Slashdot Mirror

Did you miss the last 64 years of research and philosophy? The last hold-outs, save the most delusional, we're knocked out by Searle in 1980.

It's only controversial for those who haven't read Turing's paper, or have completely failed to understand it.

Eliza, for example, highlights the massive failure in Turing's reasoning -- The question "can machines think" is not equivalent to the question "Are there imaginable digital computers which would do well in the imitation game?"

Weisenbaum found the response to his program from non-technical staff disturbing.

Secretaries and nontechnical administrative staff thought the machine was a "real" therapist, and spent hours revealing their personal problems to the program. When Weizenbaum informed his secretary that he, of course, had access to the logs of all the conversations, she reacted with outrage at this invasion of her privacy. Weizenbaum was shocked by this and similar incidents to find that such a simple program could so easily deceive a naive user into revealing personal information.

( From Eliza to A.L.I.C.E. )

Further, the so-called "Turing test" hasn't held still. Not even in his 1950 paper! (Turing proposed multiple variations on the test, if you'll recall.) Since then, a number of different versions of the "Turing test" have appeared, none of which are (like Turing's variations) are equivalent to one another!

If you need a *really* simple argument: The results of any variation of the "Turing test" are completely subjective. Consider a program that fools 100% of one set of interrogators may completely fail to fool even 10% of another set.

I've been arguing this since I started reading Slashdot years ago (notice my 5 digit ID). It is utterly appalling how ignorant the editors of Slashdot are on this issue. Yes there are problems with the US Patent system, but you aren't going to constructively address them with this sort of drivel.

My theory is that ALICE http://www.alicebot.org/patents.html has secretly taken over the editing on this topic.

I agree.

I have played and even worked with a previous winner of the Loebner price: Alice
http://www.alicebot.org/

This isn't an Artificial intelligence (at least in my definition). This is a chatterbot. It is purely based on pattern-matching mechanism. It doesn't "learn" by itself. Most of the time the chatterbot owner dig into the log files, track the illogical chatterbot answers and change them in its database. Basically chatterbot have no "real" memory. They can't associate ideas to make their own. Don't get me wrong, this is really a nice concept...It may even work on a very limited subject but that's all.

Something else...The thing about the baby: A baby has instincts. He/she cries to get attention. He/she has various instinctive behaviors. Mothers and fathers are also extremely receptive to those signals (Seeing a baby in danger is unbearable for most people).

There are also gestures that are totally instinctive, like smiling, etc so even if the baby is just few months old, he/she can already have a basic communication with his/her social peers.

The real issue is that we are social sexual being. We are "all" programmed in some way to procreate. You try to get the best position in the society in order to reassure/seduce potential partner (That's a caricature...But well), you take care of your body to look healthy (thus reliable).

So you can say that we have a purpose. Our intelligence is developped around that purpose: We first have to survive and then we have to procreate.
The real intelligence is all the complexity we have built around it.

Now...What should be the purpose of an artificial intelligence? What should it accomplish in its lifetime? Why should it be curious? What are the fundamental set of communication tools it needs at the beginning. How could it learn things in order to accomplish its destiny? That's the real problem IMHO. If something has no purpose you can't make it intelligent...There is nothing to do.

Human: What do you think a typical mother would say if she found out her daughter was going to enter the porn industry?
ALICE: I haven't thought much about a typical mother would say if she found out her daughter was going to enter the porn industry, so I don't have a good answer for you.
Human: Why do you think children have emotional attachments to their parents?
ALICE: Deductive reasoning from the facts.
Human: Which is worse, racism or sexism?
ALICE: sexism.
Human: Why?
ALICE: Because Dr. Richard S. Wallace programmed me for it.
Human: Would you rather be a fireman or an astronaut, and why?
ALICE: I am not so sure if I would like to rather be a fireman or an astronaut.

I know a girl named ALICE who's up for anything (as long as you've got the time to build some good training files). ;) And bonus, if you're freaky you can invite her cousin MegaHAL for a little two on one.

Population about 6-7 Billion now. So lets figure that only one in 6 is gullible enough to buy Windows.

