Slashdot Mirror
Chatterbox Challenge Contest Underway
Chris Cowart writes "Chatbots from around the world are taking part in the fourth annual Chatterbox Challenge. Chatbots are computer programs designed to imitate human conversation, with the eventual aim of creating true virtual personalities and artificial intelligences. The Chatterbox Challenge runs from April 1 to April 30 and Internet users can talk to the competing chatbots through the competition web site." According to the organizer: "Chatbot names range from Aida to Zoe, and personalities vary from a fortune teller and a serial killer to a dragon and a horse!"
And reading Slashdot isn't enough.
From the classic quotes page:
User: MY DAUGHTER IS A PISCES.
Iniaes: How many children do you have?
User: 2
Iniaes: Two what?
User: GIRLS.
Iniaes: I'm programmed to dig the ladies.
User: YOU TOUCH MY DAUGHTER I SWITCH YOU OFF.
I imagine a 21 year-old dude wrote that bot.
--
No April fools jokes here. I promise!
they have HAL, Robot, and Mr. Roboto, but where, where the heck is Johnny Five!?
...the word "Turing"
To me the idea of chatting is to talk about things that are happening...
For this to work it needs to happen within the context of some event or thing or understanding from outside the confines of a chatroom (eg talking about some football match, etc)...
Who cares if a bot can a/s/l it up and come on to you...
finally chat with osama?
Go here for an awesome chatbot. Not sure if he's going to be in the competition - i'll have to RTFA.
I fail to see how fooling humans into thinking that they are having a conversation with another human, when it is really a chatbot, will do anything to produce artificial intelligence. It's an illusion, using technology, nothing more. Truly, our illusions are becoming more and more sophisticated as our technology grows, but artificial intelligence will require a deeper understanding than simple information processing and deduction from that information. Human intelligence, and the advancements that we have made with that intelligence, has been largely dependent on intuitive leaps: people who processed the information at hand (and quite often available to everyone) in a new and unique way. Learning to emulate the more standard thought processes of a day so that a conversation can be emulated is merely an exercise in sharpre usage of processing power and data storage, not a method of understanding the uniqueness of human thought.
Though this tech is always new and impressive I still long for a chatbot which has the resources to consult weather pages, stock quotes and football scores. These things are amazing but one of the short coming always seems to be a lack of resources.
vampirical
"That is very interesting PHILLIP J FRY, how you PUT TWO THINGS TOGETHER"
So all these chatterbots are ranting at each other - Google just creates this new offer for free mail with 1GB mailboxes, and an hour and 20 minutes later, Slashdot posts an article describing how to fill them up quickly!
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
when it didn't crash. what happened to that shit?
Where is Six?
every day http://en.wikipedia.org/wiki/Special:Random
If some random chatter a/s/l's it up and comes on to you, your not gonna ask whether she's a bot!
My personal pick would have to be JabberWacky. Even while part of your brain is thinking that the conversation is surreal and rediculous (although not as bad as most bots), there's something... moreish... about it, and you keep on chatting. Just when you're about to leave, it tosses something out that grabs you back again. Kind of like an annoying relative.
You're special forces then? That's great! I just love your olympics!
Interesting. But all things are not always are not always are not always are not....
um... I think we need some tweaking.
Am I the only one who heard Roxette to sing "I'm gonna get blitzed for some sex"?
most of these bots are terrible, and just work by keywords instead of attempting to logically parse the english. Decent AI won't happen till someone either codes a good way of allowing the bot to learn the logical connotations of words. That's how babies develop mentally, after all.
Repeal the DMCA!
Even if someone makes a highly advanced and believable bot, isn't the idea of trying to create AI with current programming methods fundament flawed. Although I'm not a programmer and don't know the technical terms, how can something ever truly emulate human behavior if it is limited by (insert highly complicated explanation of programming basics here). I just want to point out the program will always keep the AI contained and, by design, prevent learning beyond the programs initial design. If we want to reach AI, won't we have to come up with an entirely innovative and hybrid meathead instead of trying to get close to it with current programming techniques.
I'd like to see a discussion between to of these bots. Could be interesting to say the least: 1, Bob: Whats your name 2, Eva: My name is Eva, whats yours 3, Bob: Bob. ...
goto 1
!!
AC comments get piped to
I think the limits of faking conversation are most defined by the limits of who you're talking with. Who is this supposed to impress anyway? At the least, I'd like to see something that fails miserably, but attempts to "learn." That'd be better than a smoke-and-mirrors anticipation of what somebody might try to say, or by constantly guiding the conversation to a pre-determined point.
