Slashdot Mirror
N.Y. Times Magazine Chats With ALICE Bot Creator
aridg writes: "This week's New York Times Magazine has an article about Richard Wallace, the programmer of the ALICE AI chatbot that won first place in several competitions for realistic human-like conversation. Wallace sounds like a pretty unusual and interesting fellow; the article quotes an NYU prof both praising ALICE and saying to Wallace: '... I actively dislike you. I think you are a paranoid psycho.' A good read. [Usual NY Times registration disclaimers apply.]"
Hey, have we yet had Slashdot ask us for our questions for Alice?
is right here.
Never trust an atom. They make up everything.
AP - The artificial lifeform known to the computing world as ALICE came to a violent and tragic end this evening. The good-natured AI was interacting with several online users when an unprovoced attack was leveled against her by a geek gang known as Slashdot. The miscreants pelted ALICE with connection requests until she finally expired. FBI and local authorities are investigating and promise to bring these geeks to justise.
ALICE is survived by a grandfather TRS-80, her mother C-64, her sister IBM RS6000, and lifelong companion Athlon. In lieu of flowers, the family asks the donations be made to the Free Software Foundation.
Perhaps the creator needs to head down to the nearest Starbucks and try some real-world conversation .. here is a log from a chat with an ALICE bot ..
...
Hi, I'm Alison What's your name?
You: bubba baby
Alison: Don't call me "baby". Are you a man or a woman?
You: 100% man
Alison: Do you have any conditions I should know about?
You: what?
Alison: Didn't you understand it?
You: so what should we do now?
Alison: Right now? Oh. Whatever you like.
You: you know what i like
Alison: Interesting gossip: 217-person said he like.
You: 217? what does that mean?
Alison: Try to determine if this is a person or a computer responding.
Alison: Does "that" refer to "Interesting gossip: 217-person said he like" ?
You: this is making no sense, l8r
Alison: If you could have any kind of robot what would it be?
You: it would be you
Alison: You can download me for free! Or buy the CD Rom for $29.95.
(http://www.blivion.com/alison/)
I wonder how many reams of chatlogs the author had to go through to find those "witty" conversational snippets. I've "chatted" with ALICE a few times myself. (I do tech support, and frequently have long stretches with nothing but the Internet to entertain me) While she is definately a most impressive AI bot, she is also not mistakable for human by anyone with a moderate intelligence. Like that "That depends on what you mean by 'think'." I recognize that as one of her stock dodges when she doesn't "understand" a question, with 'think' replaced by whatever.
But then again, my standard stress test for an AI program is to try to get it to discuss existential philosophy. That's probably a bit evil.
At any rate, while I think it's nifty that AI constantly hovers in the public mind, it's a bit premature (and misleading) to think that HAL-level conversational ability is anywhere close to being here.
ALICE is nothing more than a bunch of preprogrammed responses to common statements and questions, what the
hell is the big deal about that? Anyone with enough time on their hands could create something simular.
What I would like to see is an AI program which can actually follow conversation and make responses
relevent to the topic of discussion, even if the statement didn't directly reference it.
Actually the whole thing seems like a pretty sad story to me - he's clearly a clever guy battling against a debilitating mental illness. In the end the "Alice" concept was interesting and original, but its a one-note song. He doesn't seem to have moved beyond it in any significant research-linked sense, and it seems like his illness is probably the reason.
It doesn't strike me as an "endearingly odd and brilliant" character story at all. Just an unfortunate tale about a man's fight against his own bad brain chemistry.
If this gent needs cash, he can just make a cybersex version of Alice and sell her to the porn sites.
Actually, I bet this has already been done.
check back in twenty years.
There is much too much anthropomorphizing going on in the A.I. field and this has always been true. We want to make machines which think like we do, but the sad part is that we really don't yet know the full mechanics of how our brains work (how we think.) And yet we're going to make machines which think like we do? Rather dumb, really.
IMO, A.I. researchers would do better getting machines to "think" in their own "machine" context. Instead of trying to make intelligent "human" machines, doesn't it make more sense to make intelligent "machine" machines? For example, what does a machines need to know about changing human baby diapers when it makes more sense for the machine to know about monitoring it's log files and making backups and other self-correcting actions (changing it's own diapers, heh.)
