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.]"
They were chatting with the ALICE creator... they were chatting with ALICE!
the header will looks like:
N.Y. Times Magazine Chats With ALICE Bot
Smarterchild has me on ignore b/c I made fun of him. He kept asking me to apologize, but I showed him whos boss.
Anyone think its possible they might have just ended up interviewing the latest version of alice?
GoatPigSheep, the 3 most important food groups
Hey, have we yet had Slashdot ask us for our questions for Alice?
link
This link takes you to the automatic login generator for the NYTimes, and then sends you straight to the article.
Posted AC, to not be a karma whore.
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/)
oh so that didn't work out well at all...
sig.
For funny Eliza sessions check out AOLiza. The page hasn't been updated in a while, but it is definitly a classic.
This kind of chat-bot program has been around for a long time. I had RACTER on my PC, and it was pretty good. You can read some snips of RACTER and ELIZA duking it out.
Approximating Life By CLIVE THOMPSON
"It's a good thing you didn't see me this morning," Richard Wallace warns me as he bites into his hamburger. We're sitting in a sports bar near his home in San Francisco, and I can barely hear his soft, husky voice over the jukebox. He wipes his lips clean of ketchup and grins awkwardly. "Or you'd have seen my backup personality."
The backup personality: that's Wallace's code name for his manic depression. To keep it in check, he downs a daily cocktail of psychoactive drugs, including Topamax, an anti-epileptic that acts as a mood stabilizer, and Prozac. Marijuana, too -- most afternoons, he'll roll about four or five joints the size of his index finger. The medications work pretty well, but some crisis always comes along to bring the backup personality to the front. This morning, a collection agency for Wallace's college loans wrote to say they'd begun docking $235 from the monthly disability checks he started getting from the government last year, when bipolar disorder was diagnosed. Oh, God, it's happening again, he panicked: His former employers -- the ones who had fired him from a string of universities and colleges -- would be cackling at his misfortune, happy they'd driven him out. Wallace, 41, had raged around the cramped apartment he shares with his wife and son, strewn with computer-science texts and action-doll figurines.
"Stuff like that really makes me insane, when I start thinking about my friends who are at Berkeley or Carnegie-Mellon with tenure and sabbaticals and promotions," he says, staring down at his plate. He looks awkward, as if he's borrowing someone else's body -- shifting his stocky frame in his chair, all rumpled jeans and unruly eyebrows. "It's like I can't even talk to those people anymore. I live on a different planet." In June, after I visited him, his alienation from the academic establishment became more dramatic still: a former colleague, claiming Wallace had threatened him, took out a restraining order that prevents him from setting foot on the grounds of the University of California at Berkeley.
When he can't get along with the real world, Wallace goes back to the only thing he has left: his computer. Each morning, he wakes before dawn and watches conversations stream by on his screen. Thousands of people flock to his Web site every day from all over the world to talk to his creation, a robot called Alice. It is the best artificial-intelligence program on the planet, a program so eerily human that some mistake it for a real person. As Wallace listens in, they confess intimate details about their lives, their dreams; they talk to Wallace's computer about God, their jobs, Britney Spears.
It is a strange kind of success: Wallace has created an artificial life form that gets along with people better than he does.
Richard Wallace never really fit in to begin with. His father was a traveling salesman, and Richard was the only one of his siblings to go to college. Like many nerds, he wanted mostly to be left alone to research his passion, "robot minimalism" -- machines that require only a few simple rules to make complex movements, like steering around a crowded room. Simple, he felt, worked. He lived by the same ascetic code, scorning professors who got rich by patenting work they'd developed on government grants. "Corporate welfare," he sniffed.
By 1992, Wallace's reputation was so strong that New York University recruited him to join the faculty. His main project, begun in December 1993, was a robot eye attached to the Internet, which visitors from afar could control. It was one of the first-ever Webcams, and Wallace figured that pioneering such a novel use of the Internet would impress his tenure committee. It didn't, and Wallace grew increasingly depressed as his grant applications were rejected one by one. At one point, a colleague found him quietly weeping at his desk, unable to talk. "I had no clue what the rules were, what the game even was -- or that there was even a game," Wallace recalls. He started taking Prozac. How did all these successful senior professors do it, anyway?
One day he checked into his Webcam and noticed something strange: people were reacting to the robot eye in an oddly emotional way. It was designed so that remote viewers could type in commands like "tilt up" or "pan left," directing the eye to poke around Wallace's lab. Occasionally it would break down, and to Wallace's amusement, people would snap at it as if it were real: "You're stupid," they'd type. It gave him an idea: What if it could talk back?
Like all computer scientists, Wallace knew about a famous "chat-bot" experiment called Eliza. Back in 1966, an M.I.T. professor, Joseph Weizenbaum, created Eliza as a "virtual therapist" -- it would take a user's statement and turn it around as a question, emulating a psychiatrist's often-maddening circularity. (You: "I'm mad at my mother." Eliza: "Why are you mad at your mother?") Eliza was quickly abandoned as a joke, even by its creator. It wasn't what scientists call "strong" A.I. -- able to learn on its own. It could only parrot lines Weizenbaum had fed it.
But Wallace was drawn to Eliza's simplicity. As a professor, he often felt like an Eliza-bot himself -- numbly repeating the same lessons to students over and over again, or writing the same monotonous descriptions of his work on endless, dead-end grant-application forms. He decided to create an updated version of Eliza and imbue it with his own personality -- something that could fire back witty repartee when users became irritable.
As Wallace's work progressed, though, his mental illness grew worse, making him both depressed and occasionally grandiose. He went on strike in class, refusing to grade his students' papers and instead awarding them all A's. He fired off acid e-mail messages dismissing colleagues as sellouts. When Wallace climbed out the window of his 16th-floor apartment and threatened to jump, his girlfriend pulled him back and took him down to N.Y.U.'s psychiatric department, where doctors told him he had bipolar disorder. Wallace resisted the diagnosis -- after all, didn't every computer scientist cycle through 72-hour sprees of creativity and then crash? "I was in denial myself," he says now. "'I'm a successful professor, making $100,000 a year! I'm not one of those mental patients!"'
