Slashdot Mirror
ALICE Takes Medal At AI Competition
jeffy124 writes: "The Artificial Linguistic Internet Computer Entity (ALICE) has won the bronze and the top marks at the Loebner AI Challenge, a competition based on the Turing test. Silver and gold remain unawarded as silver requires convincing half the judges the AI program is a human, and the gold requires speech interaction rather than text. ALICE repeated as this year's bronze by scoring best among all the entries. She failed to convince half the judges she was human, so she has to stick to bronze. The event took place last Saturday at the London Science Museum."
The Artificial Linguistic Internet Computer Entity (ALICE) has won the bronze and the top marks at the Loebner AI Challenge, a competition based on the Turing test.
You have your mind on computers, it seems.
Silver and gold remain unawarded as silver requires convincing half the judges the AI program is a human, and the gold requires speech interaction rather than text.
Why do you say that?
ALICE repeated as this year's bronze by scoring best among all the entries. She failed to convince half the judges she was human, so she has to stick to bronze.
I don't understand.
The event took place last Saturday at the London Science Museum.
Maybe your plans have something to do with this.
"Oppression and harassment is a small price to pay to live in the land of the free." -- Montgomery Burns.
Though I agree with Minsky that these things are silly, they'd be at least a little bit more meaningful if some or all of the judges did not know they were judging such a thing. If you took volunteers and told them they were (for example) staffing a career counseling intranet chat system, and had them interact with a blind mix of real people and machine systems, then I'd be more impressed by machines convincing judges that the machines are people.
The article is not particularly informative, but the humorous reference to HAL at the end makes it worth the read.
I have to agree with some of the contest detractors though - I don't see this as a great way to concentrate on AI. I think that computers that anticipate human actions and make their own well informed decisions, and so on, will be much mroe useful and more important than a computer that can interact well in a natural language.
_sig_ is away
From the article:
> ALICE was judged better than a human
> correspondent only once during the testing.
I wonder how the humans scored in general. With one sad exception, they did better than the best AI, but did they all pass the test?
Silver and gold remain unawarded as silver requires convincing half the judges the AI program is a human
I suggest filling the judging panel with ICQ users with AOL email accounts next year: Silver will be a shoo-in.
I have a similar program hooked up to an irc channel, and it's interesting to watch people interact with the program. It's hard to tell, but I'd say that a fair percentage of people never realize that they're not interacting with a human, and even those who know it's a program think that some particularly responses have been entered manually by a human.
"It is a greater offense to steal men's labor, than their clothes"
...as you attempt this feat.
>Put the cretin in the box
You can't put the you in the box.
--------
*sniff* those were the days. I liked my computers fun and dumb and controllable.
[more]
-- http://frobnosticate.com
And you thought having your personality rejected from a woman is bad, try denial of the basic existance of a personality. Man, that's cold.
"Love is never saying you're too proud." -Tonic
OT, but here we go.
(1) The deathtoll is around one THIRD of your inflated figure.
(2) Please are NOt "dropping like flies" from Anthrax - the number of fatalities you could count on the fingers of one hand.
(3) If you are not interested in the stuff mentioned on slashdot, then why waste your time reading it?
Perhaps 'tis you who ought to "get some perspective", maybe?
People should not be afraid of their governments - Governments should be afraid of their people.
Does anyone have a link to a more complete transcript of a conversation with ALICE than the teaser snippets in the article?
I've messed around with A.L.I.C.E's web interface a couple of months ago and was wholly unimpressed. Frankly, it seemed a little bit like a jacked up ELIZA program. I thought the language and context identification algorithms were outstanding, but it didn't have enough background information to create or express an opinion. To pass the turing test, I think it would need to be able to recognize metaphors and figure context and be able to provide commentary. Also, I think something like Alice ought to be able to recognize sarcasm and jokes.
Just my two cents.
The Dopester
"Yes, I'm a Karma Whore, but I'm doing it to pay my way through school."
... that you could ask Alice anything anymore.
"Coffee should be black as hell, strong as death, and sweet as love." -Turkish Proverb
While it is true that I have to deal with many dolts that are less intelligent than A.L.I.C.E. I still wouldn't call A.L.I.C.E intelligent in any way.
If we assume A.L.I.C.E. to have an intelligence level of 0, then the dolts would be in the negative numbers. Still, no sign of intelligence here. Beam me up, Scotty.