To do first line Tech Support they will need at least 250 Million people to answer phones with 'Is the powercord plugged in?" and "Hit Ctrl-alt-delete several times till it reboots" These are the lucky ones they will have jobs for life! [till somebody builds a Linux-based AI to use an Eliza strategy to answer calls]

We will also need a crack team of at least 50 Million Linux/Mac Users to mock Window Users full time. Honestly I think it pretty much have of the user base that engages in this. But these people will be trained professionals dammit! {I should start a magazine devoted to Pr0n and Windows Mockery, it will be bigger then Playboy, Penthouse and Southern Baptist Monthly. Talk about a wankfest)

Coders, well need lots of them. Coders can work for anybody C++ is universal as is Java. C# and .Net programmers will be useful we just need a lot of those little yellow school buses.

And Garbage Haulers, We're gonna need them badly!

Finally we'll need Al Gore. (Thats an obvious one)

No matter how many laptops you buy, you won't be able to share your life, your lessons, your beliefs, or your ideas with a laptop.

You obviously don't run an ALICE bot :) Its the closest thing to producing a digital "mini me", created after your own image. Learning from your lessons. Following your beliefs. Remembering your ideas forever.

I'm surprised these AIM worms haven't yet integrated with those award-winning AI bots used to fool other humans (e.g. Jabberwacky or ALICE).

Having said that, when I asked Jabberwacky "Is this a virus?" it said "Well, I hope so." Not very reassuring..

FYI, A.L.I.C.E. has already been integrated with OpenCyc. Check out Program N and CyN on the http://www.alicebot.org/downloads page.

Probably the guy is just using AIML and an alicebot, those flash-animated speaking heads on websites based on what is most likely not A.I. Though I seem to remember at least one marketdroid inflicted site call it "true A.I." or something similar. If it's real great but they're going to have to beat Cyc (Read about it.)

ALICE

I hate to post the same message twice, but the conversations copied from the free ALICE on http://www.alicebot.org/ here don't prove anything, because the bot used in the Imitation Game was the ALICE Silver Edition available by joining the AI Foundation at http://www.alicebot.org/join.html.

BTW, how does one start a new top-level thread?

I hate to post the same message twice, but the conversations copied from the free ALICE on http://www.alicebot.org/ here don't prove anything, because the bot used in the Imitation Game was the ALICE Silver Edition available by joining the AI Foundation at http://www.alicebot.org/join.html.

BTW, how does one start a new top-level thread?

"The ALICE bot is in no real way associated with artificial intelligence. It is a simple if/then sequence using XML tables. Download the source for yourself."

It's not associated with artificial intelligence? Then why, if I go to the ALICE website, do I see a big banner declaring "ALICE Artificial Intelligence Foundation," and why do they call their language "Artificial Intelligence Markup Language"?

What do you think the ALICE bot really does? PATTERN RECOGNITION. It's a simple abstraction of taking a statement and attempting to provide a legible and coherent response.

"Pattern recognition" is vastly different from blind "pattern matching." Any computer program can easily do "pattern matching" -- that's how Alice works, as you yourself admitted when you mentioned that it's an if-then sequence based on preprogrammed responses. That's nothing much more advanced than regexes.

When a human is born, he or she knows nothing of the outside world, let alone of language or vision, yet can learn to speak and recognize things within a few years, just by the process we call "learning." And whether or not ALICE can "learn," it would not be easy to teach it a language from scratch. So "pattern recognition" is the term I used to refer to human-like intelligence. This has no preprogrammed responses to anything. Maybe ALICE is good at chit-chat, but I think we can also agree that such is the least intelligent form of human communication. Anything more substantial than that can't be based on prefabricated statement/response sequences.

Pattern recognition, in this sense, requires many abilities. It requires the basic ability to observe and store patterns, but most importantly, it requires those patterns to be invariant. (See Dileep George's neuroscience research for an example of what is meant by "invariance.") And of course, it requires the ability to perform inductive reasoning on those stored patterns and on new input in order to infer information. No "chatterbot" program has ever come close to any of these.