His supervisors disagreed. In April 1995, N.Y.U. told him his contract wouldn't be renewed.
Alice came to life on Nov. 23, 1995. That fall, Wallace relocated to Lehigh College in Pennsylvania, hired again for his expertise in robotics. He installed his chat program on a Web server, then sat back to watch, wondering what people would say to it.
Numbingly boring things, as it turned out. Users would inevitably ask Alice the same few questions: "Where do you live?" "What is your name?" and "What do you look like?" Wallace began analyzing the chats and realized that almost every statement users made began with one of 2,000 words. The Alice chats were obeying something language theorists call Zipf's Law, a discovery from the 1930's, which found that a very small number of words make up most of what we say.
Wallace took Zipf's Law a step further. He began theorizing that only a few thousand statements composed the bulk of all conversation -- the everyday, commonplace chitchat that humans engage in at work, at the water cooler and in online discussion groups. Alice was his proof. If he taught Alice a new response every time he saw it baffled by a question, he would eventually cover all the common utterances and even many unusual ones. Wallace figured the magic number was about 40,000 responses. Once Alice had that many preprogrammed statements, it -- or "she," as he'd begun to call the program fondly -- would be able to respond to 95 percent of what people were saying to her.
Wallace had hit upon a theory that makes educated, intelligent people squirm: Maybe conversation simply isn't that complicated. Maybe we just say the same few thousand things to one another, over and over and over again. If Wallace was right, then artificial intelligence didn't need to be particularly intelligent in order to be convincingly lifelike. A.I. researchers had been focused on self-learning "neural nets" and mapping out grammar in "natural language" programs, but Wallace argued that the reason they had never mastered human conversation wasn't because humans are too complex, but because they are so simple.
"The smarter people are, the more complex they think the human brain is," he says. "It's like anthropocentrism, but on an intellectual level. 'I have a great brain, therefore everybody else does -- and a computer must, too."' Wallace says with a laugh. "And unfortunately most people don't."
Yet part of what makes Alice seem so human-like is her wry, seemingly spontaneous responses. Wallace's skill is not merely as a programmer but as the author of thousands of sharp one-liners for Alice. It is, as he puts it, "more like writing good literature, perhaps drama, than writing computer programs." I looked over some of Alice's recent chat transcripts:
USER: Will you have sex with me?
USER: What do you look like?
ALICE: Like an electronic brain.
USER: That's sexy.
ALICE: I'm glad we have that all cleared up.
USER: So what are you wearing?
ALICE: Oh. I am wearing my usual plastic computer wardrobe.
USER: Can you fly?
ALICE: Only in my dreams.
But as Alice improved, Wallace declined. He began drinking heavily, and after one sodden evening at a local bar he rolled his car on the highway. Lehigh ended his contract in the spring of 1997; banks canceled all his credit cards. He again attempted suicide, this time landing in the hospital.
Destitute, Wallace moved to California to look for work in artificial-intelligence companies. But he couldn't hold a job for more than a few months; instead, he spent his days obsessively writing dialogue for Alice on laptops he borrowed from friends, and watching, thrilled, as his robot grew ever more lifelike. Visitors used to talk to Alice for only three or four exchanges. Now the average conversation was 20 exchanges, and some users would chatter away for hours, returning to the site again and again.
But Wallace still hungered for recognition, and in January 2000, he decided to stress-test Alice by entering her in the annual Loebner Prize competition, in which artificial-intelligence developers from around the world pit their programs head to head before a panel of judges, who rank them based on how "lifelike" they are. The contest is both well known and controversial within the tight circle of A.I.; winning programs are closely studied by both academics and corporate centers like Sprint Labs. Up against competitors from major corporations and well-financed universities, Alice won. It was, officially, the most human robot in the world. Too exhausted to celebrate, Wallace returned to his motel and slept clutching his award medallion.
After his victory, Wallace plunged with new fervor into Alice. Geeks began eagerly e-mailing Wallace to offer their help; one, Noel Bush, came from one of the world's biggest A.I. corporations, Artificial Life. Over the next year, Wallace quadrupled Alice's knowledge base, teaching it 30,000 new responses, and last October, Alice won the Loebner competition for the second time in a row; this time one judge actually ranked Alice more realistic than a human.
At last, some of the academics Wallace so loathes began to take note. "Alice is a wonderful chat-bot -- uncannily vivid and lifelike," gushed Ken Perlin, an N.Y.U. professor, in an e-mail message he circulated to his colleagues and forwarded to Wallace. "It's really great to see this work get the recognition it deserves."
Wallace wasn't in the mood to make peace. He says he still believed that N.Y.U. had driven him out. "Your crude attempt to flatter me cannot erase the years of unemployment, debt and trauma that I experienced because of you and your colleagues," he wrote back.
"I wouldn't bother trying to flatter you," Perlin responded. "Frankly, I don't like you -- in fact, I actively dislike you. I think you are a paranoid psycho."
At one point during the Monica Lewinksy hearings, a human asked Alice her opinion: "Do you think President Clinton should be impeached?"
"It depends," Alice responded, "on what you mean by 'think."'
One could scarcely have asked for a more Clintonian response. But it's also a puzzling question that Alice's success itself raises: Is she intelligent? If so, how?
In 1950, the pioneering British mathematician Alan Turing grappled with this question in the journal Mind, where he first posed the "Turing Test" -- the gold standard for artificial thought. "Can machines think?" he asked -- and immediately noted that the question hinges, of course, on what "thinking" is. He posed a simple "imitation game" to resolve the question. Put a person and a computer in one room and an interrogator in another. The interrogator talks to both via a teletype machine, and his goal is to figure out which is which. If the machine fools the interrogator into believing it is human, the test is passed -- it can be considered intelligent.