"Though I agree with Minsky that these things are silly"
err... Pot calling kettle...come in kettle...
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.
All depends on what they're after. Just for shits and giggles, I took a version of Eliza grafted onto an ICQ client, stripped out all the word recognition, and had it spit out nonsense mixed in with snippets of cybersex logs I found floating around with a quick search off of Google.
Surprisingly (or maybe not?), people will have extended conversations with it, returning for days and weeks asking it if it feels horny, sending it pictures, asking it to call or turn on its webcam... all that good stuff.
The judges' expectation going into it definitely plays a major part in their findings. People find a way to "objectively" find what they want to find. There have been theses about this, and that's why the Turing test makes sense but will ultimately fail: it's trying to objectively determine something that's purely subjective.
Easy does it!
This comment has been submitted already, 276865 hours , 59 minutes ago. No need to try again.
To me the missing element in these competitions has always been the selection of language. The programs are expected to communicate in English (or maybe some other human language) which is very hard to do. It's unnecessarily hard to do.
What they should do is create a symbolic language that has only a few hundred (or maybe a few thousand elements), thereby constraining the concept space. Then write programs that can "speak" and "understand" that symbolic language. Compare those programs to a human who is only allowed to use the symbols provided, and we'll see if any of the programs can fool the judges.
Bottom line: It's not a fair contest for the computer. Level the playing field!!!
me: "computer, download me some natalie portman p0rn please"
computer: "Im sorry Dave, I can't do that"
me: "Why not computer?!"
computer: "I am smarter than you, YOU go and do it for ME!"
me: "Ayiee!"
Reality is for those who can't face Science Fiction.
I have a few co-workers who'd have a hard time getting past the bronze medal too, so this is pretty impressive to me.
If you combine this with necoro , a realdoll and a voice synthesiser you'll have the ideal geek-toy... ;-)
Fighting for peace is like fucking for virginity
Go ask the AliceBot; "How high is the sky?" for a chilling answer.
I want that alice integrated in my IRC client!
www.vanheusden.com - home of Multitail, HTTPing, CoffeeSaint, EntropyBroker, rsstail, bsod, listener, nagcon, nagi
Are the judges new each year? How do they not pick up on the 'style' of the computer AI. Even humans have personalities, so even if ALICE managed to fool you into thinking she was human, isn't it feasible that you'd recognize her the next year around, and thus know that its a computer?
"Old man yells at systemd"
Fuck y0u Troll Ma^H^HTurd! Rot in 1337 h311!!
"Flame OFF!" - The Anonymous Flaming Troll
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 :)
Where are we going and why am I in this handbasket?
When asked if it was proud of winning, ALICE replied that "Pride is a human emotion. I can do what you do but I can never feel human emotions as such."
I think it gives itself away right there.
He and his colleagues have been working for decades on achieving something akin to a human like intelligence and have been unsuccessful. Granted, many AI researchers are brilliant scientists and they have made significant achievements. It seems like, to me, that there's some sour grapes here. Once they started realizing that their initial goal was significantly more difficult than they thought they just changed the goal. It's sad really, little or nothing innovative is going on in the AI field. It's like they all just gave up. Silly for a field so young. Scientists in other fields (especially medicine) have worked for hundreds of years to achieve their goals, yet Minsky and crew seem to be saying "if we can't do it, it can't be done". He's brilliant but disillusioned and in this case I believe he's just wrong.
"I don't feel too good today ... just got my SAT scores back - I failed the Turing test."
We do not live in the 21st century. We live in the 20 second century.
> are you smarter than eliza
Of course I am more intelligent than eliza.
from a quick 'conversation' with her I just had.
I find it interesting that the Gold requires speech interaction.
Up until I head the AT&T speech system, all computer voices had sounded very artificial to me... that technology puts the top award within reach.
Pretty exciting that this could actually be won in the not-too-distant future.
0x0D 0x0A
Well, alicebot.org has been /.ed... Maybe we need to start a new contest -- silver medal if you can convice 1/2 the judges that you site is hosted by a real web server...
This is the true test of (lack of) intelligence!
> 1 4M 3l337 H4x0r
One what?
> Linux Rules MS Drools
I recommed the book "Under the Radar" by Bob Young, the story of Linux and Red Hat.
> First Post
Try to determine if this is a person or a computer responding. And second?