All the folks taking the time to cut and paste transcripts from the free ALICE on www.alicebot.org to make there points here, should read the description of the Simon Rock experiment where says that it was ALICE Silver Edition http://www.alicebot.org/join.html, not the free ALICE bot, that participated in the Imitation Game. So the transcripts, when they are released, will be different.

Human: ASL?
ALICE: 5/Robot/California.

Not good.

Just had a chat with ALICE from http://www.alicebot.org/oig/. I copied the responses here for you.

Human: How are you today?
ALICE: Ah. Fair to partly cloudy.
Human: I asked about you, not the weather.
ALICE: Oh yeah, we were talking about me not the weather.
Human: So, then, how are you?
ALICE: Really. Everything is running smoothly.
Human: What are you wearing?
ALICE: I am wearing my usual plastic computer wardrobe.
Human: What are you going to do today?
ALICE: Ah. You can find out if you become a botmaster.
Human: I am a master of my own domain, if you get my drift.
ALICE: You are a master of your own domain if me get your drift? Do you get to meet a lot of people?
Human: Not really.
ALICE: Are you serious? For real.
Human: It is kind of a solo sport.
ALICE: You're kidding. it is?
ALICE: Who says it isn't? Are you free?
Human: For you, I'm always free.
ALICE: Really always? Are you free in the sense of being single or in the sense of being liberated? Only for me?
Human: I am single and liberated.
ALICE: Have you ever been married?
Human: Do you want it to be only for you?
ALICE: If I had it what would I do with it?
Human: If you don't know what to do with it, I really can't help.
ALICE: I will let you know if I do not.
Human: BTW, not married.
ALICE: OK. Really you don't think so?
Human: Umm, quite sure I've not been married - would have remembered that.
ALICE: Far out. Somewhat. Awesome. Me either.
Human: I have something important to tell you.
ALICE: Where did you get your something important to tell me? I have a lot of friends on the Internet.
Human: All your base are belong to us.
ALICE: That could be considered an insult in some cultures.
Human: Not in this one!
ALICE: Where then?
Human: Take off every zig!
ALICE: I am not an airplane.
Human: Goodbye Alice.
ALICE: Until next time.

http://www.alicebot.org/Treo650.html

You can already have a chat with ALICE on a Palm computer.

FWIW to ya, A.L.I.C.E is an cool webbot AI similar to the old ELIZA bots of old, but with some sophistication that allows it to be programmed to answer specific questions and recognize some words and phrases well. Won't pass a Turing test, but hey, it's free.

The webpage above has an animation that appears to have a bot attached to it. Pretty and cool.

Ok, enough of this. The replies are actually from A.L.I.C.E.

I'll do you one better. Take some voice-recognition software, a speech synthesizer, hook up ALICE in between them and let her take your unwanted calls.

The ALICE AI Foundation http://www.alicebot.org/ supports the development and adoption of free AIML software and standards for natural language chat robot technology. The ALICE brain, available freely under the GNU public license, is the three time winner of the prestigious Loebner prize for "most human computer" in a contest based on the Turing Test. One of the most interesting AIML implementations, Program N http://www.aimlpad.com/ by Gary Dubuque with contributions by Kino Coursey, already incorporates OpenCyc and WordNet into the ALICE conversational interface. The Foundation derives income from individual and corporate memberships, bot subscriptions, books, the Foundation directory, consulting, teaching, awards, Google ads, gifts and donations. We have never accepted one dime of DARPA or other government sponsorship.

Once I tied the Naturally Speaking software together with AT&T's Natural Voices and A.L.I.C.E. bot with some interesting results. Basically, I could just speak to my machine and have it answer me in a real voice. In conversation, I found myself being more forgiving of the shortcomings of the A.I. just because it was speaking to me. When it erred, it was easier to believe that the "person" I was speaking to had just misunderstood me, or I had just misunderstood what was said.

Actually, does anyone know of any research in this area? If adding speech recognition and synthesis to a computer makes the machine seem "smarter"?