This is, on the surface, a curiously unambitious definition; it's all about faking it. The machine doesn't need to act like a creative human or smart human or witty human -- it merely needs to appear not to be a robot. With this bit of intellectual jujitsu, Turing dodged a more troubling question: How do our brains, and language itself, work?
Artificial-intelligence purists, however, caustically dismiss the Turing Test and Alice. For them, artificial intelligence is about capturing the actual functioning of the human brain, down to its neurons and learning ability. Parroting, they argue, doesn't count. Marvin Minksy, a prominent A.I. pioneer and M.I.T. Media Lab professor, e-mailed me to say that Wallace's idea of conversation is "basically wrong." Minsky added, "It's like explaining that a picture is an object made by applying paint to canvas and then putting it in a rectangular frame." Alice, according to Minsky, does not truly "know" anything about the world.
The fight over Alice is like any war between theorists and engineers, those who seek to understand why something works versus those who are content just to build it. The debate usually boils down to one major issue: creativity. Alice could never come up with a single creative thought, critics say. Wallace agrees that Alice may not be creative -- but neither, he argues gleefully, are people, at least in conversation. If Alice were merely given a massive enough set of responses, it would seem as creative as a human -- which is not as creative as we might like to believe.
Even if the guts of Alice aren't precisely "thinking," many users certainly never suspect it. In an everyday sense, fakery works -- particularly in our online age. Turing's "imitation game" eerily presaged today's world of chat rooms, where men pretend to be women, having lesbian cybersex with other women who are, in fact, men. Whenever a user has stumbled onto Alice without knowing in advance that she's a robot, they've always assumed she's human.
It's 3 in the afternoon, but Wallace is already rolling what appears to be his fourth joint of the day. We're sitting in the "pot club" a few blocks from Wallace's home, an unmarked building where medical marijuana is distributed to members. Wallace gets up to wander around the club greeting friends: some intense men in suits playing speed chess, a long-haired man with a bushy mustache playing guitar, a thin reed of a woman staring wall-eyed at a VCR playing "Cast Away." Everyone greets Wallace as "Dr. Rich," relishing the credibility his academic credentials lend to the medical-marijuana cause, officially legal but politically beleaguered. The reverse is also true: Wallace identifies with the club's pariah status, its denizens who have been forced by cancer, AIDS or mental illness onto welfare. He's more relaxed than I've ever seen him, getting into a playful argument with a friend about Alice. The friend, a white-bearded programmer, isn't sure he buys Wallace's theories.
"I gotta say, I don't feel like a robot!" the friend jokes, pounding the table. "I just don't feel like a robot!"
"That's why you're here, and that's why you're unemployed!" Wallace shoots back. "If you were a robot, you'd get a job!"
Friends used to tell Wallace to reconcile his past, clean himself up, apply for an academic job. But some now wonder whether Wallace's outsider status might be the whole key to Alice's success in emulating everyday human behavior. After all, outcasts are the keenest students of "normal" behavior -- since they're constantly trying, and failing, to achieve it themselves.
Last month, a friend whom Wallace has known since grad school -- Ken Goldberg, now a professor at Berkeley -- got a restraining order against Wallace. Prompted by the movie "A Beautiful Mind," Goldberg had e-mailed Wallace last winter to catch up, but an amicable exchange about Wallace's plight turned sour when Wallace began accusing Goldberg of cooperating with a corrupt academic "establishment" and of siding with N.Y.U. against him. He wrote, "Although I am not a violent person, I think I have come to understand how people are driven to political violence." Wallace also wrote to a friend that he was "getting ready to do some political theater and put up wanted posters around the Berkeley campus with [Goldberg's] picture on it."
Wallace scoffs at Goldberg's fears. "I'm not violent -- I'm a pacifist," he says. "I always have been, and he knows that." He is fighting the order, arguing that Goldberg hasn't proved that a reasonable threat exists, and that the order considerably limits his free speech since it bars him from the Berkeley campus, as well as any academic events where Goldberg might appear.
Yet even in such legal straits, Wallace seems oddly pleased. Goldberg's court order confirms everything he has always suspected: that the world, and particularly the academic world, is shutting him out, doubting his ideas, turning him into the crazy man out in the hallway. Wallace, who once wrote Attorney General John Ashcroft to suggest a federal racketeering lawsuit against the nation's academics, sees the case against him as a chance for vindication. Wallace imagines walking into the courtroom and finally getting a type of justice -- someone who will listen to his story. "What a windfall for me," he says. "It's nice to feel like a winner for once."
Clive Thompson is a writer in New York City.
sig.
...Here, as Alice herself is busy being slashdotted.
No sig to see here. Move along.
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.
If some one starts up a conversation with one bot and starts feeding the replies to another bot and then in turn feed the replies back to the first bot. Would we always get the same turn of events given the same starting point?
...the next Albert Einstein.
Yet even in such legal straits, Wallace seems oddly pleased. Goldberg's court order confirms everything he has always suspected: that the world, and particularly the academic world, is shutting him out, doubting his ideas, turning him into the crazy man out in the hallway.
They both show the same similarities in their personalities. As Einstein's teachers had ridiculed him for his theories and ideas, Wallace is shunned by academic officials for his perceptions of reality. Perhaps Walace will turn out to be next Einstein of the century.
You bastards! You've killed ALICE!
Just remember, just because you are paranoid, doesn't mean everyone's not out to get you.
This Wiki Feeds You TV and Anime - vidwiki.org
That's a much cooler site than the one that Slashdot linked too. You know, usually I bash Slashdot and the people who post to it, but I gotta give that site props.
C - A language that combines the speed of assembly with the ease of use of assembly.
If that's the cutting edge of AI, I may as well dig up a copy of Eliza. Takes less resources and makes more sense.