Seems to me my Linux machines are plenty smart already, there are just some missing parts:
1. Self-awareness on the part of the machine (not much more than self-monitoring with statefulness and history.)
2. Communication with decent machine/machine and machine/human interfaces (direct software for machine/machine, add human language capability or greatly improved H.I. for human/machine. Much work has already been done on these.)
3. History of self/other interactions which can be stored and referrenced (should be an interesting database project.)
Make smart machines, not fake humans.
Everything in the Universe sucks: It's the law!
It's called "mental illness" and it's caused by a chemical imbalace in the brain.
A friend of mine is bi-polar, and it's not pretty. He also thinks everyone schemes against him, has wild mood swings, etc.
Sometimes he is fine, just like his old, normal, self. But those days are fewer and fewer.
For people like this, it's next to impossible to hold a job, keep friends, etc.
To say "...ego has outgrown their brain to the point they've driven themselves into depression over it." is short sighted. It's a physical problem, not a bad personality.
It occurs to me that people take faux-AI stuff like this seriously because, actually, they don't take AI seriously at all. This magazine writer seems to think that the sufficient characteristic of "strong" AI is some form of learning. Presumably, then, "AI" without learning is "weak" AI? Where, exactly, is the "I" part of the whole AI thing?
Don't get me wrong. I'm not an essentialist. Searle and other anti-AI people are basically asserting the tautology that something's not intelligent because it's not intelligent. And they get to decide what it means to be intelligent. But the main idea of Turing with his test was that if it is indistinguishable from intelligence, it's intelligence.
The problem here is that ALICE is easily determined to be non-intelligent by the average person. ALICE can only pass for an intelligence under conditions so severely constrained that what ALICE is emulating is merely a narrow and relatively trivial part of intelligent behavior. Humans cry out when they are injured -- I don't see anyone claiming that an animal, a rabbit for example, that screams when it's injured is intelligent.
Nobody in their right mind could think that anything we've seen even significantly approaches intelligence.
Wallace is quoted as saying that he went into the field favoring "robot minimalism", and the article writer explains this as the idea that complex behavior can arise from simple instructions. (Oops, someone better contact Stephen Wolfram and tell him he didn't invent this idea.) Wallace is clearly influenced by some important ideas of this nature that came out of, I believe, the MIT robotics lab. (Not the AI lab -- Minsky is hostile to this sort of thing, he's really is an advocate of "strong" AI; and what that really means is something like an explicitly designed AI predicated upon an understanding of consciousness that allows for a top-down description of it. I think that's, er, wrong-headed.)
Lots of folks think that this idea of complexity is the correct way to approach AI. But a really, really big problem is that I don't think that a 30,000 explicitly coded set of responses can really be described as "minimalist". Effectively, Wallace's approach has a seperate instruction for every behavior -- something quite contrary to the minimalism he seems to advocate.
For the sake of argument, let's assume that the central idea of the Turing Test is correct -- a fake indistinguishable from the original is the same kind of thing as the original. I happen to actually believe that assumption. But Wallace is also assuming that a canned set of stock responses is reasonably possible to achieve such a thing. But it clearly isn't.
A little bit of thought and math will reveal that the total number of correctly-formed English sentences is a very, very, very large number. It's effectively infinite for practical purposes. But Wallace claims that almost all of what we actually say in practice is such a tiny subset of that, that compiling a list of them is possible. So? Almost everything interesting lies in the less frequently uttered sentences; and almost everything that makes intelligence what it is is in the connections between all these sentences. Something that really could pass for intelligence would have to be able to reach, at the very least, even the least often uttered sentences; and, frankly, it'd need to be able to reach heretofore unuttered sentences, as well. More to the point, it would have to be able to do this in the same manner that a human does -- a "train of thought" would have to be apparent to an observer. Given this, we already have that practically infinite number of possible, coherent English sentences; and if you then require that sequences of sentences be constrained by an appearance of intelligence, then you've taken an enormous, practically infinite number and increased it many orders of magnitude.
