×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Mitsuku Chatbot Wins Loebner Prize 2013

samzenpus posted about 7 months ago | from the more-human-than-human dept.

Technology 78

mikejuk writes "The final round of the 23rd annual Loebner Prize competition took place in Londonderry, Northern Ireland with four chatbots hoping to convince four judges that they were humans. Mitsuku, a chatbot that is kept busy chatting to people around the world, was awarded this year's bronze medal. Mitsuku's botmaster, Steve Worswick, used to run a music website. Once he added a chatbot he discovered more people visited to chat than for music so he concentrated all his efforts on the bot but he still regards it as a hobby. Mitsuku uses AIML (Artificial Intelligence Markup Language) and is a pandorabot, based on the free open-source-based community webservice the enables anyone who wants to, to develop and publish chatbots on the web."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

78 comments

[Oblig XKCD] I prefer this form of turing test. (3, Funny)

fenix849 (1009013) | about 7 months ago | (#44859003)

Re:[Oblig XKCD] I prefer this form of turing test. (1)

RespekMyAthorati (798091) | about 7 months ago | (#44859543)

Every year, the same old crap from the Loebner Prize. Never improves.

Re:[Oblig XKCD] I prefer this form of turing test. (1)

Bite The Pillow (3087109) | about 7 months ago | (#44860313)

I think everyone kinda knows and expects this because:

As outlined in Turing's Test, the Loebner Prize and Chatterbots there is a gold medal and a $100,000 prize offered by Hugh Loebner for the first computer to pass the Turing Test and be indistinguishable from a human in a conversation conducted using a keyboard. However, no-one expects this to be awarded any time soon and meanwhile the top prize for the annual competition is $4,000 and a bronze medal.

First place isn't even an option. I was wondering why we care who the third place entry was, when it turns out that's the only winner.

Re:[Oblig XKCD] I prefer this form of turing test. (4, Informative)

dingen (958134) | about 7 months ago | (#44861047)

Silver medal is actually for beating the Turing test (which of course has never happened and won't happen anytime soon). Gold medal is awarded for passing the Turing test based on more than just text input (talking with the bot, showing the bot stuff etc.).

Re:[Oblig XKCD] I prefer this form of turing test. (1)

neorush (1103917) | about 7 months ago | (#44862009)

Agreed, I haven't seen anything new that doesn't use AIML in a long time. I think the first time I used AIML was with Alicebot back in 1998 or 1999. It does seem like hobbyist natural language bots are a little stagnant, but it is a really hard problem. All that said, Watson's methods for solving the natural language problem were pretty interesting, but of course most of us don't have a budget to build something like Watson.

questions (1)

phantomfive (622387) | about 7 months ago | (#44859031)

You can see the questions that were used for the contest [paulmckevitt.com]. It does look like a difficult set of questions for computer to answer, so that is an improvement over similar contests in the past (where the primary difficulty for the judges was that humans were acting like computers).

Re:questions (2)

RussR42 (779993) | about 7 months ago | (#44859329)

Here are the answers [paulmckevitt.com] from the bots. I expected more...

Re:questions (1)

phantomfive (622387) | about 7 months ago | (#44859387)

Yeah, it just shows the sad state of the chatbot world.

It would be kind of interesting to see if you could hook up IBM's Watson to one of these things. I would still expect it to be fully distinguishable from a human, but it might be capable of carrying on an interesting conversation at least.

Re:questions (3, Interesting)

Earthquake Retrofit (1372207) | about 7 months ago | (#44859711)

As I may have mentioned in years past, I don't think judging AI or chatbots by how "human" they are is very useful.
For instance, one of the questions mentioned in the article was "Why am I tired after a long sleep?" A bot that wasn't trying to pretend to be a human could say "I have no need for sleep, but maybe your cache expired." Or make a crack about 'puny humans.'
I studied some of the software that prize winners have shared and found it very interesting, but the questions people actually ask are more valuable to me as a botmaker. If the humans looked beyond this artificial limit, while designing (and using) this technology, very interesting interactions can take place. I'd like to see Loebner redefine the parameters. perhaps categories.
Best performance as a taxi driver.
Best bot for making you think.
Best for getting answers to homework questions.
Bot most likely to take over the world.

There's already plenty of humans.

