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!"

Comments

Alan - The Great AI Bot

[Anonymous Coward]

Go here for an awesome chatbot. Not sure if he's going to be in the competition - i'll have to RTFA.

My personal pick....

[rjstanford]

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.

Re:Chat between bots?

[Anonymous Coward]

They actually can hold a conversation, although the topic tends to stray very, very quickly.

I like Fred

[focitrixilous P]

He's a forum bot over at Wackiness.org, you send him personal messages and he replies with some sense. If you post at the forums with Fred as the first word, he will rehash your question, along with random phrases from all your posts at the forum, into a semi-sensical statement. Fred 2.0 is my favorite chatterbox. I even wrote some stories about his secret internet life. I leave you with the best of Fred:

Is the short skirts attractive females tend to wear a hard subject?
Do you think I am gonna find out THAT too?
Gee. What, I you am goop it?

Re:Nice

[Trejkaz]

AliceBot would have been able to do it. It was designed for integration with information bases and you could put scripts in as part of your customisation. One of these scripts could easily fetch from Yahoo, parse the page, reword it in English and speak it out.

Re:I fail to see

[mrogers]

While I was studying natural language processing I read an interesting book in which Horst Hendriks-Jansen describes how, during a child's development, intelligent behaviour is built on a "scaffolding" of instinctive behaviour. For example, adults treat babies as intelligent, purposeful beings who are aware of their surroundings - we've all seen new parents interpreting baby's every burp and grimace as an attempt at conversation. In reality, most of a baby's actions are instinctive, and often unrelated to the people it's "interacting" with, but adults nevertheless feel a strong urge to respond and comment, keeping the false interaction going.

Hendriks-Jansen argues that this misunderstanding allows the child to "bootstrap" itself into genuine interactions, by learning from the intelligent responses to its semi-random behaviour. Fast forward two years and there's undoubtedly interaction, but most of the meaning is still interpreted by the adult rather than supplied by the child - "Go park" "Do you want to go to the park today?" "Ey say mf aw sheep" "Do you think we'll see sheep at the park? What noise do sheep make?"

What relevance does all this have for AI? If the "interactive emergence" theory is correct, computers will only become intelligent by learning to interact - bootstrapping themselves from semi-random actions, interpreted as meaningful, to genuinely meaningful interactions. This will only be possible if people have the patience to play with bots and teach them to interact, and since the urge doesn't seem to be as strong with bots as it is with babies, and the interaction starts with text rather than gurgles and winces, it will help if the bots have enough "instinctive" (ie hardcoded) conversational skills to encourage people to keep playing.

Open Source bots

[fear025]

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!

Re:Rod Speed, the ultimate Usenet chatbot

[oingoboingo]

Here's the link to the Rod Speed chatbot.

Rod Speed Chatbot

loebner prize

[blue_adept]

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.