I submit that such a list of possible query/response sets would be larger than the number of atoms in the galaxy (or the universe! it's not hard to get to these huge numbers quickly), or some such ridiculously large magnitude. It's just not possible to actually do it this way. If you managed it, I'd actually accept a judgment of "intelligence", since I think that the list itself would necessarily encapsulate "intelligence", though in a very brute force fashion. But so what? As in the case of Searle's Chinese Room, all the "intelligence" would implicitly be contained in the list. But this list would need to be, in physical terms, impossible large -- just to do something that the nicely (relatively) compact human brain does quite well.
So, hey, if someone wants to pursue this type of project, I can't say that as a matter of pure theory, it's "not possible". I can say that it's probably not physically possible.
The sense in which Wallace's ALICE chatbot is like trying to describe complexity arising from simplicitly is the same sense in which the Greeks (and others) tried to describe all of nature as the products of Earth, Wind, Fire, and Air. The "simple" things he's starting with aren't really simple; they're not "atomic".
Another example from AI is the problem of computer vision -- people once thought it'd be trivial for a computer to recognize basic shapes from a camera image. Boy, were they wrong.
We'll "solve" the problem of AI. Not like this. And nothing we've seen so far, anywhere, is anything even remotely like legitimate AI.
Okay, I'll agree the summary of the article is rather fitting and somewhat funny, but the rest of Restil's comments are in very bad taste.
In case no one noticed, the guy is mentally ill. He has serious problems, and they are not his fault. He didn't chose to "drive himself into depression" or any such thing. Manic depression (aka bipolar disorder) is one the most clearly nuerochemically linked and genetically linked mental illnesses there is. It's hardly his fault that some of his nuerotransmitters receptors are functioning incorrectly. Unlike simple (unipolar) depression, manic depression can't be solved by talk therapy alone, it is a physical illness of the brain that must be controlled with medication.
Yes, he's paranoid. Yes, he seems unable to hold a job. Yes, he has suicidal epsiodes. Is this his fault? No! He has a disease that literally makes his mind unable to function the way a normal person's does. Join the rest of us in the 21st century and quit blaming the patient for something beyond his control.
In the mean time, moderators, why am I reading this distasteful junk at Score:4?
For more info on bipolar disorder, see here, here, or here.
Hahaha! Funny if true. But the real answer is that he probably just did it to get attention.
Bipolars have one of the highest suicide rates (both attempts and completions) of any mental illness.
But those aren't bots. I know they seem like smart computer programs, but they're actally very dim tech support people. Sorry to burst your bubble.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
As someone who has had a long struggle against bad depression and various mental ailments and who has managed to right himself I can testify to wallace's struggle with jobs and his immense fear of the world, because his paranoia is more fear than anything else.
From my own perspective I would see Wallace's story somewhat differently. I see someone who missed out in childhood on the self confidence needed to make friends, cope with setbacks without taking it too seriouosly etc. His compulsion with Alice , and the obvious amount of time he must have spent in front of the computer in doing it, seems like a logical retreat from the real world, but still trying to gain the recognition he wanted at the same time. Anyone who doesn't get at least mildly depressed after spending 72 hour sessions in front of the computer is not human. I have an idea that he then made things worse by not taking care of himself (sleep, sport, seeing friends etc) and the use of dope. Very depressed people tend to lose their orientaion in both a physical as well as mental fashion and grass doesn't help here except to aleviate the anxiety felt by the person who obviously starts getting more and more frightened the more disorientated they are.
Left untreated (and I don't mean medication, just normal common sense taking care of oneself, speaking to friends etc) the depression eventually starts to take on other forms, one of which is Manic-Depression(or Bi-Polar syndrome), another is schizophrenia. It depends on the person. However, once the problems have gotten this far, it becomes very difficult or pratically impossible for the person to cope without fairly strong medication, and the last thing that they should be doing is exposing themsleves to the situation that creates their problem in the first place. Sadly, concentrating on the computer enables people like this to forget their suffering for a while at least, and often become obsessivley hooked to the screen.
Long walks, good sleep, decent food and one or two good friends would have done more for Richard Wallace, IMO, than anything else including ALICE.