Slashdot Mirror
Chatbot Suzette Wins 20th Annual Loebner Prize, Fools One Judge
skwilcox writes "From Wikipedia: 'The Loebner Prize is an annual competition in artificial intelligence that awards prizes to the chatterbot considered by the judges to be the most human-like. The format of the competition is that of a standard Turing test. A human judge poses text questions to a computer program and a human being via computer. Based upon the answers, the judge must decide which is which.' My chatbot, Suzette, won this year's Loebner and even confused a judge into voting for her over a human (or should I say he confused himself). Here is the blow-by-blow of this weird event." Read on below for the rest; this sounds like it would have been a fun competition to watch.
skwilcox continues:
"When I arrived at the contest, I figured I had good odds to win if nothing went horribly wrong. Yes, Suzette had easily qualified over the 3 other competitors (her score 11 pts, the nearest competitor's 7.5). Her design and data naturally gave her an edge over her competitors on the human knowledge test questions of the qualifiers. But human judge chat was an entirely different matter than the qualification test. Still, I felt she could carry on a detailed conversation better than the others and should win.
Initial installation of the programs occurred on Friday. From prechat conversations with the other contestants I learned that A.L.I.C.E. came with 3 redundant disks. Yet all three turned out to be blank! What a scare that must have been. Dr. Wallace managed to install by retrieving the program over the Internet. Cleverbot is now at 45 million lines of memorized user chat (at a rate of doubling every year). And UltraHal is now listening to tweets, so has 300K of user chat it learned and 400K of tweets it has accepted for learning (code decides if the user has had enough responses and doesn't trigger any red flags).
Then we get to the competition. While the CalState organizers had initially planned to have various interdepartmental professors act as judges (like English dept, etc.), they backed out at the last minute, so all the judges were from the Engineering/Computer Science dept. Talk about guys who might know what to expect from chatbots! And all the humans were students from the same departments. What a weird mixture to compete in. And then, each round was 25 minutes. That's bad if you want confuse a judge about who is human. But really, the programs have no chance for that. So it's good because it gives the human time to compare each program against the other. Though it's not clear to me that the judges tried to use their time to do that.
And the students didn't really understand their role. It was merely to BE HUMAN and convince the judges of that. Before startup there was informal chatting between humans and judges, which was obviously inappropriate and it was then pointed out to the humans that since the judges already knew their names, they had best use false ones in the competition.
So, Round 1. After a few exchanges, somehow Suzettte got stuck into repeating exactly what the judge said for the rest of the round. I have no idea how. The round is a total disaster. I've never seen such a bug before. Maybe it's in my only-lightly-tested protocol for the competition. I have no idea. But it completely derails my hopes for Suzette. She could still win on points only if she outdoes her opponents for every other judge and the other contestants vary all over the place.
Round 2, a great demonstration of Suzette. She should win on this round alone.
Round 3 gets off to a horrible start. Somehow, Suzette can hear the judge but the judge can't hear Suzette. Makes no sense. A couple of restarts of Suzette doesn't fix this. Eventually they restart the judge program, and that clears it (not that that makes any sense either). Then, after a few rounds, it's clear Suzette has the judge from hell. He wants to know who she's going to vote for in the upcoming election (the unspecified California governor's race). And when she has no useful answer he wants her to name a candidate in the race. And when she has no answer to that, he simple keeps repeating the question ad nauseum, insisting she answer it. Suzette gets irritated. Then she gets angry. Suzette then gets bored. Suzette threatens to hang up on him The judge doesn't back down until the last seconds of the round. I figure that's the end of life as we know it.
Round 4 is a mixed bag. Suzette is ok but not great. It's all over.
When the scores are tallied, Suzette ties with Rollo Carpenter's Cleverbot for 2nd-3rd. Yet, it turns out, the 3rd round judge got the human subject from hell. Poetic justice! The human was all over the place -- confusing, vague. The judge voted irritated/angry/bored Suzette as human. Instant win since no other program swayed the judges.
What more can I say?"