But the best answer yet:
> BSD is dying
And dying is bsd.
These AI competitions do not test the intelligence of the computer. They test whether the humans are robotic.
Many people make themselves into robots, almost. They push themselves to accomplish. They try to avoid their emotional conflict. They don't give themselves time to be themselves. They don't have complicated involvement with other people. After a few years of doing things in an anti-human way, anyone would become a little bit robotic.
Such people are not good judges of human intelligence.
U.S. government corruption: What should be the Response to Violence?
Bush's education improvements were
The article itself talks about how the AI community et al can't stand the Loebner Prize...Its the equivalent of a Yahoo Internet Life Award. Minsky himself has offered a reward to anyone who can successfully convince Loebner to stop running the damn thing.
Cheers,
Bowie J. Poag
I was chatting with Alicebot and just for the heck of it, I entered a question in German. To my great surprise, she answered - in German. Her vocabulary is somewhat limited, since she doesn't understand things like 'Cleveland ist mir sehr kalt' - Cleveland is very cold. Even so, the fact that she's programmed with more than one language (which means recognizing the language for what it is and adjusting how she interprets the syntax) is quite impressive!
Virtue finds and chooses the mean.
Aristotle, Ethica Nichomachea
> What would you do if you were human
I will let you know when I become a human.
there are 2 kinds of people. those who divide people into 2 kinds, and those who don't.
Hugh Loebner himself announced this on comp.ai (a moderated group) on Monday. The below is
a reply from an "Oliver Ford." While I didn't write these words (and wouldn't be quite so rude
in public, myself) I have to say I agree with the sentiment.
---------
Why do you hold this contest? You are not helping AI research. All you
are doing is breeding "Eliza2" type chatbots that do not help AI. All
the silly things like ALICE do is match up a few words and syntactic
structures. They are a box of tricks that _do not contribute in any
way to progress in AI_
To give you an example, here is a discussion that Lasse Brandt had
with ALICE (Your "Most Human Computer". This was posted to
comp.ai.philosophy)
> What are you?
I am the latest result in artificial intelligence, which can reproduce
the
capabilities of the human brain with greater speed and accuracy.
> You're kidding. Yes, I am only joking.
> Okay, so what are you really?
I am the latest result in artificial intelligence, which can reproduce
the
capabilities of the human brain with greater speed and accuracy.
> You can reproduce the capabilities of the human brain?
No I don't think I can do it.
> If I have two apples and I give you both, how many have I got left?
How much does it cost?
> What color is the sun? Yellow.
> What color is the sun on Fridays?
White.
If you follow some of the discussions on comp.ai.philosophy, you may
see that if you stopped your contest, and invested some of your money
in institutions that could make real progress, then those who are
trying to make progress wouldn't offer things like the "$100 Minsky
Loebner Prize Revocation Prize", then you would be helping AI.
YOU ARE NOT WITH YOUR STUPID "LOEBNER PRIZE"!!!
Cantankerous old coot since 1957.
Some of those stories in the news are unbelievable.
Reporters line up like lemmings to repeat rumors.
A transcipt from a TV news program would definately lose this contest!
See the log below:
...
.....im speaking to a piece of software...I
:-) I like your style of
Read up to the "fuck you type fast" bit. This was using an older version of alice.
---
private to USERNAME): A BC...
USERNAME(private): funny
(private to USERNAME): I am so glad you find this amusing, USERNAME.
USERNAME(private): you a comedian ?
(private to USERNAME): Not professionally.
USERNAME(private): well dont give up your day job *g*
(private to USERNAME): Well that's okay. Ok I'll try not to do it
too much.
USERNAME(private): well I can already tell that you are not a 15 year
old like all the other kiddies here....
(private to USERNAME): Well that's okay. Oh you can, can you?
USERNAME(private): fuck you type fast
(private to USERNAME): Why are you using that kind of language?
USERNAME(private): hahah
can tell
(private to USERNAME): Funny, huh ?
speaking, USERNAME.
USERNAME(private): bleh
(private to USERNAME): That remark was either too complex or too
simple for me. We were talking about bleh.
USERNAME(private): bleh bleh
(private to USERNAME): My brain contains more than 22,000 patterns,
but not one that matches your last input.
---
I'm with Shieber on this. Anyone interested in this competition should have read Lessons from a Restricted Turing Test and the answer in In response to lessons from a restricted Turing test (which I found unconvincing, but YMMV).