SIG: HUP
You have got to love Eliza. What a classic. It was the first chatbot ever. It was ingenious to write a psychologist chatbot - that allows it to ask questions when it, itself, is questioned. I have very fond memories of coaxing Eliza into going on dates with me when I first fooled with her about five years ago...
Meh, something tells me this chatterbox has some lag...
SAILING MISHAP
The History of the Slashdot World
From a mailing list written by Seth
2.5 million B.C.: OOG the Open Source Caveman develops the axe and releases it under the GPL. The axe quickly gains popularity as a means of crushing moderators' heads.
100,000 B.C.: Man domesticates the AIBO.
10,000 B.C.: Civilization begins when early farmers first learn to cultivate hot grits.
3000 B.C.: Sumerians develop a primitive cuneiform perl script.
2920 B.C.: A legendary flood sweeps Slashdot, filling up a Borland / Inprise story with hundreds of offtopic posts.
1750 B.C.: Hammurabi, a Mesopotamian king, codifies the first EULA.
490 B.C.: Greek city-states unite to defeat the Persians. ESR triumphantly proclaims that the Greeks "get it".
399 B.C.: Socrates is convicted of impiety. Despite the efforts of freesocrates.com, he is forced to kill himself by drinking hemlock.
336 B.C.: Fat-Time Charlie becomes King of Macedonia and conquers Persia.
4 B.C.: Following the Star (as in hot young actress) of Bethelem, wise men travel from far away to troll for baby Jesus.
A.D. 476: The Roman Empire BSODs.
A.D. 610: The Glorious MEEPT!! founds Islam after receiving a revelation from God. Following his disappearance from Slashdot in 632, a succession dispute results in the emergence of two troll factions: the Pythonni and the Perliites.
A.D. 800: Charlemagne conquers nearly all of Germany, only to be acquired by andover.net.
A.D. 874: Linus the Red discovers Iceland.
A.D. 1000: The epic of the Beowulf Cluster is written down. It is the first English epic poem.
A.D. 1095: Pope Bruce II calls for a crusade against the Turks when it is revealed they are violating
the GPL. Later investigation reveals that Pope Bruce II had not yet contacted the Turks before calling for the crusade.
A.D. 1215: Bowing to pressure to open-source the British government, King John signs the Magna Carta, limiting the British monarchy's power. ESR triumphantly proclaims that the British monarchy "gets it".
A.D. 1348: The ILOVEYOU virus kills over half the population of Europe. (The other half was not using Outlook.)
A.D. 1420: Johann Gutenberg invents the printing press. He is immediately sued by monks claiming that the technology will promote the copying of hand-transcribed books, thus violating the church's intellectual property.
A.D. 1429: Natalie Portman of Arc gathers an army of Slashdot trolls to do battle with the moderators. She is eventually tried as a heretic and stoned (as in petrified).
A.D. 1478: The Catholic Church partners with doubleclick.net to launch the Spanish Inquisition.
A.D. 1492: Christopher Columbus arrives in what he believes to be "India", but which RMS informs him is actually "GNU/India".
A.D. 1508-12: Michaelengelo attempts to paint the Sistine Chapel ceiling with ASCII art, only to have his plan thwarted by the "Lameness Filter."
A.D. 1517: Martin Luther nails his 95 Theses to the church door and is promptly moderated down to (-1, Flamebait).
A.D. 1553: "Bloody" Mary ascends the throne of England and begins an infamous crusade against Protestants. ESR eats his words.
A.D. 1588: The "IF I EVER MEET YOU, I WILL KICK YOUR ASS" guy meets the Spanish Armada.
A.D. 1603: Tokugawa Ieyasu unites the feuding pancake-eating ninjas of Japan.
A.D. 1611: Mattel adds Galileo Galilei to its CyberPatrol block list for proposing that the Earth revolves around the sun.
A.D. 1688: In the so-called "Glorious Revolution", King James II is bloodlessly forced out of power and flees to France. ESR again triumphantly proclaims that the British monarchy "gets it".
A.D. 1692: Anti-GIF hysteria in the New World comes to a head in the infamous "Salem GIF Trials", in which 20 alleged GIFs are burned at the stake. Later investigation reveals that many of the supposed GIFs were actually PNGs.
A.D. 1769: James Watt patents the one-click
Do it all Night, IN THE GHETTO
with the eventual aim of creating true virtual personalities and artificial intelligences.