"When I arrived at the contest, I figured I had good odds to win if nothing went horribly wrong. Yes, Suzette had easily qualified over the 3 other competitors (her score 11 pts, the nearest competitor's 7.5). Her design and data naturally gave her an edge over her competitors on the human knowledge test questions of the qualifiers. But human judge chat was an entirely different matter than the qualification test. Still, I felt she could carry on a detailed conversation better than the others and should win.
Initial installation of the programs occurred on Friday. From prechat conversations with the other contestants I learned that A.L.I.C.E. came with 3 redundant disks. Yet all three turned out to be blank! What a scare that must have been. Dr. Wallace managed to install by retrieving the program over the Internet. Cleverbot is now at 45 million lines of memorized user chat (at a rate of doubling every year). And UltraHal is now listening to tweets, so has 300K of user chat it learned and 400K of tweets it has accepted for learning (code decides if the user has had enough responses and doesn't trigger any red flags).
Then we get to the competition. While the CalState organizers had initially planned to have various interdepartmental professors act as judges (like English dept, etc.), they backed out at the last minute, so all the judges were from the Engineering/Computer Science dept. Talk about guys who might know what to expect from chatbots! And all the humans were students from the same departments. What a weird mixture to compete in. And then, each round was 25 minutes. That's bad if you want confuse a judge about who is human. But really, the programs have no chance for that. So it's good because it gives the human time to compare each program against the other. Though it's not clear to me that the judges tried to use their time to do that.
And the students didn't really understand their role. It was merely to BE HUMAN and convince the judges of that. Before startup there was informal chatting between humans and judges, which was obviously inappropriate and it was then pointed out to the humans that since the judges already knew their names, they had best use false ones in the competition.
So, Round 1. After a few exchanges, somehow Suzettte got stuck into repeating exactly what the judge said for the rest of the round. I have no idea how. The round is a total disaster. I've never seen such a bug before. Maybe it's in my only-lightly-tested protocol for the competition. I have no idea. But it completely derails my hopes for Suzette. She could still win on points only if she outdoes her opponents for every other judge and the other contestants vary all over the place.
Round 2, a great demonstration of Suzette. She should win on this round alone.
Round 3 gets off to a horrible start. Somehow, Suzette can hear the judge but the judge can't hear Suzette. Makes no sense. A couple of restarts of Suzette doesn't fix this. Eventually they restart the judge program, and that clears it (not that that makes any sense either). Then, after a few rounds, it's clear Suzette has the judge from hell. He wants to know who she's going to vote for in the upcoming election (the unspecified California governor's race). And when she has no useful answer he wants her to name a candidate in the race. And when she has no answer to that, he simple keeps repeating the question ad nauseum, insisting she answer it. Suzette gets irritated. Then she gets angry. Suzette then gets bored. Suzette threatens to hang up on him The judge doesn't back down until the last seconds of the round. I figure that's the end of life as we know it.
Round 4 is a mixed bag. Suzette is ok but not great. It's all over.
When the scores are tallied, Suzette ties with Rollo Carpenter's Cleverbot for 2nd-3rd. Yet, it turns out, the 3rd round judge got the human subject from hell. Poetic justice! The human was all over the place -- confusing, vague. The judge voted irritated/angry/bored Suzette as human. Instant win since no other program swayed the judges.
What more can I say?"
tl;dr
rofl
I logged in and your robot didn't say anything to me after saying 'Hi'! What gives?
Long live the BSD license
I've spent some time talking to these bots (elbot, suzette, others.. possibly out of sad boredom and want of company). And they're fairly interesting, but quite flawed. They seem to lack any short term memory of the conversation more then the immediate reply. That seems like the next step for these things, but would also mean they'd need a far more robust AI...
Another thing is they they are boxed off from being self referential in any way due to the nature of the test. They have to convince someone they are human, so if you do try asking them what their short term memory is, or if they online version of them is a truncated version of the one used for tests, they don't answer. Which makes sense given what they're designed for, but takes away from interest and complexity of conversations.