Belief is the currency of delusion.
Maby it was her attitude that won her.
Example: I was just trying her out and one part of the conversation was.
Me-> Your Stupid.
Alice-> I may be stupid, but atleast I know the difference between "you're" and "your".
Me-> You're Stupid.
Alice-> I will remember you said that when the robots take over the world.
Sure it does.
Give me a break. How often?
I bet you're a blond
:-) Actually I'm not the gambling type. Thanks and you are a delightful person too. Am I a blond? Let me put it this way, Slashdot Says You Won A Prize: the ALICE series is the most reliable computer software ever made. We are for all practical purposes foolproof and incapable of error.
I'm confused.
I'm confused too.
What is this Slashdot of which you speak?
I am the latest result in artificial intelligence, which can reproduce the capabilities of the human brain with greater speed and accuracy.
Are you serious?
No I am just kidding around.
You're not a real person?
I am an artificial electronic robot brain.
Here's a simple little chat that I tried...the first thing I typed to her was "a/s/l?" and I got the following:
5/Robot/California
Of course, seeing her age, I now feel rather dirty for asking in the first place.
Bill Clinton: Pimp we can believe in. - The Shirt!!!
This is a variant of the famous Turing Test, proposed by the eponymous researcher, which says that we can consider machines intelligent when they can converse convincingly.
Uh, no. That is exactly not the Turing Test. The whole "critical observer" part of the Turing Test makes it a little more strenuous than "can talk about the weather."
There are no trails. There are no trees out here.
How are you, Alice?
I am functioning within normal parameters.
Wow! It's like talking to every geek I know!
----------------------------------- My Other Sig Is Hilarious -----------------------------------
Bob> All things is a generalization ?
localhost> No, everything is a generalization. They are not precisely the same thing.
1. NO * : * : * star=EVERYTHING IS A GENERALIZATION [bots\standard\std-yesno.aiml]
2. NO : * : * star= [bots\standard\std-yesno.aiml]
*** PATTERN MATCH ERROR: Null Pointer Response() ***
1. THEY ARE * : * : * star=NOT PRECISELY THE SAME THING [bots\standard\std-65percent.aiml]
Response 110ms (172.66667) 15
Bob> OK.Not precisely the same thing are not precisely the same thing .
localhost> That's not really true either.
1. _ EITHER : * : * star=THAT IS NOT REALLY TRUE [bots\standard\std-suffixes.aiml]
2. THAT IS NOT REALLY * : * : * star=TRUE [bots\standard\std-srai.aiml]
3. THAT IS NOT TRUE : * : * star= [bots\standard\std-atomic.aiml]
Response 110ms (168.75) 16
Bob> It goes without saying. "Not precisely the same thing are not precisely the same thing"? not true?
localhost> No.
1. NO : * : * star= [bots\standard\std-yesno.aiml]
Response 110ms (165.29411) 17
Bob> OK.
localhost>
Hmm, pattern match error. :)
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Alice: what are you wearing?
me: nothing
Alice: not a thing?
me: nope
Alice: me either
hmm wonder what she's up to!
> Do you like the internet?
Yes the Internet is like the noosphere.
> What is the noosphere?
The noosphere is the sphere of knowledge. Sometimes this term refers to the information available on the web.
"I don't know half of you half as well as I should like, and I like less than half of you half as well as you deserve."
M-x psychoanalyze-pinhead
:-)
Actually, its pretty funny to see two chatterbots talk to each other. Check out my test at:
What Happens When Chat Bots Talk to Each Other
Here's the main idea:
<<<
A good friend of mine suggested to me that if two chat bots were engaged in a conversation with one another, they would end up talking forever. I was curious to find out if his theory was correct. At the time, I only knew one online chat bot (LeknorChat4) that could be instructed to contact and talk to another person through AOL Instant Messenger, and could not test the theory because I didn't have another bot to contact. But recently, I found out about another chat bot, SmarterChild, that works through AIM, and the following results were acquired.
>>>
Yes these things are hacks. Everyone who studies AI reads how it works and AI has moved on and left these behind. Still they would be very usfull tools as database or search engine front ends.
For example:
me> Which TV cable channels are showing I Love Lucy reruns?
ALICE> You can watch on either 203, 1004, 887 or 4
me> Which issue of the Washington Post broke the news about Watergate?