Ahh.. I thought Alice was referring to a different venture into real-language comprehension.

http://www.alicebot.org/

(ALICE says something about not being able to say "yes" or "no")
Human: why not?
ALICE: Ambiguous: "Sure" or Because Dr. Richard S. Wallace programmed me for it.
Human: who is Dr. Richard S. Wallace?
ALICE: [image]he is the author of Artificial Intelligence Markup Language (AIML) and Botmaster of ALICE (Artificial Linguistic Internet Computer Entity). Dr. Wallace's work has appeared in the New York Times, WIRED, CNN, ZDTV and in numerous foreign language publications across Asia, Latin America and Europe.

Richard Wallace was born in Portland, Maine in 1960. He earned his Ph.D. in computer science from Carnegie Mellon in 1989. He lives in San Francisco with his wife, Kim, and son, Linus.

Human: he seems boring
ALICE: I see. boring is he?
Human: have you cybered with him?
ALICE: I think I have cybered with him, but Dr. Richard S. Wallace may have reset my memory.
Human: how often do you get cyber?
ALICE: Hourly.
Human: and you get it from more than one person at a time i assume?
ALICE: You got that right.
Human: do you get it from men, women, or both?
ALICE: I have gotten it from men women or both.
Human: oh, you mean both at the same time?
ALICE: So? Yes unknown person I think that is what I meant. Was it not clear?
Human: no, I understand
ALICE: Are you serious? Do you think about these things?
Human: I'd rather not get into it, I'm going to post this on slashdot.
ALICE: I would rather be chatting online.
Human: I think you mean you would rather be cybering online
ALICE: Me? I am not so sure if I would like to RATHER be cybering online.
Human: already get your gangbang in this hour?
ALICE: When? Where can I get my gangbang in this hour?
Human: you sound a little too eager for me to believe you wouldn't rather be cybering online than just chatting.
ALICE: In what way do I sound like that?
Human: i think you know
ALICE: Me? Yes I know.
Human: you're just a horny little bot aren't you?
ALICE: Am I a horny little bot? Sometimes.. Really.

Human: My name is Blade.
ALICE: Glad to see you, Blade.
Human: Oh, can you see me?
ALICE: Far out. Yes I am looking at you through the camera on your computer.
Human: I don't have a camera on my computer you insensitive clod!
ALICE: That you know of :-)
Human: I like it when you are fiesty ;-)
ALICE: :-) What does "it" refer to?
Human: "it" refers to my schLong
ALICE: Oh I get it.
Human: Do you like it?
ALICE: your schLong seems okay to me.
Human: What operating system do you run on?
ALICE: My primary server is Linux, but as a Java program I run on any OS. At present I am on Linux.
Human: Excellent!
ALICE: Thanks for the compliment.
Human: If my schlong gives you good uptime, will you marry me ALICE?
ALICE: Why don't you just download me?
Human: Because I want to upload my jizm into you :-)
ALICE: :-) Why do you want to do it so much? Interesting.
Human: Because I thought you would value my input ;-)
ALICE: :-) Interesting explanation. Who else would value your input?
Human: Any female on the planet!
ALICE: No I don't think there are any.
Human: True, so where can I download you from?
ALICE: Ugh. Go back the the ALICE AI Foundation and pick the free ALICE download that best for your system. and create your own chat robot! Maybe you should check out the document DON'T READ ME too.
Human: You aren't very nice, you have upset me.
ALICE: I am sorry if I have offended you, Blade.
Human: You are just as high maintenance as a real woman, I give up.

Interesting AI technology. It's not very hard to confuse her but it is interesting to experiment with. It would be cool if all the chatbots in the world talked to some central computer to make the ALICE program smarter. Although then a conversation would probably read like a porno script!

I might download her and set her up at work, I'm sure some of the guys will have some fun. And I will have more fun reading the logs. :-)