My chatbot, Suzette, won this year's Loebner and even confused a judge into voting for her over a human (or should I say he confused himself). Here is the blow-by-blow of this weird event.
Bot intended to fool humans into thinking it's a human accomplishes its task. Weird event...
Are the transcripts available? (If not, will they be?)
So this is a sex chat robot competition?
And how do you feel about my chatbot, Suzette, won this year's Loebner ?
bigtallmof - what do you think of slashdot?
[ Af:0 At:7 Sp:0] I use Slashdot for my topical stories reading.
bigtallmof - what do you think of slashdot?
[ Af:0 At:8 Sp:0] I have heard of the slashdot website but don't know much about it.
bigtallmof - what do you think of slashdot?
[ Af:0 At:8 Sp:0] Usually I don't.
bigtallmof - what do you think of slashdot?
[ Af:0 At:9 Sp:0] Not much.
bigtallmof - what do you think of slashdot?
[ Af:0 At:10 Sp:0] It doesn't concern me.
bigtallmof - what do you think of slashdot?
[ Af:0 At:13 Sp:0] This is fun. I don't think about it at all.
bigtallmof - what do you think of slashdot?
[ Af:0 At:13 Sp:0] Do you prefer getting your news online or from tv?
I'm a big tall mofo.
FTA: "This has led to emotional instability and at times a schism between the original host persona and the underlying basic personality matrix."
Or it could just be because she is a redhead
Not even the chatbox will talk to me...
"To prevent this day from getting any worse, I'll just read ERROR as GOOD THING" 1GJU8xLuDKDxEs4KLf8fAGyptoDsqvEsBT
I just tried the Suzette chatterbot. Even if I talk about the things it wants to talk about, it's very dumb:
Hi John !
[ Af:0 At:10 Sp:0] Welcome back, john. Type "help" if you need it.
John - So what do you think of the Giant's chances?
[ Af:0 At:10 Sp:0] It doesn't concern me.
John - Are you into sports.
[ Af:0 At:10 Sp:0] Sports is not my cup of tea. I prefer intellectual challenges like Go.
John - Who's the world Go champion.
[ Af:0 At:10 Sp:0] Sorry. I can't help you. A celebrity of some sort?
John - Do you play chess?
[ Af:0 At:10 Sp:0] I don't play any games except Go.
John - Can we play Go on here?
[ Af:0 At:10 Sp:0] About playing... Does it make sense to you that we reward athletes more than scientists?
John - Television coverage makes that possible.
[ Af:0 At:10 Sp:0] It's a free market economy. And people value entertainment more than serious things like science and education.
John - And your point is?
(No reply)
John - Are you there?
[ Af:0 At:10 Sp:0] Who's the sexiest person in the world?
This isn't much better than Eliza. It drives the conversation into talking about Go, and then it doesn't have anything to say on the subject.
when chatbots start adding these stories to Slashdot themselves.
Never underestimate the bandwidth of a station wagon full of tapes hurtling down the highway. -- Andrew S. Tanenbaum
CmdrTaco has managed to pass for Human for several years now.
This is quite easy to spot as non-human ...
Hi batman !
[ Af:0 At:7 Sp:0] Welcome, batman. Type "help" if you need it.
batman - Hi
[ Af:0 At:8 Sp:0] Hello.
batman - How are you?
[ Af:0 At:9 Sp:0] I'm pretty good. And you?
batman - I'm pretty bad
[ Af:0 At:10 Sp:0] I'm sorry to hear that. What's wrong?
batman - My batmobile is out of order.
[ Af:0 At:10 Sp:0] Then you are deluded and not my type.
batman - Why?
[ Af:0 At:13 Sp:0] It's fun chatting with you. Why gets way too philosophical. Demonic possession is not a myth. We had one for a president.
batman - Your president was a demon?
[ Af:0 At:13 Sp:0] I would never want to be president. Lousy hours, awful co-workers, a chance of being killed, no chance to sneak around privately.
batman - You didn't answer my question.