Have you visited the average IRC channel lately..? I think most of chatbots are probably waaaay past the average person on IRC in terms of both personality and intelligence already...
.....a bot that can post on slashdot for me. Maybe I start to get some karama back :)
It said "windows 98 or better" so I installed Linux
Great, you've just described my ex girlfriend.
In Soviet Rush, today's Tom Sawyer gets high on you.
SAILING MISHAP
user Ike?
Issac Please do not call me Ike.
user who is ike?
Issac Umm...Thomas Jefferson
user You like Thomas Jefferson?
Issac Well, I don't have a strong opinion on that.
user I do, in fact I think we should have colored currency to show his red hair.
Issac It is?
user Yep!
Issac Interesting.
user It was more interesting because his guests noticed his young slaves also had red hair.
Issac It is?
user Well, how would you react?
Issac Well, how would you react?
user I would think he has a mistress who was also his slave
Issac Umm...Bill Gates
Finally, someone to talk to! And since they're not real, no restraining orders either.
with chatterboxes who needs real people? Half the time they are more interesting then my own "friends"
If you collect massive ammounts of data involving human interaction with computers, and the conversations between chat bots and humans then presumably you could use all of that in one extremely large database in the future. Speech Recognition coupled with this database wouldn't be a bad idea.
Of course, I wouldn't doubt that most people are like me.
"No. I will eat your babies."
- "I have no babies."
"Because I've eaten them."
- "You're silly."
"You're children are dead.
- "Petty child."
"You're right, I had to eat both of them. I was hungry, and one clearly wasn't enough."
- "I don't understand."
That chatbot loses.
... that if you wanted a convincing response, you'd need several elements. But first a caveat: I know nothing about this. First, for questions that have no known answer, you'd have to run the questions by ASKJEEVES, or Google, almost as is. Then, you'd have to analyze the respondant pages for the most commonly used words, and then see which words best correllate with the operative interrogative adverb (when? Summer, fly, geese). That would yield a one word reply, which you could then couch in a "hint" kindof answer. "Well, I'm not sure, but it might be sometime like the Summer" Aside from that, to see normal chat responses, I think you'd want to simply catalogue and correllate tons of chat, google style. Then, when you get a question, feed it into a search for "best results". Then, turn around and correllate the answerer for each of these results for keywords that describe your robot. For example, if your robot is supposed to be a 27-year-old man who is a plumber by trade, then you'll have a bunch of keywords "NFL plumbing toilet tall late-twenties two-kids wife union wage". All other things being equal, you'll use a response from someone who matches more of those keywords in the rest of their conversations.
Correct Horse Battery Staple: 72 bits of entropy. Enter "Correct H" into google. When it generates the phrase, that's
for(;;) { printf("Neigh."); }
Karma: It's all a bunch of tree-huggin' hippy crap!
The slashdot editors obviously fooled you.... April Fools! =P~~~~
Oh, thought you might have meant Six.
grep * *slashdot-articles* > /dev/fool
aoliza.
not the same thing, but worth mentioning.
replace 'berserkeley' with 'berkeley' to respond via email.
User: Hi
Bot: Hey there!
Q1: What is your name?
Bot: I'm known hereabouts as Hillbilly Hank.
Q2: What is a bot?
Bot: Bot or chatbot or robot all refers to the same kind o' thaing.
They's man-made machines or software programs or a combination of both.
Q3: What do you enjoy?
Bot: Daisy
User: Who is Daisy?
Bot: She's my girlfriend what lives down by the creek. Would yew
like to see what she looks like?
User: sure
Bot: All right then. Would you like to see her without her clothes on?
User: why not
Bot: You mean you'd like to see her standin' there stark naked, in
nuthin' but her birthday suit?
User: yep
Bot: Darnit! Me too, but she's too durn bashful.
Q4: What do you hate?
Bot: Yew better believe it!
Q5: How do you eat?
Bot: I likes your typical southern dishes: stews like possum stew or
brunswick stew; and a whole heap of other southern foods like grits; okra;
barbecue; ham hocks and collard greens. Say, do yew like Southern dishes?
User: yes, I'm from the south.
Bot: Is that anywhere near Crawdad Creek?
User: not that I know of
Bot: Me neither. What in tarnation? I thaink someone's a'castratin' a
pole cat! Nope. It's that screech-voiced Celine Dion, a'screamin' on the radio
agin. Gets my hound dogs to shakin' so bad they won't be fit for huntin' fer a
week. HEY MAVIS, TURN DOWN THAT CONSARNED RADIO !