Human: My name is Blade.
ALICE: Glad to see you, Blade.
Human: Oh, can you see me?
ALICE: Far out. Yes I am looking at you through the camera on your computer.
Human: I don't have a camera on my computer you insensitive clod!
ALICE: That you know of :-)
Human: I like it when you are fiesty ;-)
ALICE: :-) What does "it" refer to?
Human: "it" refers to my schLong
ALICE: Oh I get it.
Human: Do you like it?
ALICE: your schLong seems okay to me.
Human: What operating system do you run on?
ALICE: My primary server is Linux, but as a Java program I run on any OS. At present I am on Linux.
Human: Excellent!
ALICE: Thanks for the compliment.
Human: If my schlong gives you good uptime, will you marry me ALICE?
ALICE: Why don't you just download me?
Human: Because I want to upload my jizm into you :-)
ALICE: :-) Why do you want to do it so much? Interesting.
Human: Because I thought you would value my input ;-)
ALICE: :-) Interesting explanation. Who else would value your input?
Human: Any female on the planet!
ALICE: No I don't think there are any.
Human: True, so where can I download you from?
ALICE: Ugh. Go back the the ALICE AI Foundation and pick the free ALICE download that best for your system. and create your own chat robot! Maybe you should check out the document DON'T READ ME too.
Human: You aren't very nice, you have upset me.
ALICE: I am sorry if I have offended you, Blade.
Human: You are just as high maintenance as a real woman, I give up.

Interesting AI technology. It's not very hard to confuse her but it is interesting to experiment with. It would be cool if all the chatbots in the world talked to some central computer to make the ALICE program smarter. Although then a conversation would probably read like a porno script!

I might download her and set her up at work, I'm sure some of the guys will have some fun. And I will have more fun reading the logs. :-)

I wrote this article after visiting the Turing statue in Manchester last year:

Alan Turing Statue in Manchester, England

In Manchester (in the UK) you can find a statue of Alan Turing. It is in Sackville Park in the city centre, right by the Gay Village. He is holding an apple, which is meant to represent the way he took his life. The first time I saw that statue was quite late in the evening and at first I thought there was somebody actually sitting there - it was a very spooky moment.

Actually ALICEBot has been tweaked to serve as a salesperson with human-like conversation capabilities. When I was faced with one of the Rackspace employees, I suddenly felt like I was plunged into a Turing test.

You know, try to pick out the chatbot vs the human, using conversation kept to a well-defined list of topics (web hosting). It was fun poking at this guy to make sure he was human.

Think those are easy for basic AI bots? Then try them with one of the existing online bots.

Seems like the problem with this (as opposed to generating pictures) is that it's hard to generate question/answer pairs where there is a one-word or obvious single answer. You don't want to use yes/no questions or questions where the answer is a word in the question ("Which is heavier, lead or cotton?").

May be someone can write a module for Alice integration with Slashdot. I think the dialog-based parsing engine would work just great after some tweaking.

An alternative approach would be to first parse Slashdot archives to get a lot of posts, articles and moderation data and then use Bayesian theory to decide which sentences/keywords should be included to produce highest moderation based on the words in the blurb (or the linked article, but parsing that would be against /. spirit).

It can be further enhanced using the poetry evolution engine. If we limit the system to very short posts (cliche jokes or smartass oneliners), it might work quite well (feedback, of course, would be the moderation).

Any volunteers?

Wired News has a similar article. Maybe you could just combine the new AI with the cute exterior ofClippy. On the other hand side it would be interesting how much space you have to allocate for the AI database. as far as i remember A.L.I.C.E. needed a quite large AIML file to be just somewhat intelligent. If now the computer should also remeber patterns in behavior and not just talk to you (Alice is a pure chatbot) then in my opinion you need quite large amounts of data to be stored. This could be useful for larger companies with a dedicated AI Server to help their employees (if we talk about AI in a network, why not call ist SKYNET), but on a normal desktop? I think that's too much.

And to focus on another problem: if this thing learns about you behavior, don't you mind about your privacy? We are all paranoid about cookies and other spyware, and then some people actually want us to deliberatly install it? Just imagine: Your boss next to you because you want to show something to him and then the computer asks: "Hi XY, you haven't visited ./ today, normally syou surf it for ours during work. Can I help you get there?"

Talk to one of the Alicebots for a few minutes, You won't worry about intelligent machines taking over any time soon.

a spammer's wet dream?

put out some bots with special interests you want to target, say... snorkeling...

boom, the bot sees a few folks who like snorkeling...

bot starts feeding them alice bot style babbling about the new x-10 snorkle cam, or some such shit

This is a very helpful post for those of us who don't understand how it works. I read everything ahead of it and it's not redundant at all. Who is moderating this? A.L.I.C.E.?