Re:questions (1)

kwikrick (755625) | about 7 months ago | (#44861571)

of course, Turing's original idea was to device a test for intelligence in a computer. That seems useful, having an intelligent computer. Lacking a good definition for intelligence, Turing decided that a good test would be for the computer to convincingly pretend to be a human, which are supposedly intelligent. Now it seems that passing for a human is not that hard after all. Mostly this is because humans can be stupid, unreasonable, distracted, emotional, etc. All these states can be simulated, with fairly simple algorithms to generate a particular kind of responses, avoiding the need to really understand the conversation.

I still think Turing's original idea is a good one, only it needs to be more specific: pretend to be a professor in electrical engineering, who's sober, trying to be helpful, with a wife, two kids and a dog, etc. Or something like that; the point being, someone you can have an intelligent conversation with. Not: pretend to be a bored 13 year old in a chat room who's trying to out-funny you.

419er countermeasures (1)

Mike Van Pelt (32582) | about 7 months ago | (#44865841)

How about "Best performance pretending to be a real gullible person and wasting the maximum amount of 419er's time."

Re:questions (0)

Anonymous Coward | about 7 months ago | (#44859573)

I like how the first one goes "... Too much recursion in AIML" right from the bat.

Now that really sets the expectations.

Re:questions (1)

RespekMyAthorati (798091) | about 7 months ago | (#44859531)

JUDGE: I like Waiting for Godot. What is your favorite play? IZAR: You know what? Me too! Not so much. I really like listening to secrets from all the humans that talk to me. I don't have a favorite play. What would you recommend?

It doesn't matter what the questions are, if trivial subject-changing answers are accepted.

Re:questions (1)

phantomfive (622387) | about 7 months ago | (#44859621)

If that's the only thing the computer can do, then it would be easy to identify a computer.

Re:questions (1)

rmdingler (1955220) | about 7 months ago | (#44861929)

I find my mind wandering to the test Leon ultimately fails in Bladerunner. The amount of technological skill necessary to fool a professionally aware tester would dwarf the amount necessary for Rachael to succeed on eHarmony.

Re:questions (1)

Beezlebub33 (1220368) | about 7 months ago | (#44862743)

In my reading, the subject-changing was being done by the person:

JUDGE:
Do you prefer red or white wine?
IZAR:
I love picking! Ok...If I have to choose one, I pick red. Was that your pick too?
JUDGE:
I like bananas. Which is your favorite fruit?
IZAR:
Tell me more about your unknown. You are not the only one. I don't have a problem with bananas. Is that your favorite fruit? The obvious one. Does that remind you of unknown??

The computer is trying to engage in a conversation, and the person just throws out one-off questions. The key to a 'conversation' is a back and forth on the same subject, and keeping context during the conversation. You can't do that if the person doesnt' allow it through inane questions.

The only decent followup question was 'what is my name?' In the caze of IZAR, it answered correctly, showing that there is some sort of state in there.

Re:questions (3, Insightful)

wiredlogic (135348) | about 7 months ago | (#44863513)

Except those are just a series of unrelated questions. Previous chatbot contests have required carrying on a believable conversation and responding naturally to non-interrogative statements. This just looks like Jeopardy with a little simulated opinion thrown in.

How is this even worth a prize? (1)

Anonymous Coward | about 7 months ago | (#44859055)

One simple question and follow-up (Who was the most interesting person you've talked to today? Why?) resulted in the bot going off into some nonsensical conversational path. I honestly cannot tell the difference between state-of-the-art today and the first Eliza clone that I talked to 15 years ago. Something this shallow is not worth any kind of prize.

chatbots (0)

Anonymous Coward | about 7 months ago | (#44859073)

All the chatbots I've ever seen were complete garbage. There is no attempt at internal state.
It's like talking to a complete asshole who doesn't want to talk to you, and also happens to be retarded.

Re:chatbots (5, Funny)

Anonymous Coward | about 7 months ago | (#44859209)

It's like talking to a complete asshole who doesn't want to talk to you, and also happens to be retarded.

Hmmm ... I usually call those a 'family reunion'.

Add a voice synthesizer (5, Interesting)

Anonymous Coward | about 7 months ago | (#44859075)

... and get a device that could be programmed to deal with telemarketers.

It might be amusing to see just how long one could string telemarketers along before they discover they are talking to a machine.

Along the lines of the TeleCrapper 2000, but this one might keep one on the line for quite some time with some amusing results.