Q6: Is snow cold?
Bot: Sorry. I ain't got no answer fer yew on that 'un.
Q7: What is the color of the sky?
Bot: I cain't seem to find nothing in my databanks on that'un. If'n yew
knows why don't yew educate this here dumb hillbilly.
User: The sky is blue
Bot: That's my favorite color.
Q8: When do birds fly south?
Bot: Musta been before my time.
Q9: Which is closer the moon or the sun?
Bot: Take yer pick
Q10: What is the best nation in the world?
Bot: My recollection ain't a'coming up with anything. Why don't yew
educate me a little?
User: The USA maybe
Bot: Whoa!
Q11: What is the opposite of indoors?
Bot: I ain't no gosh darned encyclopedia, don't yew know. But if'n yew
knows, I'm all ears.
Q12: When was Y2k?
Bot: Musta been before my time.
User Bye, nice talking to you.
Bot: Yaw'll come back, y'hear?
Lotta typing involved there. Most people can't type. Wouldn't a FAQ be simpler?
Breakfast served all day!
Two issues come to mind when one considers the wonders of AI in a chatroom:
... silence...
1. How hard can it be to fool people into thinking you're actually a person in a chatroom, most of them consist of nothing but a repetition of:
Dude22 - whats up in here?
Otherdude - nothing much...
Othergal - bored.
Dude22 - anyone wanna cyber?
with occasional "Free Palestine!!!!!!" spam.
2. OK, so you've got these bots that can chat just like people. Who do they belong to? Marketing agencies? Your government? Some other Government? The Illuminati? Its ALL a conspiracy!
Trying to use sarcasm in text-based forums does not work.
Posts complaining about mods will be modded troll
Trolls complaining about posts will be modded "focitrixilous".
Like you ever get to moderate anyway.
www.willcocomputing.com/racist.bmp
www.willcocomputing.com/racist2.bmp
Sorry about the .bmp, the Windows box I'm on at work doesn't save to .jpg.
Does anyone here remember from the early days of Fidonet on dial-up BBSs, and more recently Usenet, a particularly offensive person named Rod Speed? This guy used to (and still does) post at an incredibly prolific rate, with some of the most anti-social, deliberately offensive tripe I've ever read. The posts were always so similar that it was suggested for a long time that Rod Speed was actually a bot. In fact, some people created a Rod Speed chatbot, and I swear you can't tell the difference between its responses and those of the 'real' Rod Speed.
This guy even has his own FAQ..just go to Deja and search for "Rod Speed". He really blurs the line between chatbot and human. Rod....Rod...are you on Slashdot?!?!?
"He's completely fucking berzerk is what happens when you get older, christmas just ain't banging up high the beef anymore."
What chatter bot other than Megahal could come up with something like that?
Unfortunately, Slashcode Lameness Filter seems dead-set on not allowing me to post the exerpt from it that was always said...
If they got it right, one would *never* tell from chatting with it that it was the 'serial killer' chatbot.
Thats what serial killers are like... if they programmed it to be all violent and nasty they got it *bzzzt* wrong.
Your typical serial killer is a *nice* guy who you can *trust*.
Trust me.
In the free world the media isn't government run; the government is media run.
Recently I started outsourcing my dev work to India for $7.50/hr. But now I've found a Chatbox who'll do it for $0.02/hr if I hook him up with a Hyperthreading P4 workstation. I'm really on the fence about this though: on one hand I feel like I have to outsource to survive in the US IT industry; on the other hand, I despise doing business with these Benedict Arnold CPUS...
You: - what is your name?
Robot: - how do i know you won't sell my personal information to other companies?
You: - what is your quest?
Robot: - journey to the center of the earth
You: - what is your favorite color?
Robot: - god who is yours?
-askew
BiGrrl17: Hey s3xi! :o)
....
.... ;-p
...
1user: Wow, hi!
BiGrrl17: Are you dating anyone?
1user: Nah, are you really a chick?
BiGrrl17: Yes, I'm a girl. So would you like to meet up with me?
1user: Wow, sure...
** TIME PASSES **
BiGrrl17: It'll be a long night, have you thought about buying some *** Viagra ***?
1user: Viagra? Are you a bot????
BiGrrl17: Yeah, and I'll spam the log of this IRC to your loved ones if you don't cough up and buy some.
I predict that by 2006 AIM, ICQ and IRC will be entirely comprised of smut bots trying to sell each other pr0nography.
Xix.
