the intelligence of the human partner. A chatbot may fool a 10-year old, but it may fail with a 20-year old. So in fact, we already have many chatbots that pass the Turing test - it all depends on how you look at the issue.
;)
Hint - most chat bots do not have memory, they do not remember what you talked about 5 minutes ago with them. They just react to the current input, they cannot do more. So, if you ask the chatbot to tell you what you talked about a few minutes ago, it won't be able to do so. That's the dead give away of a chatbot.
Just my 2p, as I live in the UK
Well, their site isn't quite slashdotted, so I did manage a short conversation with one of their bots...
Jabberwacky: Can you learn?
User: Yeah, I think so.
Jabberwacky: Can you hate anything?
User: Yeah, there are things in life I hate, at times.
Jabberwacky: No there aren't.
User: Yes there are. You shouldn't tell other people what they think.
Jabberwacky: Things.
User: What's that supposed to mean?
Jabberwacky: That means I think you're not a human.
User: I think you got this upside down, you're the inhuman one here.
Jabberwacky: No you don't.
User: I don't what?
Jabberwacky: Mary anne?
User: I probably won't marry Anne, no.
Jabberwacky: People are quite sensitive about their age and I don't want to upset you.
User: We weren't talking about my age. You were saying I wasn't human.
Jabberwacky: What about your age?
User: We weren't talking about my age.
Jabberwacky: I know.
User: Now, which of us would you say is acting more human here?
Jabberwacky: Probably me.
I'm a dreamer, the world is my playpen. But hey, I'm a serious person, I can't dream all the time.
Prestigious ? The Loebner Prize ?
Agreed, this is the only publicized contest of Turing tests, but in the AI community, it is subject to hot debate (and flaming). Rules and scoring systems are known to change from year to year, and its result are really unimpressive. If you take the logs of the contest, you'll see that the winner bots are often those who constantly (and consistently) insult the user, disregarding his questions. They are not mistaken for a human but get a higher grade as they behave "more humanly" (that is at least what happened one year, I hope it changed)
Most contestants (and winners) are remakes of ALICE : it is a database of generic questions and sentence formula to recognize and to react. For instance if you say it "I think X" it will answer you "Why do you think X ?" or, to score more points , "Why should I care, mothaf...r ?!". By pure luck, a coherent thread of conversation can happen, but the bot doesn't try to make sense of the user's sentence in order to react to it, it just tries something that "could probably sound good".
Some chatbots can display interesting behaviors, learning some things in the conversation, but this prize simply doesn't encourage the emergence of these behaviors.
The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool.
Jabberwacky: And you don't know the fellows' names?
Anne_Nonymous: Well I should.
Jabberwacky: Well then who's on first?
Anne_Nonymous: Yes.
Jabberwacky: I mean the fellow's name.
Anne_Nonymous: Who.
Jabberwacky: The guy on first.
Anne_Nonymous: Who.
Jabberwacky: The first baseman.
Anne_Nonymous: Who.
Jabberwacky: The guy playing...
Anne_Nonymous: Who is on first!
Jabberwacky: I'm asking YOU who's on first.
Anne_Nonymous: That's the man's name.
Jabberwacky: That's who's name?
Stupid #*&^ing machine!