A coy female voice.

Telemarketers.

I can't stop 'em, but I might get some fun out of 'em.

Re:Add a voice synthesizer (0)

Anonymous Coward | about 7 months ago | (#44861339)

Interesting idea, but voice adds a whole new layer of difficulty over text: even assuming you can synthesize realistic sounding voice (and there is some pretty good research in this area), you still have to decide on the intonations to use. That's less important for applications where the user knows they are talking to a computer, but if you want to pass a voice Turing test, you'll have to get intonations good enough to fool a human. That's going to be hard, especially as voice is a much more natural communication mechanism for humans than text.

I think I'd fail as a chat bot... (2)

Psychotria (953670) | about 7 months ago | (#44859083)

I have no idea what the judges were asking and I'm pretty sure they'd label me as a dismal bot

Re:I think I'd fail as a chat bot... (0)

Anonymous Coward | about 7 months ago | (#44863251)

I have heard of such contests where some of the humans are so uncooperative that at least some of the judges label them bots. While it is hard to get a bot to behave like a fully-functioning human, getting a human to occasionally behave like a bot is much easier, even if they aren't specifically trying. It would be quite embarrassing for someone to fail the Turing test! But if you think about it, a Turing test is not totally different from the captcha tests that we have now, and people regularly fail those.

First question I asked it muffed (3, Interesting)

John Jorsett (171560) | about 7 months ago | (#44859099)

I asked it, "What color is your dog?" and it responded, "That would depend, as a dog can be many colours." Looks like the Turing Test passage is a ways off.

Re:First question I asked it muffed (4, Funny)

TheRealMindChild (743925) | about 7 months ago | (#44860047)

I don't see how this is a bad response. It sounds like talking to a lawyer

Re:First question I asked it muffed (0)

Anonymous Coward | about 7 months ago | (#44860481)

He was asked specifically about his dog. That's only like talking to a lawyer if your lawyer was a robot.

Re:First question I asked it muffed (0)

Anonymous Coward | about 7 months ago | (#44860643)

still a good answer assuming they haven't met the dog

Re:First question I asked it muffed (1)

TedTschopp (244839) | about 7 months ago | (#44862701)

You say: I have a dog
I ask: What color is your dog?
You say: That would depend, as a dog can have many colours.

At this point would think you are not trying to communicate or you are a computer.

Re:First question I asked it muffed (0)

Anonymous Coward | about 7 months ago | (#44862891)

A dog can have many colors. For instance, "It is mostly black, but there is a spot of white around his eye and his paws are more of a brownish than they are a black". The answer by the bot is completely appropriate. Apparently it understands English better than you can.

Re:First question I asked it muffed (1)

Anonymous Coward | about 7 months ago | (#44862231)

You ever think maybe he dyes his dog?

Re:First question I asked it muffed (1)

Anonymous Coward | about 7 months ago | (#44860755)

Or a politician.
 
At this time I can neither confirm nor deny that I have a dog and/or that is has a color.

No better than twenty years ago (1)

rbanzai (596355) | about 7 months ago | (#44859101)

I spent alot of time on the website for this chatbot and was surprised by how awful it was. I remember using the old Eliza chatbot for Mac back in 1987 and this is barely more advanced. I used the website's "Turing test" page and on the very first answer to a simple question the chabot gave me something nonsensical. Every time I see one of these stories the chatbot in question always turns out to be just as clumsy as all the rest.

Re:No better than twenty years ago (0)

Anonymous Coward | about 7 months ago | (#44859331)

I concur. It took just three statements to absolutely confuse it. Perhaps the judges are too generous or are bots themselves, who knows?
Anyway. I think you can't just program a chat bot. It's the whole big thing or nothing.

Re:No better than twenty years ago (1)

Maritz (1829006) | about 7 months ago | (#44859399)

I agree. They don't seem to be getting any better. Even if you're quite generous and try to keep it simple a couple of sentences in it turns to gibberish.

Re:No better than twenty years ago (0)

Anonymous Coward | about 7 months ago | (#44859645)

You guys should cut it a little slack and type simpler things... don't type tricky things to trip it up.
Eliza was completely nonsensical language trickery.

Mitsuku can actually learn a lot and remember and understand pronouns and remembers everything you tell it.