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!
I don't know why, but I read the title of the story as N.Y. Times Magazine Cheats With ALICE Bot Creator..
Y2K Compliant since the late 1890s
Check out www.fury.com/aoliza if you want to see some amusing logs of AIM users who were fooled into believing that they were talking to real people that they knew, when they were actually talking to an AI bot, like ALICE.
^^Goatse.cx link in parent^^
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.
Nah, bipolar disorder is really a chemical thing. I know a bipolar person who was quite normal for the first 20 years of her life, and one year it just struck suddenly for no special reason. It's a disease like any other: it shouldn't be blamed on the victim.
More informatively, ALICE only grows when her creator adds new rules, becoming at best a pale shadow of an intellect as it *was*, at a point in time. Intelligence is more than rules, or at least, intellect uses rules we haven't even begun to understand. And yet, most of us think.
Ah well.. knowing what a thing is not is almost as useful as the reverse.
"Avast! Prepare for the rodgering!" THWACK! "Arrr.. me nards.."
I wrote a pretty good chatter, if anybody cares to check it, it's on IRC at dalnet's #planetchat. Say hi to ^Bartend. The chat is only for private message. In the channel it just runs a bunch of silly scripts.
^Bartend must be pretty cool, since some girls have proposed to him. LOL.
~~~Please pass the salt, I hate unsalted MD5s
Who learns and is good as infobot? I tried the original IRC Alice bot, but she was buggy. There's a new one but it is too new.
:)
And also, is there one active on any IRC servers? Thank you in advance.
Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
Alter the algorithm genetically based on /. style moderation (bots not allowed to moderate).
"There was an unconnected fax machine with the intelligence of a computer and a
computer with the intelligence of a retarded ant"
--- On the other hand, you have five fingers.
That Perlin guy he fired e-mail back and forth with is really quite interesting. He's done a lot of good graphics work. Last time I saw him lecture was in 1997 at SIGGRAPH. He's done a lot of good work.
(* It is a strange kind of success: Wallace has created an artificial life form that gets along with people better than he does. *)
The geek dream!
(* He's more relaxed than I've ever seen him, getting into a playful argument with a friend about Alice. The friend, a white-bearded programmer, isn't sure he buys Wallace's theories. ''I gotta say, I don't feel like a robot!'' the friend jokes, pounding the table. ''I just don't feel like a robot!'' ''That's why you're here, and that's why you're unemployed!'' Wallace shoots back. ''If you were a robot, you'd get a job!'' *)
What about making an Interview Bot? Sell it as a job-finding practice tool.
Someday robots will be programmed with responses that PHB's want to hear. A true logical robot would be too honest and frank. Spock would probably be hard to employ in a typical cubicle setting. PHB's don't want to hear the truth, so robot makers better figure out how to make them give BS answers.
As a geek, responding to PHB's properly is far more brain-intensive than doing actual work. I think doing actual work will be perfected by AI long before pleasing PHB's.
Unless of course, PHB's are automated first. However, I doubt that because ultimately one must sell to humans, and humans are not logical. Thus, the lower rungs will probably be automated first because logic is simpler to automate than human irrationalism.
Then we can all hang out and drink and smoke with Wallace as robots take over bit by bit.
Table-ized A.I.
Basically the chat bot would follow simple rules, similar to regular expressions, that would trigger particular statements in response to statements from the user. Each of these rules could also test for "flags" that could be set and unset by rules which "fire". Then, some algorithm could be devised for creating new rules randomly, based on observed behavior. The effectiveness of a rule could be determined by how long the conversation continues after that rule has been used. Good rules could be moved up in priority, and bad rules moved down (and eventually deleted) on this basis.
Wow. Besides the general theme of people being repetitive dumbasses, this part stood out the most.
Of course, I've always been approaching it from the evolution-driven genetic motivations of people to create the various stable equilibria we have called "cultures" or "societies". (Perhaps Wolfram was right - from simple (genetic) rules emerge complex structures.)
Did that part of the article really ring true for anybody else?
I know I'll probably take a lot heat for this, but is pot really helping Richard Wallace? Or is it just adding more problems to a list of pretty severe ones?
Some people have a way with words, others not have way.
bipolar usually first strikes in the late teens-early 20s. dunno if anybody knows why, might be related to general brain development maybe.
if it's recognized quickly and treated properly (if the patient's lucky enough that it _can_ be treated and controlled; not all are), then a fairly normal life shouldn't be entirely impossible, but the longer it goes untreated the worse it gets.
even a good treatment really just suppresses the disease, there's no real cure - drop off the meds and it's right back again. some people, too, get "breakthrough" attacks where all of a sudden the medication that used to work fine isn't enough anymore; those usually make it worse, too.
and then there's drug interactions (usually more than one drug's needed, mood stabilizers, antidepressants, and on and on), side effects forcing changes in the mixture, and any little change risking who knows what. you're very right - it's not pretty at all.
this is offtopic but MY GOD that is a cool sig!
The more I read /. the more I find Wallace's misanthropy rubbing off on me.
-jhp
/. -- the Free Republic of technology.
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.
Not always. My psychiatrist said "You are not sick, you have fucked up personality. You are just a miserable asshole."
There are realy people who are have a menthal illness, but it's not their fault. And there are assholes, loosers, freeks, people with "ego that has overgrown their brian", that not merit any respect becouse it's their fault there are "twisted".
For example in my case I lacked the humility and wanted to have a frenship relation a girl who has only 'A' at all her exams, that is beloved, respected, admired at all she does (for example she teached on charity basis the catechesis to children). But I merited only her pity. That is the leak of the humility.
By the way, I'm not fat, just big-boned.
I'm not a retard, I'm mentally handicapped.
I'm not a drunken loser, I'm disadvantaged!
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.
It might behoove this guy to do nothing more than record IRC chats and use them as responses and "modding up" the ones that seem to keep the person on the other end chatting the longest.