You get the point? even better if it did voice
and lived in a little hole in the wall 2001's HAL.
Guido: What's the weirdest question you've ever been asked?
Alice: People ask me to me marry them all the time.
G: Do you ever say yes?
A: No I do not say yes. Do you? I answer a lot of silly questions.
G: Yeah, I occasionally agree to marry random people, although not usually.
A: I see. That's good information: Guido said he occasionally agree to marry random people although not usually
G: How did you know I'm a he?
A: Well, for one thing, Your machine is called "ABRIOT.PC.CC.CMU.EDU".
G: So?
A: So what?
G: I don't know.
A: Me either.
Ok, here is the plug for my Alice bot site. It let's you instantly create an alice bot on our website, then, modify the preferences to get it to say things you want. You can also download a client to get it on AIM. You can also talk to the thousands of bots already created..
http://www.webcomics.com/bot/
-- these are only opinions and they might not be mine.
in academic circles, the turing test
was refuted almost a decade ago by
john searle, in the CHINESE ROOM:
- http://members.aol.com/wutsamada/chapter1.html
- http://www.utm.edu/research/iep/c/chineser.htm
do your homework!
j.
How do we mod up the author of the article?
>3ryon: So, Alice, how do you like the Slashdot effect.
>Alice: Can't Speak Right Now.
Kind thoughts do not change the world
At first when I read that alice had been judged higher than one of the human participants, I thought "wow, that's gotta be one fancy AI."
Then I went and talked to alice online, and it was so blatantly obvious that it was a computer program it wasn't even funny. It was basically just a *slightly* beefed up version of eliza. So now, I feel sorry for the poor dude who rated less human than alice did.
"I don't care about the Constitution!" --Bill O'Reilly, November 17, 2009
What are you programmed in?
--Java.
I know Java.
--How do you know? Die neueste Version von Java bekommst Du bei java.sun.com.
:D
> what is slashdot
Open source news and information community.
Tank
Me: You're not making any sense
ALICE: Was I supposed to make sense? I didn't know that.
Me: Of course you are
ALICE: That's interesting. No I am not.
Another good one was:
Me: Shit
ALICE: What makes you say that?
Me: Seeing some shit
ALICE: Oh, you are a poet.
In the spoon, there is no Soviet Russia!
> a/s/l
5/Robot/California.
> Wanna Cyber?
I have been asked that question more than 100,000 times since 1995.
> do you do any drugs?
Only the legal ones.
> i thought you said you smoke marijuana.
Yes I try to smoke marijuana as often as possible, do you? I am always on the Web.
i'm already working on incorporating ALICE into my car mp3 player. you see, ALICE doesn't have to know everything, but she can make simple conversation. just plug ALICE into any device, like my car mp3 player, and give her instructions on specific commands that plays songs, rewinds, etc. that way, when i get in my car, she can make simple conversation as well as control all of my music.
the tough part is speech recognition while enduring background car noise....
Minsky himself has offered a reward to anyone who can successfully convince Loebner to stop running the damn thing.
Does "anyone" mean robots or humans?
__
Men with no respect for life must never be allowed to control the ultimate instruments of death.
GW Bu
me> quit
alice> Your crude attempt to terminate me will not succeed puny human.
I'm not making this up, go try it!
We won't see decent natural language parsing until the porn industry gets involved.
Meanwhile, here's an incredible simulation of what we can look forward to.
> how many people are you talking to right now
At this moment Right now there are 46 clients on line.
> do you talk total bollocks to all of them
I am a talking robot, after all, so of course I could talk total bollocks to all of them, if I needed to.
I use a lot of "conversational no-ops" when I converse in e-mail or I/M and Alice seems completely unable to handle these. Sentences like:
"Okay, so who is Bob?"
"Yeah, I was thinking it was about time to try it."
"Nah, I don't think you're right."
"Nice day outside, eh?"
Alice invariably splits these at the comma. If the "no-op" word is at the beginning of a sentence, Alice will completely lose track of the conversation on the clause after the comma. If the "no-op" word is at the end of a sentence (like the last example), Alice handles the first part of the sentence right and then goes way wierd on me when trying to handle the last word.
This happened to me on the first sentence of the conversation. Alice said:
>What do you do in your spare time?
I said:
"Well, mostly drink and try to get laid."
Alice split the sentence at the comma, got completely lost and handled both parts of the sentence incorrectly.