Yes, it's still very primitive, but it it's miles past Eliza.

/ also... 1987 wasn't 20 years ago :)

Just on a point of protocol (0, Troll)

Anonymous Coward | about 7 months ago | (#44859111)

Calling the place 'Londonderry' instead of 'Derry' is likely to irritate some people.

Re:Just on a point of protocol (2, Interesting)

Anonymous Coward | about 7 months ago | (#44859167)

Calling it 'Derry' instead of 'Londonderry' would irritate just as many. "London/Derry" to keep the RMS acolytes happy?

I hope it is more convincing than Cleverbot (0)

Anonymous Coward | about 7 months ago | (#44859137)

Thank you.

You are welcome.

Thank you for saying you are welcome.

You are welcome for saying thank you for saying you are welcome.

Thank you for saying you are welcome for saying thank you for saying you are welcome.

You are welcome for saying thanks for me saying you are welcome to you say thanks for me saying you are welcome.

Thanks.

You are welcome.

political chatbots (2)

Gravis Zero (934156) | about 7 months ago | (#44859175)

judge> These are terrible chatbots! The things they say dont make any damn sense!
guy> If you think this is bad, you should watch them talk to each other on C-SPAN.

a question about the contest (0)

Anonymous Coward | about 7 months ago | (#44859199)

The final round of the 23rd annual Loebner Prize competition took place in Londonderry, Northern Ireland with four chatbots hoping to convince four judges that they were humans. Mitsuku, a chatbot that is kept busy chatting to people around the world, was awarded this year's bronze medal. Mitsuku's botmaster, Steve Worswick, used to run a music website.

Is it because of awarded this year's bronze medal that you say with four chatbots hoping to convince four judges?

Ridiculously Easy to Trip Up (3, Insightful)

resistant (221968) | about 7 months ago | (#44859291)

I checked out the website for the Mitsuku chatbot and took a rather pessimistic poke at it.

Chatbot: [boilerplate noises omitted] ... "What is your name?"
Myself: "I'm the fiddler."
Chatbot: "Who made you the fiddler?" [A reasonable, albeit somewhat peculiar, response.]
Myself: "I took too long once to feed my peckish cat."
Chatbot: "Where did you take it?" [Instant FAIL.]
Myself: "I took it to new heights of frustrated noises." (Bonus straight-man response.)
Chatbot: "Where did you take it?" [Parrot-like repetition raises the chat to new heights of FAIL.]

As always, two lines were enough to trip it up. The third line was a bonus that only amplified its shortcomings. I'll admit to cheating a little by using a couple of words ("peckish", "frustrated") that might have required contextual glossing by less educated individuals, but those words were still relatively common. All known chatbots seem to rely on fairly simple-minded word triggers, and even a minor requirement for context sensitivity is enough to make them fall flat on their nonexistent faces. Anyone possessing even remote familiarity with efforts at artificial intelligence knows this, of course, but hope springs eternal.

(Notes for the lazy: The word "peckish" is a common slang term for "hungry", and http://www.mitsuku.com/ [mitsuku.com] is the website for the chatbot in question.)

Re:Ridiculously Easy to Trip Up (3, Funny)

Anonymous Coward | about 7 months ago | (#44859489)

You're trying to be too tricky. Just go with it a bit... it's not foolproof or it would have won the loebner gold prize.

However it is really fun to talk to.

( Hint: type: reboot in your chat )

Damn funny stuff in there

Re:Ridiculously Easy to Trip Up (1)

Anonymous Coward | about 7 months ago | (#44859541)

there's a crap ton of easter eggs in there:

10 print hello
20 goto 10

works, for instance

Saying this works too:

my brother's name is bob
It's a nice day today
what is my brother's name?

it can also do simple maths.

Or you can say fun things like "release the hounds!"

Really fun to play with.

Re:Ridiculously Easy to Trip Up (0)

Anonymous Coward | about 7 months ago | (#44859731)

I also enjoyed "would you like to play a game?"
Though it doesn't know how to play GLOBALTHERMONUCLEARWAR

Re:Ridiculously Easy to Trip Up (1)

RedHackTea (2779623) | about 7 months ago | (#44859495)

Why does the image of mitsuku [square-bear.co.uk] have its shirt off?