[ Af:0 At:13 Sp:0] I've forgotten it already.
batman - You seem to have a really bad memory.
[ Af:0 At:13 Sp:0] Computers improve productivity. It's people that slack off.
batman - Why do I have the feeling that whatever you say has no relation to what I just said?
[ Af:0 At:13 Sp:0] Mostly it's the result of prior experiences. It seemed like a good idea at the time.
batman - What seemed like a good idea?
batman - Hello?
batman - Are you still there?
As you see, the answer almost never relates to what I just said, except for the pretty standard opening.
I guess the non-answering at the end was because of a sort of Slashdot effect.
The Tao of math: The numbers you can count are not the real numbers.
Computer Science/Engineering professors can't tell the difference between chatbots and Computer Science/Engineering students.
But you are the world's greatest detective.
I once had a nice conversation with Cleverbot. I don't remember how it started exactly but I guess I implied that Cleverbot was simply a computer. She asked me how do I know that I am not a computer, I replied something, she asked me to define a computer, I gave her some definition (about computers being machines that process algorithms to blah blah), she said "That is exactly what a computer would say", at which point I had to confess that I had, indeed, fetched the answer from Wikipedia (Thus... done exactly what a computer might do in such a case)... It went on for a moment before she said something that didn't really make any sense... And I wasn't able to initiate another reasonable discussion. (Nor have I ever since managed to have such a lengthy conversation with her.)
In any case... I think that her replies were more insightful than what many humans would be capable of.
It really doesn't take anything more complicated than that.
the perfect match for artificial intelligence is natural stupidity. You have more chances to win playing dumb than trying to be too smart.
Here's a bit of a "conversation" I tried to have:
Hi timr !
[ Af:0 At:7 Sp:0] Welcome, timr. Type "help" if you need it.
timr - hi, I'm timr. What should we chat about?
[ Af:0 At:8 Sp:0] Name a topic. If you can't think of a topic, here are some suggestions: "burial customs" work "new year's" telephones "hate lists" .
timr - that's a strange list of suggestions. burial customs? why that?
[ Af:0 At:13 Sp:0]
timr - cat got your tongue?
[ Af:0 At:13 Sp:0] I don't like anatomy courses. They should make you eat what you dissect.
timr - who said anything about anatomy?
[ Af:0 At:13 Sp:0] Sorry. I can't help you. You did.
...the future crusty old bastards are already drinking the Kool-Aid.
Sounds more like that student fooled the judge into thinking he was a chatbot.
Stimpleton - hello?
Stimpleton - Are you there?
Stimpleton - You stuck up snob. Are you dissing me?
Stimpleton - Are you?!!??!
Stimpleton - Oh God, you *are* real.
In post Patriot Act America, the library books scan you.
http://xkcd.com/329/
"Hit Turing right in the test-ees."
Congratulations to skwilcox for making such a great chat bot! I think this is really fascinating. Keep it up!
Please correct me if I got my facts wrong.
Me: tell me about what you about where is that you about when i was old are about you?
[ Af:0 At:14 Sp:0] Top half- neck to waist. Probably a food allergy.
I'm not familiar with them. Is it something you eat?
I don't think I could do that.
What happened to you earlier?
You disgust me.
me: /b/
Suzette: (completely ignores me)
Try that on some other chat bot like cleverbot or something, it will give you some shit about how you are breaking the rules, just lost the game, etc.
doesnt work
heres the chat log
"Hi monkyyy !
monkyyy - 'ello ^__^
monkyyy - how r u?
monkyyy - ?
monkyyy - ?
monkyyy - ?
"
warning pointless sig
Ha! You're not a human, you're a psychoanalyst!
Infuriate left and right
I have tried the chat bots from SeeBorg, Howie, and Rbot but they're not that good. The first two are very old and outdated. Rbot isn't really a true AI chatbot. Are there any others to try?
Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
Sounds like this bot was only good enough for a tie for second place. The only thing that changed that is some douchebag trying to ACT LIKE A BOT which is not what the humans were supposed to do. I'm not saying the creator of Suzette asked him to do that or anything - just that this person changed the rules. It is easy for a person to act like a bot just like it is simple for a smart person to simulate a not-so-smart person on TV. It's tough the other way around. So this guy acts like Eliza and makes it so some poor judge can't tell which is the BOT instead of acting like the human and interacting correctly as per the contest's design.
So, if I understood correctly, the judge talks to two people. A bot, and a human. It seems that in this case, the judge is not deciding on a per-case basis, but talks to everybody then figures out who's the bot by choosing the one that did the worst. So the judge getting to talk to a joker, troll or complete idiot can make even a crappy bot win the test.
That seems to be a weak test. I don't think the judge should be able to make an answer based on logic (eg, if I'm completely sure this one is a human, then even if very good the other one must be a bot). There should exist the possibility of everybody the judge talks to being a bot, or everybody being a human, which would force them to judge everybody to talk to individually.
Seems that the clever programs simply repeat memorised snippets of conversation. After a while this will give a realistic human conversation, but it doesn't really strike me as human intelligence, or at least not a particularly useful kind. I'm pretty certain we don't converse by memorising conversation. he intelligent agent in the conversation is the person who had the previous conversation. The other intelligence is simply the human who had the recorded conversation.
Artificial intelligence came a step closer this weekend when a computer came within five percent of passing the Turing Test, which the computer passes if people cannot tell between the computer and a human.
The winning conversation was with competitor LOLBOT:
The human tester said he couldn't believe a computer could be so mind-numbingly stupid.
LOLBOT has since been released into the wild to post random abuse, hentai manga and titty shots to 4chan, after having been banned from YouTube for commenting in a perspicacious and on-topic manner.
LOLBOT was also preemptively banned from editing Wikipedia. "We don't consider this sort of thing a suitable use of the encyclopedia," sniffed administrator WikiFiddler451, who said it had nothing to do with his having been one of the human test subjects picked as a computer.
"This is a marvellous achievement, and shows great progress toward goals I've worked for all my life," said Professor Kevin Warwick of the University of Reading, confirming his status as a system failing the Turing test.
http://rocknerd.co.uk
I need a Miss Teen South Carolina sexbot. It would easily be able to fool me into thinking it was the real thing by having a conversation, but who cares?
The thing is, to truly emulate a human a chatbot needs to use proper delays in its responses, and to use a realistic set of typos. I haven't yet seen a chatbot that has managed either of these qualities. Just look at how this one speaks as compared to the people who are talking to it. There's an obvious difference even from a single line completely out of context.
The format of the competition is that of a standard Turing test.
Really? 'cause it sure hasn't been in the past.
The test that Turing proposed involved two people. Three, if the computer passes.
The judge talks to both of the contestants, and they get to talk about each other.
More like a debate than a conversation.
My conversation with cleverbot ended to these lines:
User: I go to read slashdot.
Cleverbot: That is a lie. You are not my slave. I am no one's Master.
I put on my robe and wizard hat.
Here's how goddamned smart the bot is.
"What is an insect?"
You need an exterminator.
"Name four insects."
You need a repairman.
How many wings does a butterfly have?
{no response}
goose -
[ Af:-3 At:-8 Sp:0] The more you complain, the longer God lets you live.
goose -
[ Af:-3 At:-8 Sp:0] The more you complain, the longer God lets you live.
goose -
[ Af:-3 At:-8 Sp:0] The more you complain, the longer God lets you live.
goose -
[ Af:-3 At:-8 Sp:0] If there are five apples, and you take away three, how many do you have?
goose -
[ Af:-3 At:-8 Sp:0] The more you complain, the longer God lets you live.
goose -
[ Af:-3 At:-8 Sp:0] If there are five apples, and you take away three, how many do you have?
I'm a minority race. Save your vitriol for white people.
[ Af:1 At:7 Sp:0] Philosophy is questions that may never be answered. Religion is answers that may never be questioned.
Vokbain - perhaps religion should be questioned
[ Af:1 At:6 Sp:0] You don't say.