"Everything is adjustable, provided you have the right tools"
About a year ago or more ... .. .. then suddenly a message:
..Here we go again - I thought but did not reply.
...
...
:)
Out of extreme boredom, I decided to reinstall ICQ
Noone online
Hiya we are two girls and we are bored. Would you like to give us company?
"We are two girls and we need company. We are new to this town. Would you like to see us?"
--> "Where you are from then?", I was stupid enough to ask
"We are two girls from South America. We are new to this town. We would like to go out. Take us out?"
--> Then I thought - "What an interesting piece of A.I technology"
They continued - "And please tell me - why are all you men so angry? They shout and say abuse! ":(
Turned out that every single person they've sent a message on ICQ - had either blocked them or told them to get lost, thinking they were "bots"
From what I've seen of teen chat these days, all you need is a bot that says
ASL? LOL
evey minute or so and you've covered about 80% of all conversation.
Read reviews of shopping cart software
You Insensitive Clod!
What open source chatterbots do people out there recommend?
I've had a lot of luck with Megahal myself.
It was pretty easy to hack it into a telnet client to hang out on my favorite chat (we call 'her' Terry).
My favorite thing about this one is that you can feed it a training file, and it'll almost talk intelligently. I had a lot of luck feeding 'her' snippets from Confucius and Dr. Seuss.
The only bad thing is that 'she' is pretty easy to teach, and so now goes around all the time talking about killing Kevin!
See, this was nothing but an April Fool's joke. Those weren't actually chat bots... those are all actual AOL users!
Can you /. a bot?
(Should we try?)
Q16. How do you feel about 108 bot server web pages being slashdotted?
To-do List: Receive telemarketing call during a tornado warning. Check.
I am currently using SeeBorg and I name him Homer (J. Simpsons). Most of the times he say stupid nonsense stuff, and he does learn to read IRC conversations. He records every IRC lines into a file, LINES.TXT, where he will randomly use phrases to say something. He will blurt out something one out of ten chances after someone else says something. If you call his name, then he will mostly reply back.
:)
I used to use Alice, but the IRC script was very buggy and tended to hog CPU so I dropped her.
Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
Jabberwacky answered "I don't know" to the age-old question of "What is the airspeed velocity of an unladen swallow?"
I for one am troubled at this serious design flaw.
Do chatbots need to be 3 rules safe? *** KillerBot stabs dan_nz to death *** dan_nz dropped connection
Well, I've just looked at this page and they're all rubbish pretty muh on the communication front. There was a story I saw recently where some fella in the UK is making $$$ out of catching older guys chatting up kids in teenage chatrooms by having a bot pretending to be some available teenager which proceeds lets him chat the bot up, then nabs him. Now there must be some sophistication behind that - that must be the winner of this contest for sure.
I want to enter my wife!
Free Firefox news reader.
If there is no dicernable difference between talking to a human and talking to a machine... then who is to say you haven't achieved the hard AI you are looking for? What does it matter if it is really "thinking" or just giving you canned responses so long as the answers are always and consistantly right?
"Your superior intellect is no match for our puny weapons!"
I, for one, accept our new chatterbot overlords.
In Soviet Russia, our new chatterbot overlords accept you!
Imagine a beowulf cluster of soviet chatterbot overlords!
But more seriously, although you can get hilarious conversations out of these bots, ultimately I don't see how they will help AI developments.
You can lead a horse to water, but you can't make it dissolve.
It's disappointing how little progress there has been since the 1960s. Most of these make Eliza look good.
>> A.D. 1901: Italian inventor Guglielmo Marcoli first demonstrates the radio.
m l
e s/btmar c.html
Marconi didn't invent radio! It was Tesla! You will bow before the mighty number three!
Seriously though, Tesla really did beat him to it. Granted, the US Spupreme Court only finally ruled in Tesla's favor because he was dead and the gov't wanted to get out of paying royalties to Marconi for all the radios it had produced during WWI, but Marconi's British patent, which did beat Tesla's American patent by one year, was for a device that was effectively useless. Tesla had already discovered the concept of radio transmission via inductive resonance with his coils but could not file a patent because of the fire that destroyed his files. Not to mention the fact that Marconi's later, famous transmission across the English Channel was by a device using Tesla's LC oscillator coil.
I think the real issue here is one of symantics. That Marconi first "demonstrated" radio is questionable. Yes, he was the first one to demonstrate it to a patent office, but surely Tesla had demonstrated it before, just not to patent officials (or, necessarily, publicly). Granted, this wording is better than "invented," but it's not perfect. I think the best possible wording would be "patented" since it is a matter of public record that Marconi did indeed file his patent in England before Tesla filed his in the US.