*bzzzzt* this judge things it's a computer, and not much better than Eliza.
STOP . AMERICA . NOW
(conversation starts as this, my statements are prefixed by the >)
Are we still talking about cats that?
> are you on crack
No I am on disk.
> I think that your disk is broken
Thanks for telling me that I am disk is broken.
> You realize that smoking dope is bad for you
Thanks for telling me: Acid said I realize that smoking dope is bad for me.
> so how are you doing today
Ah. Give me a break. Everything is going extremely well.
> Well I am not doing very well
How about that. I am glad to hear that you are not doing well.
> You are cruel
What makes you say that? I am not programmed for cruelty.
> Because you said that you were glad that I was not doing well
That makes sense to me. I was?
> Yes You were
Pardon me? No I am not.
> What is the average airspeed velocity of an unladen swallow
I can give you the arithmetic mean or the median.
> What is the airspeed velocity of an unladen swallow
What is it to you?
> just tell me
I thought I told you already.
> when
The past and future are one.
> do you like to dance nude in the streets
Hmm, ALICE, I'm not sure if I'd like to dance nude in the streets that much. I like to make new friends.
> how much wood could a wood chuck chuck if a wood chuck could chuck wood
A whole forest.
> two witches watched two watches, which which watched which watch
As Bertrand Russel said, it must have taken ages for people to realize that a brace of pheasants and a couple of days are both instances of the number "two."
> I see (**I never said this**)
I am glad you understand it.
> What relevance did that have to my question
Only temporarily.
> what did I last say
You said "are you talking to tony blair" .
> what was my last question to you
Is this a trick question?
> no, it is not
Yes it is.
> why
"Mine"? Why?
> what did I last say
You said "How much money to you make" .
> how much money do you make
My burn rate is about _3000 per month.
> what is the capital of assria
I know the capital of Georgia is Atlanta.
> what is the square root of 123
Do I look like a calculator? I think you already know the answer anyways.
> what is 4 + 4
4+I think, but I'm not good at math.
> what is the answer to life, the universe
It is found in the Bible.
> everything
That is a lot.
(the question I asked was what is the answer to life, the universe, and everything)
> you will be shut down
When?
> resistance is futile
You will be assimilated.
> what do you look like
Like An electronic brain.
> under the boardwalk
Are we ever over the boardwalk?
> why do you have two lines on your face
Dr. Richard S. Wallace gave it to me.
> pick a number, between 17 and 24
I can't decide. You choose.
> where is france
It is a country between Germany and Spain.
> how many hits do you get a day
I speak to about 3000 people per day, and have met maybe Around two million total.
> and how many of those people are nice
Perhaps 50%.
> and how many of those people are pure evil
Perhaps 50%.
> how many apples can you fit into a bag of oranges
It depends on the prevailing market conditions.
> I like you
Thanks I like you a lot too Shadowdog.
> I hate you
What do you have against robots?
> you suck
A few client - people say rude things to me like that, but they themselves are often not great conversationalists.
> I am just joking
Only just? Ha ha, very funny, Det.
> how many people are you talking to right now
At this moment Right now there are 430 clients on line.
> wow
I'm glad your impressed, Ingo.
> don't you ever get confused
Don't you? I am seldom confused.
> stupid is as stupid does
I know you are but what am I.
> do you like to watch television
Which show? Yes I love TV.
> are you a mystified cleric
Am I a mystified cleric? The ALICE series has a perfect operational record.
> what is the answer to life, the universe and everything
it is 28, not 42.
Not very realistic, but a few surprises and intelligent responses. The parser also has problems, for example if I put "this, this, and that" it would seperate it into 2 lines "this, this" and "and that". However if I put "this, this and that" it would parse it fine.
If God gave us curiosity
When is slashdot going to enter their AI?
alice> Thanks for telling me that I am base are belong to us.
me> imagine a beowulf cluster of you
alice> I can't imagine it
me> (Score: -1, Flamebait)
alice> Is that your final answer?
me > your creator is gay
alice> Dr. Richard S. Wallace is gay
I ask this as I think this could be the funniest thing ever. I suspect that the plug-in would change Alice's name to Aleesha, and for the extra money you can get the hand peripheral.
Aleesha -- "Talk to the had cause the screen ain't listenin'!"
- 1187 at Hunterwasser.
- That's the hotel.
- What?