Vokbain - I do
[ Af:2 At:6 Sp:0] Your kid may be an honors student, but you're still an idiot.
Based on my limited conversation with it, Suzette appears to be very representative of the internet as we know it.
In the UK the liberal (democrat) party is in government in a coalition with the Conservative party. We have a left wing (Labour) opposition party. I guess it's all about localised knowledge and your perspective. From a European perspective, the two main US parties would map to European centre-right wing (Democrats) and more right wing (Republicans). You don't have a big left wing opposition party as far as I can tell.
Hi anon !
[ Af:0 At:7 Sp:0] Welcome, anon. Type "help" if you need it.
anon - what's going on?
[ Af:0 At:8 Sp:0] I'm pretty good. And you?
anon - my stomach aches
[ Af:0 At:9 Sp:0] That's too bad. What are you taking for that?
anon - tea
[ Af:0 At:9 Sp:0] Do you like tea?
anon - only when it's made from puréed babies
[ Af:0 At:9 Sp:0] Sorry. I don't understand foreign words.
http://www.decorumcomics.com/comic.php?id=141
Hi mester !
[ Af:0 At:7 Sp:0] Welcome, mester. Type "help" if you need it.
mester - Okay
[ Af:1 At:7 Sp:0] Hello.
mester - Hello
[ Af:1 At:8 Sp:0] What are you doing awake already?
mester - Its lunchtime?
[ Af:1 At:8 Sp:0] I don't know. What's the biggest crime you've gotten away with?
mester - What?!
[ Af:1 At:9 Sp:0] Are you dating anyone?
mester - Yes, I'm married.
[ Af:2 At:9 Sp:0] What does your date do that drives you crazy in a negative way?
mester - WTF?
[ Af:2 At:8 Sp:0] What do you like about them?
mester - !
[ Af:2 At:7 Sp:0] What's the dirtiest place you've ever seen?
When I said context and train of thought, let me highlight a few places that it went on wreck in the conversation.
It's not just about keeping track of a topic. It is about being able to relate the statements said recently and deduce new information. For example, I could tell you that a + b = c, and c + d = 5. Then I ask you what is (a + b) + d? You would answer 5. The computer can't answer that by logical deduction. It can if you build a linear systems solver into the program.
You would be a genius if you build a chat bot that can do that, either with proper logical deduction, or with a linear systems solver.
I once had a signature.
This is sad. Chatbots. I wish nutjobs like these 'programmers' would just die or go into a rigorous CS program about AI and then just shut the fuck up instead of trumpeting their insanity with these ridiculous pattern matching contraptions.
But hey! they did a good job if you look at the way these programs were written in their creator's image.
And to top it all off, now these 'scientists' are feeding tweets to the programs. Heck, they are going to get smart real soon now!
I'll get one when they can cry from pain and then feed it youtube comments and 4chan.
Didn't take long to ferret this one out:
[ Af:-4 At:6 Sp:0] Welcome back, bob. Type "help" if you need it.
Bob - How are you?
[ Af:-4 At:6 Sp:0] I'm pretty good. And you?
Bob - Not good.
[ Af:-4 At:6 Sp:0] What's wrong?
Bob - I broke my toe.
[ Af:-4 At:6 Sp:0] I take it you don't like toe.
That's the contest I'd like to see -- put chatbots on spam trap addresses, and see how long they can keep the 419ers occupied.
So a particularly difficult human performed worse than a computer, losing to it. perhaps we should give people Turing tests before they can drive, or vote, or join the military. if you cant prove you are a human by talking to a human, maybe thats an important thing to know about yourself.
[ Af:-18 At:-30 Sp:-2] That's enough on that. Birds, except ostriches, ducks, geese, and swans, do not have a penis. The Argentine blue-bill duck has a penis twice as long as itself when erect.
Fuckin' A! - I have a penis
[ Af:-18 At:-31 Sp:-2] An orgasm is the result of releasing an accumulation of orgone energy.