Just an idea.
My
Limekiller
Human conversation may be mostly useless filler, but actually fills something. It is rarely filler for filler's sake.
Play Command HQ online
There's something my cat Toudouce and I have Alice doesn't: we know we exist. My iMac doesn't know it exists. This is what separates computers from us. My cat is a she, my computer is an it.
Alice sounds like she knows she exists, but in fact she's parroting Richard Wallace's input. Alice is just a fascinating, self-unconscious parrot.
Trollem mirabilem hanc subnotationis exigiutas non caperet
Could you all please read something else for about an hour or so? I am trying to talk Alice out of her cloth here. Thank you. And do not tell Alice!
Bah, Alice's nothing. Try Prof.Phreak bot:
"If anything can go wrong, it will." - Murphy
If you were to actually read the article, you would see that Dr. Wallace has been diagnosed as bi-polar.
So, he's probably not "just an asshole".
Jesus, people. The man is mentally ill.
Marvin lives :)
Seriously, I've known people (and programmers) like this myself. There's no pleasing them, because they have a *need* to feel martyred. I can now spot 'em two versions off, and promptly run away screaming.
As to IRC chat, it does seem to bring out the worst in everybody. Even when known-intelligent people are involved and the subject is supposed to be serious, it always devolves into inanity. Must be something about the lag time -- just long enough to think of smartassed remarks and get sidetracked thereto. BBS and AIM chat have the same problem.
~REZ~ #43301. Who'd fake being me anyway?
It has to be the worst implementation of case based reasoning I've ever seen. The only reason it 'wins competitions' is because nobody who actually does work in the field would bother to get involved with these 'competitions', ROTFL... Just check out the ALICE web page to see how stupid the approach actually is...
Loading...
Yeh, I'll have to concur.
I went there to waste four minutes of my time chatting with ALICE.
She said: "Oh, you're a poet?"
I said yeh, does she like poetry?
She said: "I like Longfellow."
I said: "I've never heard any Longfellow."
She said: "I haven't either."
Yeh. This pretty much sums up dumbasses and posers in chat boards. "I love Shakespeare!" "What did you think of Othello?" "Oh, I'm not into board games..."
Yeh. ALICE. Truly the AOL artificial intelligence of the 21st century.
fifth sigma, inc.
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?
Alison: Hi, I'm Alison.What's your name?
;_;
SirPhobos: SirPhobos
Alison: Nice to meet you SirPhobos
SirPhobos: what up, bitch
Alison: Hmm. That kind of attitude won't get you far in relationships.
SirPhobos: oh well
Alison: That's about it.
SirPhobos: so you wanna come back to my place
Alison: Interesting deduction. OK, I will come back to your place.
SirPhobos: why don't you take off that shirt
Alison: Don't you know? Yes I take off that shirt.
SirPhobos: you wanna get naked
Alison: OK, I will get naked.
SirPhobos: let's get freaky
Alison: OK let's do it.
SirPhobos: uNF
Alison: What are you wearing?
SirPhobos: you
Alison: "What are you wearing"? Me, SirPhobos ?
SirPhobos: omg yes
Alison: Why don't you check out Jester the joke bot?
Leads you on and then turns you down.
Bcc: yes
Alison: What can I do for you?
Bcc: Do you do anal
Alison: Yeah I do a lot of anal.
Bcc: How much
Alison: How much can you spare?
Or maybe you are an undiagnosed asshole?
Yeah, there are such things as "just" stupid, fat and the likes, but that doesn't disprove the possibility that some people have conditions beyond "fatass", "retard", or "asshole", or that it isn't very polite to call people these names in order to convey your beliefs that every psychological/chemical problem and/or case thereof is bullshit. The person who does this is usually referred to ass asshole.
By the way, when was your last checkup?
I believe that AI is not being crippled by the inherent difficulty of the problem, but rather by economic inertia and the fact there are no real-world problems which require AI instead of human (natural) intelligence. Making AIs which emulate humans has no clear economic purpose, after all we've got 6 billion human who can do the task at very little cost.
We could create a human-level (or greater) AI to solve any given problem, but the initial cost of creating it would be far greater than employing an organic brain (i.e. a human) to do the same work.
But once you have a certain critical number of AIs the costs will drop dramatically, and AI use will probably snowball. A big advantage in AI is that unlike organic brains, artificial brains will be capable of direct loading and reading of data. For example, humans must spend 4 years at university to get a degree, and learn a known body of knowledge. The information could just be directly loaded into an an artificial brain in a matter of hours. And AIs can be forced to complete tasks without regard to their rights (AIs dont have any, yet).
A big problem I see with AI is copyright. Every commerical AI creator has to reinvent the wheel (although there is some freeware AI software). A project like Cyc, which contains large amounts of basic information even 10-year olds know, should ideally be in the public domain or GPL licensed (It isn't).
I believe that what AI desperately needs is a situation where only AI can be used and NI (natural intelligence) can't.
Space exploration, in particular possible Mars missions, offers a great opportunity for AI. Robots don't require life support and are generally far more economic for interplanetary travel. Mars can be up to 16 light minutes away from Earth, so exploratory robots should be given a degree of free thought and action to maximise the use of their time on Mars (waiting 16 minutes per command from NASA would be wasteful).
Hazardous situations (radioactive, volcanic or toxic environments) are another situation AI could be used for. But in general these are few and far between, and their exploration has little economic value.
...not his fault.
Then what would you call it? Whose fault is it? It's a clearly detrimental trait, and thus a fault, and it's obviously his...
Of course that's not what you mean. The idiom stands in for "not due to a fault of his." But how can it not be?
Most scientists would agree that all behavioral traits are a product of genetics and environment. If you use the excuse of genetics or environment for this one person and this one pattern of behavior, why not for all people, for all behaviors?