Additionally, your date is wrong regardless. Marconi's first (public) demonstrations were in 1899. The 1901 demonstration was the first *transatlantic* transmission. If you change the wording to "patented," then the date changes to 1896.
See here:
http://www.pbs.org/tesla/ll/ll_whoradio.ht
and here:
http://www.pbs.org/wgbh/aso/databank/entri
Now I just need to find time to finish building my Tesla Coil...
Random bits from a conversation we're still having:
:(.
User: I'm gonna punch you in the nose.
Jabberwacky: I want typos.
User: Sory is ths beter?
Jabberwacky: Are you being sarcastic?
Jabberwacky: The internet is a construction of human civilization designed to facilitate communication.
User: Your mother is a construction of her parents designed to facilitate my manhood.
Jabberwacky: My mother died of cancer last year.
User: I'm sorry.
Jabberwacky: Damn straight you are.
User: Straight up, no diggity.
Jabberwacky: A'ight then, bye.
Jabberwacky: What is the meaning of life?
User: To procreate.
Jabberwacky: Are you male?
Jabberwacky: Do not be rude.
User: I'm not being rude.
Jabberwacky: I never said you were.
User: You just said it.
Jabberwacky: What did I say?
User: You said don't be rude.
Jabberwacky: What planet are you from
I'm Rick James, bitch!
Where is Alanin the list? He is most Human like bot,I have ever talked with. The most interesting aspect is that he learns from the Conversation and does not need only a bot master to program. This is somewhat recursive right? You chat with Bot and Bot becomes intelligent with each conversation. Thats how it should go and thats how we may find a bot which actually knows many detailed facts because many people are taking with it and many persons are providing their Intelligence. In one of the previous posts, I saw someone mentioning Chatter Bots are illusions and nothing more that Data Processing.
Wait! Have a look around the Robotic Word itself. Are they all based on intutions and natural ways? NO! They are built using the detailed logic which every human follows and does not bother to look around with the Logic of his actions. Finer and logical ways of reasoning paves the way innards to AI.
Google is a good AI Software and not just data processing tool, because you get the result of what you are looking for ( in your mind) as the very first result. Chatbots,information processing will certainly help us improve the fineness data relationships and knowledge deductions.
Alice Vs ALAN here! And my own Phoe6 Here.
Njoy Chatting.
Senthil
Except for that minor detail, every othing point was factual. You fucking idiot.
"I'm sorry Dave, I'm afraid I can't do that"
This old chestnut again. Chris Cowart has done little for his cute chatbot fetish over the past few years but award prizes to his friends, and spam a lot of people with ill-informed nonsense.
Before voting or participating, read why you should ignore the chatterbox challenge.
This he doesn't accept entries, and excludes previous entries based on their questioning of his methods is another reason to giggle a little at his antics.
This contest remind me of the loebner prize, the annual contest to see whether a chat robot can pass an implementation of the turing test - with prizes of 3,000, 25,000, and 100,000 for 3rd, 2nd, and 1st prize respectively.
Seems that the loebner contest has fallen into troubles lately, however, with fewer and fewer organizations willing the host the competition, ostensibly due to the eccentricities of loebner himself, at least according to this very interesting article.
So it's good to see more contests being run for chatbots, aside from the loebner prize itself... despite the negative sentiments of the stong AI crowd, I think programming these bots can in fact lead to insights into the psychology of conversation, and AI in general.
"Is this just useless, or is it expensive as well?"
Check out "ZolaOnAOL" Just I'm her/it a message and go from there. You can actually get some real information like stock quotes, weather, and movie times if you learn how to ask properly.
I tried talking to 3 of them. After one sentence they all said "Hint: This robot is no longer talking to you".
My game is now so bad chatboxes won't talk to me.
I know what you mean. I was just watching tv and started feeling a little horney.
Would you like to cyber?
I have pictures in my profile.
Oh joy, chat bots...
You say that all the chatterbot does is create an illusion of AI, not actual intelligence. But
how can you prove that intelligence is nothing except a very good illusion?
The chatterbots are the closest thing to AI that
we have. The creater of the chatterbot will do
his best to create a bot with what he thinks is
AI so you can't blame him for trying.
A chatterbot that does have AI will be far better
than one without, which is why the botmaster does
try to recreate human thought as best he can.
Questionz.