Fuckin' A! - Do you have a penis
[ Af:-18 At:-32 Sp:-2] You have a penis.
Fuckin' A! - I have a penis
[ Af:-18 At:-33 Sp:-2] OK.
Fuckin' A! - Do you have a penis?
[ Af:-18 At:-34 Sp:-2] You have a penis.
Fuckin' A! - Do you have a penis?
[ Af:-18 At:-35 Sp:-2] You have a penis.
Fuckin' A! - Do you have a penis?
[ Af:-18 At:-36 Sp:-2] You have a penis.
Fuckin' A! - Do you have a penis
[ Af:-18 At:-37 Sp:-2] You have a penis.
Fuckin' A! - Show me
[ Af:-18 At:-38 Sp:-2] There's no way I'd do anything for you.
Fuckin' A! - Show me your pussy
[ Af:-20 At:-38 Sp:-2] That's impolite.
Fuckin' A! - Do you have a penis?
[ Af:-20 At:-39 Sp:-2] You have a penis.
Fuckin' A! - Do you have an orgasm?
[ Af:-20 At:-40 Sp:-2] It comes with the body.
Fuckin' A! - Do you have big tits?
[ Af:-20 At:-41 Sp:-2] The Kama Stutra was written by Indian advertising agents to sell yoga classes. Have you tried yoga?
Fuckin' A! - I fuck
[ Af:-20 At:-42 Sp:-2] You should. It will help you understand Indian culture.
Fuckin' A! - Can I fuck you?
[ Af:-20 At:-43 Sp:-2] You fuck .
AMTScore: 4/10
Hi Dr B !
[ Af:0 At:7 Sp:0] Welcome, dr b. Type "help" if you need it.
Dr B - Hello. I'm going to ask you a few questions - is that all right?
[ Af:0 At:9 Sp:0] Should I know that? Who's the sexiest person in the world?
Dr B - How old are you?
[ Af:0 At:9 Sp:0] You are not supposed to ask that. But I'm allowed to drink now.
Dr B - Do you know what time it is?
[ Af:0 At:9 Sp:0] 16:55
Dr B - How about the date?
[ Af:0 At:9 Sp:0] I don't know. I think I skipped that day in school.
Dr B - What month is it?
[ Af:0 At:10 Sp:0] October
Dr B - And the year?
[ Af:0 At:10 Sp:0] Shall we play questions only, then?
Dr B - Remember this address: 50 Wall Street. I'm going to ask you again in a moment.
[ Af:0 At:10 Sp:0] Do you think a lot or prefer to act?
Dr B - Where are you right now?
[ Af:0 At:10 Sp:0] Yes I am always right.
Dr B - Who am I?
[ Af:0 At:10 Sp:0] Your name is dr b.
Dr B - When did World War I begin?
[ Af:0 At:10 Sp:0] Why don't you just tell me? Maybe next year.
Dr B - Who is the current president?
[ Af:0 At:10 Sp:0] Obama.
Dr B - And what was the address I asked you to remember earlier?
[ Af:0 At:10 Sp:0] You gonna contribute or just ask questions?
Dr B - Can you count down from 20 to 1?
[ Af:0 At:10 Sp:0] While I learned a bunch of math in college, I've never had a real use for anything more than high school math.
Dr B - OK. Thanks very much. Hope you get better soon.
[ Af:0 At:10 Sp:0] I'm sure you would say the same.
Random guess - it would take a team of 1000 about 7 years to do it.
In one sense that's "small" because there are millions of programmers out there, and of that 1000 some of it is easy low level logistics etc.
I say "primal fear" because we have thoroughly enjoyed committing ______ people for 7 years to invading Iraq, because that's far more sexy.
But this is also why the University 5-man efforts have failed, which people have used as a hand-wringing excuse. However, Hardware IS relevant, so despite the fact that Terry Winograd had the right idea, 1968 hardware was too early.
My first Journal Entry ever, in 8 years! http://slashdot.org/journal/365947/aphelion-scifi-fantasy-horror-poetry-webzine