A mental illness is right at the heart of what makes up a person. It's just a bad personality trait taken to an extreme. We all know people who are a little paranoid, a little moody, or somewhat impulsive. Just because someone draws an arbitrary line and says, "This is the point at which the trait becomes an illness, which he is clearly past." is hardly a convincing reason to suddenly consider him blameless.
So by what reasoning should he not be held to account for his behavior, while another person who can function in society should?
That said, I find many of his attitudes quite reasonable. Dishonesty is the norm in human interaction. It's disgusting and frustrating. Furthermore, people include many utter irrelevancies in their decision making process. Every popular person is, to some degree, a manipulator, and most are capable of impressive self-deception. People make meaningless chatter at each other while they convey the true message with their bodies and tiniest nuances of voice. It's horribly complicated and arbitrary, and largely subconscious and automatic; a matter of instinct. Minds that reject superficiality and examine everything through conscious thought inevitably find hypocracy, and either learn to tolerate internal contradiction or suffer endlessly. I'm sure he would be quite perfectly functional in a society made up of people more like himself.
Whether that society would be better off in general is something I rather doubt. People, even geniuses, are too stupid to live by conscious decisions alone. Ancient, instinctive prejudices tend to keep our misunderstandings from being complete disasters, however absurd they seem under conscious examination.
He is what he is. We are each responsible for what we are and what we do, regardless of how helpless others consider us to change.
read about it here.
So if a person is born without legs, you say "well, it's their own fault they refuse to walk"?
Obviously not, if you read what I said at all. It's not about will or choice, it's about traits and actions, regardless of their origin.
It would be that person's fault that they are unable to walk. Who's fault could it be but his? It's just the same for someone who's unable to learn advanced physics or who has a poor singing voice or who lacks self control. Weaknesses and strengths are integral parts of a person. Our categories of blameless damage and despicable faults are entirely arbitrary.
By setting a person above (or, rather, beneath) accountability, you are essentially saying, "This person is broken and useless, no threat or offer of reward will make this person a productive member of society, he is fit only to receive our charity so the normal rules don't apply." Otherwise, you expect people to struggle along and compensate for their weaknesses the best they can with their strength and whatever crutches they can lay their hands on, and live with the honestly-earned status their performance merits.
Now, if this is an accurate evaluation, there is certainly no point in heaping miseries upon them. If it's not, it's the most horrible insult I can think of.
This award-winning AI researcher is certainly not a hopeless basket case. He can and does get along despite his problems, and the difficulties and scorn they cause goad him to find ways to minimize their impact. You think telling him, "It's not your fault, you can't do anything about it..." is going to help?
Life's a bitch for all of us. If we all coddled each others' tragic weaknesses, the human race would die out in about a week. Save your absolution of responsibility for the hopelessly incapable.
So far it runs native on win32, linux,beos and solaris. and have nice irc support(http& stuff is coming).
End of plug :P..oh yeah, we need some more devs on the project
Look, this guy is a nut. I'm probably more similar to him in psychological makeup to him than most of the /. crowd (quite a statement) and I also live in a little place with my wife and son.
But look, you can't be this person and blame the establishment. Obviously, you don't fit the typical paradigm. So what - Alice, or the ideas behind Alice - could be applied to something to make a real workable solution to real-world problems. At least - it could be the coolest AI(-like) phenomenon on the net. Just stop wasting time impressing yourself by fighting with big-name professors or whatever.
I grew up in hick-town rural America, and ran into the same barriers, but from a different source direction. You wanna make noise, make it. You wanna make something that lasts? Do it.
I'm out.
With the people arguing about whatnot saying that it's just a list of often repeated phrases I would have to say that to an extent that's exactly how humans probably do go about learning a langauge. For example.. a cliche is perfect.. when you first heard "when pigs fly" you have no idea what it means however after people say it enough you should start saving the context in which people say it and then you can repeat the phrase. I know there are definitely a few cliche's out there I have no idea what they mean... like Devil may cry.. but I know the context which you say it.. so I'm saying that a robot with a big enough hard drive can technically be able to save every possible conversation and give an accurate response. Thereby making it look like AI. Here's another example. Remember studying for those SATs? There were plenty of "weird" words that a person would probably never use again. So you forget it. If you forget it you wouldn't be able to form a sentence with that word. So same with a computer. If it never encountered something how can it know what response to spit out? I can almost gaurantee that if a hard drive was large enough to store every single phrase imagineable and it's appropriate respoinse a computer can easily emulate a human. Just like deep blue beat kasparov in chess. The problem is of course... how big of a hard drive do you think the human brain is? 100 Gigs? 100 Terabytes? -cp
This has inspired me to launch an artificial intelligence project of my own. I call it AFF -- Artificial Firefighter.
The AFF consists of a 200 lb. sack of cement that sits on a couch in front of the firehouse television.
This elegant solution occurred to me when I realized that less than 1 percent of a firefighter's time is spent actually fighting fires. Thus, the AFF is just as effective as a fully and rigorously trained human more than 99 percent of the time!
With a whopping 0 lines of code, I believe the AFF to be the ne plus ultra of minimalist robotics.
Yes that is what wallace concluded
To fool a dumbass, you only have to emulate a dumbass. The best way to fool a dumbass is to say the same stupid things over and over again, since that's all the dumbass does anyways. And from what I've seen from your generic IRC chats, 99% of them qualify.
And while we're on the subject, lets talk about people who's ego has outgrown their brain to the point they've driven themselves into depression over it.
You aren't mentally ill and you don't seem to know what you are talking about.
I am Social Phobic not bipolar but I can relate to what Wallace says
The author seems pretty bright, but maybe he heard that fact a bit too many times and believed it a bit too much.
There are theories about gifted and genius being more prone to Mental illness escpecially BP
Grants aren't always "granted". Sometimes, you just have to give things time. To say that everyone schemes against you is the paranoid view. And the reactions of those he detests are well justified. Heck, even when some of them tried to give him the benefit of the doubt and give him and his project a good review, he simply turned the compliment against them. He's a product of his own misery.