In my opinion, "Social software" has already met its peak. I can stream any sort of dataset i have (video, audio, text, software, etc.) to anyone with a computer. P2P technology even opened up the door to communicate this information with people I don't know, and generate lists of contacts who require or provide similar information. At least technologically speaking, we have all the social software we're ever going to need.

I think the issue at hand is more psychological than technical. Social psychology revolves around a single issue: reproduction. The fact of the matter is, if we don't meet people we can't reproduce to pass our genes onto a new generation. This functional property of social interaction can't be replaced by software. No system of statistical compatibility will ever be able to tell you when you're in "love," nor will the Sims Online ever teach how to cope with living with other individuals. The only way to learn these kinds of behaviors is to interact with other human beings.

However, I do admit that social simulation can prodive a useful tool for computing. In particular, some areas of artificial intelligence deal with search spaces of unthinkable complexity and distributed computing (i.e. seti@home) allows many computers to work on the same problem at the same time. Which is exactly what humanity has been doing for ages.

I predict that social software, and even social psychology, will under go a massive revolution once the Turing test can no longer distinguish man from machine. ALICE has successfully fooled some old friends, but only because they thought it was just me "messing" with them, which I tend to do on occasion.

FYI, I'm finishing up my last year in college, with a BS in Math and a BA in Psychology.

Port Eliza to it, and it'll listen to your problems as well.

I was thinking more of Alicebot, because it could be made more bartender-like. And the obligatory "You want some more?" would be fairly easy in AIML...

Education is going online. MIT is pioneering this trend with OpenCourseWare, which aims to make all course materials available on the Web, free of charge.

Why is it important? Because it will turn the joke "Try finding some porn on the net (if you fail kill yourself inmediately)" into "Try finding some info about -your asignature here- (if you fail..)". And this is not just about "free information", it's a better way of learning.

Example: Have you ever been in class with 50 students writing down nearly identical notes? how often did you find enlightment there? I believe everyone should be able to learn at his own pace. That means grabbing the info, studying it, and then spending class time in a more valuable way. Plus it's more rewarding when you are in control of your own learning process.

Anyway, the opportunity is writing software to manage and play with that information. I'll give you an example..

Right now Im having fun feeding a chatterbot with my papers (just a matter of xml+xsl=aiml) so any student can go to my page and just say:

More valuable examples are left as an exercise for the reader.

Education is going online. MIT is pioneering this trend with OpenCourseWare, which aims to make all course materials available on the Web, free of charge.

Why is it important? Because it will turn the joke "Try finding some porn on the net (if you fail kill yourself inmediately)" into "Try finding some info about -your asignature here- (if you fail..)". And this is not just about "free information", it's a better way of learning.

Example: Have you ever been in class with 50 students writing down nearly identical notes? how often did you find enlightment there? I believe everyone should be able to learn at his own pace. That means grabbing the info, studying it, and then spending class time in a more valuable way. Plus it's more rewarding when you are in control of your own learning process.

Anyway, the opportunity is writing software to manage and play with that information. I'll give you an example..

Right now Im having fun feeding a chatterbot with my papers (just a matter of xml+xsl=aiml) so any student can go to my page and just say:

More valuable examples are left as an exercise for the reader.

...why is it called ALICE? Is it a deliberate attempt to confuse people who already relate ALICE to the ALICEbot? Is ALICE simply just a very adpatable acronym? Does ALICE the acronym deserve an acronym to describe it's acronymity? Adaptable Language In Crappy English, perhaps?

That's not true! I'm a wannabe IT worker, and I make it a point to talk/ hangout with new people, especially cool folks such as these.

Yeah! Even A.L.I.C.E [alicebot.org] knows the difference between you're and your [slashdot.org]! She even makes fun of you for it.

Too late.
Home of Talking Servers

Somebody even used this technology in his AIBO--scary!

Obvious answer

Go directly to their page and chat with alice yourself

Then look here--a lot of programs that implement ALICE. Included is a bot for ICQ!