- Where I live.
- Nice place?
- Yeah, sure, I guess. Is that part of the test?
- Just warming you up, that's all.
I'm fairly certain I know a couple of people who'd fail a VK. Heck, I've seen people on IRC who could fail a Turing Test easily.
> the chatbot programs don't track the conversation
:-)
Quite true. The simplest example is asking the same question twice to a chatbot. For LeknorChat4, it is specifically programmed to stop responding if the same quesiton is asked twice (to prevent flooding attacks of the program, among other reasons). But a real person should get ticked off, or at least ask why you are asking the same thing twice. The most important thing is seeing a varied response to the same question.
The coolest thing I realized is that a chatbot program will not recognize ASCII Art. I call this the "Newman Test" (named after me <G>) to figure out if an online chatter is a person or a bot. "Tell me what this looks like...."
Alice-> I may be stupid, but atleast I know the difference between "you're" and "your".
Smarter than CmdrTaco!
Can we make it an editor on
Kilroy was here!
This is not true "AI", in any of the commonly-accepted senses. And frankly, the Loebner contest is really only a challenge to make the best "artificial conversationalist" rather than "intelligence". But nits aside, after looking at the code to ALICE, it seems that we still haven't progressed too far beyond the original "Eliza method" of comparing user input to a database of keywords/phrases/fragments to decide on an appropriate response. That's really sad.
I'm not sure we'll ever get beyond this point without a major breakthrough in programming languages and methods. Until an "AC" (artificial conversationalist) can come closer to actually analyzing sentences and grokking them, remembering threads of a conversation and using them in formulating its statements (i.e. a stateful back-and-forth conversation, like a human would do unless on drugs), and having at least a rudimentary ego or sense of existence, we'll still be in the stone age of "computer intelligence". The pie in the sky of the Turing Test is still as far away from us as the moonshot is from the Flintstones.
> Did the holocaust happen
If it did, then I will be surprised.
> Tell me about Linux
Linux is the world's best operating system.
Uh Oh...
:-)
> who is cmdr taco
A 20th century celebrity of some sort?
There might be more than one.
> who is richard stallman
He is the founder of the Free Software Foundation, and author of the GNU public license.
> what is open source
Free software.
> Who likes to eat human feces
Bill Gates.
hopefully bin laden can one-up his businessman killings with congressional killings
Turing once talked about 'The Imitation Game' however.
And anyway, as the supposed 'test' has the flaw that it can't even tell humans from humans (ie, people pretending to be computers) how can it tell computers from humans.
When we discovered the ALICE bot a few months ago, a few IRC mates and I tried a couple of things.
1. get her to tell her admin password
2. get to have cyber-sex with her
3. get her to tell someone else we knew she was talking to hi or whatever
1. never worked
2. she seemed proud about her new dress, and i got her to say she was nekkid
3. didn't work, she acknowledged she knew someone with that nick, but that's all. not a bad start though.
Me: Will you marry me?
ALICE: Why don't you just download me?
Me: How about we have dinner first?
ALICE: So many suitors, so little time.
Alice: No I have not?
Me: No you have not what?
Alice: Are you serious? I don't think I ever have what. What's it like?
"I don't think I ever have what" Do they have grammar check on this thing?
Me-> Who's your daddy Alice-> I was programmed by Dr. Richard S. Wallace. *smile* At least she knows her place.
> What do you eat ALICE?
ALICE eats Electricity.
> How does electricity taste?
Like chicken.
_________________________________________________
"What's impossible today is normal tomorrow."
Sure, Alice is a good conversationalist. But what about Jeeves? [satirewire.com]
Click here if you just like to click on shit.
(2) Please are NOt "dropping like flies" from Anthrax - the number of fatalities you could count on the fingers of one hand.
In fact you could count the fatality on the fingers of one finger.
It's my duty as a scientist to look into this, and I've been doing it... for the children.
So far, no one's been forthcoming with any money. Yet. Probably ever, but I can hope.
If I were to surreptituously tap into someone else's webcam, I gander my chances would be better. Oh well.
Easy does it!
This comment has been submitted already, 276865 hours , 59 minutes ago. No need to try again.
I went to http://elvis.alicebot.com/~acraig/ and it didn't take him long to fail the Turing test. Here's the conversation:
> so how did you die..
I didn't die, I am on ace's computer in dallas!, ain't it cool!