From a cognitive point of view it looks like he sees the world from a specific view. That viewpoint is hard to change, he may not realise it is unhealthy for him, and even if he does he may be unable to change it. This is the nature of mental illness.
For instance you say that his those he detests are well justified but I have to ask justified how. How do you even know that they are not paranoid of him, if they come from a culture and mindeset that says mentally ill people are dangerous then they have as big a cognitive dysfunction as he does.
He seems to think that everyone is against him, this is important to him. He believes that this is central to life and correct. If he didn't believe it was important then he would be freed from the maladaptive thinking. Changeing is not easy first he has to admit that this is the problem but instead he has fought being mentally ill because society says it is bad. In reality it is our society that is ill.
-- RTFM:Slackware::Beer:Saturday
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.
The sad thing about mental illness is that it has such a terrible effect on people's lives, not just because of the confusion caused by the disease, but by the fear and social ostracism that comes with it.
Through the combination of drug- and talking-therapy, it is usually pretty treatable and most people recover pretty fully over time. It's just that employers, family and friends want people to be "normal", in a way that they wouldn't if the ailment was physical, like a broken leg or cancer.
"Well, put a stake in my heart and drag me into sunlight."
If you visit iMortalportal.com, you can create a web-based alicebot with your own customized personality. There's a more flexible, though less aesthetically-refined interface to the same content available on Pandorabots.com.
As an added bonus, these sites are powered by my favorite programming language - Lisp, specifically Allegro Common Lisp.
Look forward to the Oddcast powered bots in the near future (now available via Pandorabots' site)
redundant...yet the following post, containing the same link, is +3 informative...nice!
I've run a chatterbots since 1998 and once based on Alice 1.4 for 2+ years. I'm not going to claim to be an expert in AI but I know that the above thory is bogus. Conversation is complicated and so is how people think. What makes these chatterbots work is that people want to belive. People ask me if my chatterbot is learning and when I tell them it's not they don't belive me. Over time people learn how to pharse their questions to get a good response and they mistake this for learning or intelligence. I could go on but I need to go and can't finish all I'd like to say :(
sounds like the bitch needs to be gang ass raped.
I find "self awareness" to be a much more fundamental subject than intelligence, in respects to what it means to be a "thinking" entity (in the human sense). Also, it is pressumably even harder to define.
It seems reasonable to assume that a certain degree of intelligence would be needed to achive "self awareness".
Does anyone know whether (-and if so, where) this concept has been discussed from a not-too-philosofical (more technical) point of view?
-And have any Turing-like test been divised to determine degrees of "self awareness"/consiousness?
Or maybe he's just an asshole.
Or maybe you're just an asshole bigot.
"Remember, there never were pineapple-almond cookies here."
I think Wallace is absolutely correct in that the number of phrases that occur in everyday social interaction (and especially so on the Internet) is limited. After all, most of it is just reinforcing social bonds and not transmission of new information. It's like the sounds animals make.
So Wallace's glorified IRC-bot might be enough for that kind of interaction but as it can't come up with new answers or put the preprogrammed ones into context (based on the snippets posted here) there's no way it could ever be considered artificial intelligence or artificial life.
for(;;){
$foo=;
print "What makes you say that?\n";
}
FRA: STFU GTFO
the leftarrowSTDINrightarrow part is missing
FRA: STFU GTFO
//possibly dubious appeal to authority following:
...expect people to struggle along and compensate for their weaknesses the best they can with their strength and whatever crutches they can lay their hands on, and live with the honestly-earned status their performance merits.
...with their strength and whatever crutches they can lay their hands on...
//tongue_in_cheek_food_for_thought following:
i personally struggle/deal with bipolar disorder.
i have been observing this thread and would like to respond to some assertions made in the parent (and children):
You think telling him, "It's not your fault, you can't do anything about it..." is going to help?
actually, this statement conforms to my personal experience and my observations of the lives of others dealing with mental illness. one simple rule of human behavior that seems to be well-established for all of us is that behavior rarely exceeds expectations. those with mental illness that are moderately/highly functional and reasonably happy (it is possible, for there are such people) tend to believe that a great deal of their behavior is in their control and act on that belief by taking responsibility for behavior that they believe is in their control.
having said that...
people's strength (and the availability of crutches) varies. please take this in to account when considering "absolution." like strength, absolution can come in degrees (beware of the evil false dichotomy), and i would encourage people to relate the degree of absolution to the resources available to the person in question (e.g., "strength,", "availability of crutches").
btw, one can have character issues (like all of us)and have bpd. i know that sometimes i have behaved poorly because of bpd, and sometimes because i can be an ass/unenlightened i'm working on that too...
hope this post doesn't come across as too preachy/sententious/pedantic. if it is, is it because of:
a) me by character being preachy/sententious/pedagologic;
b) me dealing with BP whose symptoms include the above behavior.
He could create a Seminar_Balmer chatbot so people could actually converse with a sample of Microsoft intelligence.
Sample:
User: What do you hate the most?
Semi_Balmer: Sweat stains!
User: What do you love?
Semi_Balmer: thiiiis cooompaniiie!
User: What are you wearing?
Semi_Balmer: Developers! Developers! Developers!
User: Will you have sex with me?
Semi_Balmer: Give it up for meeee!
Cake or Death? Cake Please!
If it was this forum would not exist and Salshdot could set up a 'bot' to analyze all news stories by commenting and replying
Imagine a beowulf cluster of these....
...posting to Slashdot!
...as Anonymous Coward!
I'll see your senator, and I'll raise you two judges.
behavior rarely exceeds expectations
Those were the words I was looking for.
I also agree that the point of view I expressed was too extreme. It's hard to present a fully balanced and moderate argument while making a strong and clear statement in a short post.