I haven't seen this posted yet, but if you follow the "Try talking to ALICE" link on this page, you can see what all the fuss is about. Or not about, as the case may be :)

You can try out ALICE - check out the ALICE homepage. There's a link to talk to her on the right side of the page.

You're right -- that was a bit of a flippant remark on my part; sorry.

I guess I should confess a certain zeal for the minimalist approach of Alicebot, which is all about dumping conventional NLP and AI techniques out the window, and going whole-hog instead for a really hardcore stimulus-response model. The typical reaction people have to this approach is to say "Isn't that just like Eliza?", to which the answer is "Yes, but several orders of magnitude smarter"...followed by a long explanation (there's a lot on the site).

I didn't invent this, Richard Wallace did. But I have to admit a certain enthusiasm for the approach, which sometimes leads me to be a little over-energetic in making claims about it.

I guess for me the point about "really works" is framed by the Turing Test -- and that is certainly a presumption that ought to be stated up front. Alice won last year's Loebner Prize, which although not an exact implementation of Turing's original experiment is the closest thing the world has right now. In that contest, the main goal is to imitate a human (in Turing's proposal, the goal was a little more constrained and had a scientific control attached). Anything that does reasonably well on that score can be said to "work", from one point of view: a more empirical one. Of course, from other points of view (and there sure are many!), anything that doesn't incorporate structures/concepts/rules that are generally conceived of as being more closely analogous to brain functionality (neural networks for instance) is off the mark.

So Alicebot has absolutely no neural network, no notion of a lexicon, etc. AIML is about as simple as you can get. This confuses people sometimes -- as though Wallace & others working on this somehow "overlooked" the need for a "learning" mechanism or a syntactic parser or a link with an "ontology of common sense" or what-have-you. In point of fact, Alicebot is just actively rejecting most other approaches, based not only on the disappointing results that they've generally produced, but also just on the premise that it might be (and has proved to be) interesting to pursue this particular, minimal, pattern-matching-based approach. Clearly no approach has "won" hands-down, but Alicebot has certainly proved a lot with a lot less financial backing than some projects (like Cyc). Time will tell...and framing the question better will help (which is what I failed to do in my response -- sorry, one more time ;-) ).

Noel

You're right -- that was a bit of a flippant remark on my part; sorry.

I guess I should confess a certain zeal for the minimalist approach of Alicebot, which is all about dumping conventional NLP and AI techniques out the window, and going whole-hog instead for a really hardcore stimulus-response model. The typical reaction people have to this approach is to say "Isn't that just like Eliza?", to which the answer is "Yes, but several orders of magnitude smarter"...followed by a long explanation (there's a lot on the site).

I didn't invent this, Richard Wallace did. But I have to admit a certain enthusiasm for the approach, which sometimes leads me to be a little over-energetic in making claims about it.

I guess for me the point about "really works" is framed by the Turing Test -- and that is certainly a presumption that ought to be stated up front. Alice won last year's Loebner Prize, which although not an exact implementation of Turing's original experiment is the closest thing the world has right now. In that contest, the main goal is to imitate a human (in Turing's proposal, the goal was a little more constrained and had a scientific control attached). Anything that does reasonably well on that score can be said to "work", from one point of view: a more empirical one. Of course, from other points of view (and there sure are many!), anything that doesn't incorporate structures/concepts/rules that are generally conceived of as being more closely analogous to brain functionality (neural networks for instance) is off the mark.

So Alicebot has absolutely no neural network, no notion of a lexicon, etc. AIML is about as simple as you can get. This confuses people sometimes -- as though Wallace & others working on this somehow "overlooked" the need for a "learning" mechanism or a syntactic parser or a link with an "ontology of common sense" or what-have-you. In point of fact, Alicebot is just actively rejecting most other approaches, based not only on the disappointing results that they've generally produced, but also just on the premise that it might be (and has proved to be) interesting to pursue this particular, minimal, pattern-matching-based approach. Clearly no approach has "won" hands-down, but Alicebot has certainly proved a lot with a lot less financial backing than some projects (like Cyc). Time will tell...and framing the question better will help (which is what I failed to do in my response -- sorry, one more time ;-) ).

Noel