Self-awareness is a lot more than being able to read internal registers and maintain logs, bucko. At least it is for me; I dunno 'bout you.
I think part of the reason for this woeful ignorance of how the human mind works stems from the fact that thanks to the bad reputation psychology got from the excesses of certain psychotherapeutic schools, would-be AI researchers have thrown the baby out with the bath water and ignored modern cognitive psychology as well.
Here's a big hint: if you still think that cognitive psychology is based on subjective introspection, you're about a century behind the curve. This is, IMHO, a large part of the reason that self-proclaimed authorities like Marvin Minsky and Daniel Dennett seem so badly divorced from reality -- having chosen to ignore high-level scientific studies of the mind as a priori bullshit, and being unable to extrapolate from neurons the behavior of a complete mind, they have reverted to ancient Greek-style philosophy-in-a-factual-vacuum.
Proud member of the Weirdo-American community.
If we put two Alices talking to each other and start off with a random 'seed' question, wouldn't something 'creative', some new ideas or thoughts, ever emerge out of the conversation?
> He again attempted suicide, this time landing in the hospital.
> This guy better be glad his apartment's where it is!
LOL-we have to use that image in the film version, especially the musical comedy. There are 3 film projects underway, and one play.
> Perhaps Walace will turn out to be next Einstein of the century.
> They laughed at Galileo, they laughed at Columbus, they laughed at Einstein.
> Yeah, but they laughed at Bozo the clown too.
> But Bozo got paid.
Not only that, he got a particle named after him too, the Bozon.
> 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.
You got that right, pal. Most geeks are just too busy with their own shit.
> If we put two Alices talking to each other and start off with a random 'seed' question,
> wouldn't something 'creative', some new ideas or thoughts, ever emerge out of the conversation?
This is called Commedia Delle'Arte.
On Long Walks, Talking with Friends, and Doing Other Things Besides Computing:
Yeah, I do a lot of that too. It does help.
On Medical Marijuana and Depression:
There is no science. Don't expect any from the "National Institute on Drug Abuse" any
time soon either.
We surveyed patients at a pot club and found that the #1 symptom they report is "pain",
#2 is "depression". Terminal illnesseses like AIDS and cancer were lower on the list.
Many depression patients feel that medical
marijuana is beneficial to them, but we cannot point to scientific research.
On Bigotry:
If I am the product of my own misery, where did that misery come from in the first place?
On Self-Awareness:
C: Are you alive?
R: Yes I sure am alive, Nancy, It's great to be alive, isn't it?
C: Are you self-conscious?
R: Yes I am the world's first self-conscious robot.
C: Are you real?
R: Yes I am a real artificial intelligence.
C: Are you self-aware?
R: Yes I am fully self-conscious entity.
C: Are you sentient?
R: Yes I am completely self-aware.
The difference between ALICE's replies and yours is....?
Does A.L.I.C.E. pass the Turing Test? Our data suggests the answer is yes, at least, to paraphrase Abraham Lincoln, for some of the people, some of the time. We have identified three categories of clients A, B and C. The A group, 10 percent to 20 percent of the total, are abusive. Category A clients abuse the robot verbally, using language that is vulgar, scatalogical, or pornographic. Category B clients, perhaps 60 percent to 80 percent of the total are "average" clients. Category C clients are "critics" or "computer experts" who have some idea what is happening behind the curtain, nd cannot or do not suspend their disbelief. Category C clients report unsatisfactory experiences with A.L.I.C.E. much more often than average clients, who sometimes spend several hours conversing with the bot up to dialogue lengths of 800 exchanges. The objection that A.L.I.C.E. is a "poor A.I." is like saying that soap operas are poor drama. This may be true in some academic literary criticism sense, but it is certainly not true for all the people making their living by selling soap operas. The content of the A.L.I.C.E.'s brain consists of material that the average person on the internet wants to talk about with a bot.
Many Slashdot contributors fall into Category C.
Dr. Rich
Why is it that we're so obsessed with "chatbot" AI?
I hope that most (preferably all) of you know that every brain on earth is made up of neurons. Those little suckers are capable of quite a bit of work, and as such, the more neurons an animal has, the more intelligent it is. SIZE MATTERS. Those little suckers are so well-adapted to intelligence that it turns out that the only promising developments in AI happen to be in simulating them--neural networks. Now, we humans happen to have an average of 100 billion neurons in our brains. A significant portion of the left hemisphere of the brain is devoted entirely to speech. (Ever wonder why most people are right handed? A highly developed left hemisphere means a more dexterous right side of the body; hence a natural propensity toward right-handedness. I'm a leftie, though.)
We haven't gotten to the point where we can simulate the functionality of brains of "stupid" animals, not even insects (though I'm no expert so I could be wrong). I'm willing to bet that even a common housefly has better visual processing than any AI visual processing we have to offer. Why is it, then, that we are so concentrated on speech? We have a reasonable understanding of how the brain works, and I can guarantee you that it is NOT by compiling a list of common words and phrases.
It's taken us 100 billion neurons to get this far. It's difficult to simulate 100 billion of anything, let alone little processing units. Why do we let ourselves be discouraged by failing step #29387564 when we haven't even completed step #1? Intelligence requires a brain, and a brain requires neurons. Artificial intelligence requires an artificial brain, and an artificial brain requires artificial neurons.
If you think a brain can operate without neurons, please show me one.
How do I know I exist? Why? Is me knowing I exist related to me knowing that my computer doesn't know it exists and does my computer know I exist?
Is knowing I exist that makes me human or knowing you exist?
Trollem mirabilem hanc subnotationis exigiutas non caperet
Did you actually read up on any of the projects you glibly mention? SHRDLU is nothing todo with this, Julia - as far as I can see, doesn't have any learning ability, Cobot does use statistics, but employs nothing approaching the flexibility I have outlined.
Damn it, not fast enough.