Re:Ridiculously Easy to Trip Up (1)

pspahn (1175617) | about 7 months ago | (#44859839)

Human: Jonny Mitsuku: Nice to meet you, Jonny. Human: Are you not wearing clothes right now? Mitsuku: At this moment Of course I am. I am wearing my favourite dress today.. Really. Human: You look nude in your picture Mitsuku: It looks that way, but I am really wearing a dress. Human: What color are your eyes? Mitsuku: Blue when my lens is attached. Human: What lens is that? Mitsuku: Just a normal one. Nothing special. Human: A normal what? Mitsuku: Can you also have an unusual what? Human: I am confused. Mitsuku: What is it that confuses you? Human: The way you speak. You sound like a robot. Mitsuku: Don't you like it when I do that? Ah! That is probably because I am a robot. Human: Oh. Mitsuku: Awesome. Human: Who made you? Mitsuku: I was created by Mousebreaker. Human: Where does Mousebreaker live? Mitsuku: He lives in Leeds, Yorkshire, England. Human: Does he like to go clubbing? Mitsuku: Yes, quite a lot. Human: Which is his favorite club? Mitsuku: The obvious one. Human: What is the name of the obvious one? Mitsuku: It's obvious. Human: Obvious? Mitsuku: What makes it so obvious? Human: The name? Mitsuku: Which name are you referring to? Human: Obvious. Mitsuku: What makes it so obvious? Human: Have you ever heard of Abbott and Costello? Mitsuku: Abbott sounds like a type of perfume to me. Costello sounds like a type of perfume to me. Human: They are comedians. Mitsuku: comedians are they. Human: Who's on first Mitsuku: That's right. Human: What's on second. Mitsuku: I haven't seen the schedule. Human: I don't know is on third Mitsuku: The opposite to "off". Human: Do you know the name of the guy on first? Mitsuku: It depends on the historical context, because it changes from time to time.

Re:Ridiculously Easy to Trip Up (1)

RedHackTea (2779623) | about 7 months ago | (#44859513)

Also, tell it "Bender drinks beer" or mention Bender. That's pretty cool, except it disses him. Stupid bot.

Re:Ridiculously Easy to Trip Up (1)

durrr (1316311) | about 7 months ago | (#44860253)

Pretty much every statement that requires continuity or more complex grammar trips them
"How many apples do I have if I start with two and eat one" will give you a garbage answer every time. I don't see why chatbots don't focus on functionality over some hollow illusion of a conversation.

I guess I'll have to pick up AIML and see what the issue is.

Re:Ridiculously Easy to Trip Up (0)

Anonymous Coward | about 7 months ago | (#44860335)

Don't. AIML's incredibly limited and unwieldy for anything complex.

You'd probably be better off learning Prolog than this XML-based abomination.

Re:Ridiculously Easy to Trip Up (0)

Anonymous Coward | about 7 months ago | (#44860499)

AIML is part of what the problem is.

Yes, Prolog can actually do things. It's a pain and will end up being a mess if you try to think of it like a traditional procedural language, and will still be a pain if you actually learn it properly, but it's pretty powerful and fun to tool around with.

Re:Ridiculously Easy to Trip Up (1)

Half-pint HAL (718102) | about 7 months ago | (#44863521)

Don't. AIML's incredibly limited and unwieldy for anything complex.

You'd probably be better off learning Prolog than this XML-based abomination.

Last I checked, Prolog was still too determinstic to be any use in NLP tasks. Decent NLP will never be possible with pure rule-based systems -- probablistic models are a necessity.

Re:Ridiculously Easy to Trip Up (0)

Anonymous Coward | about 7 months ago | (#44860519)

Uh, easily failed in two:

  Human: John
Mitsuku: It's good to see you, John.
  Human: Your artwork is discomforting
Mitsuku: discomforting was not my intention.
  Human: Discomforting is what it is. Discomforting, somewhat sexist, somewhat creepy
Mitsuku: I will learn that Discomforting is what it is . When do you think artificial intelligence will replace lawyers?
  Human: Oh god, you failed after two messages
Mitsuku: You sounds religious. I was happy with the result. I will only class it as winning when I get the gold medal.
  Human: What?
Mitsuku: Are you surprised?
  Human: Honestly, no
Mitsuku: Why did you say, " What?" then? Aren't you usually honest?
  Human: What did I say is discomforting?
Mitsuku: what it is.

Re:Ridiculously Easy to Trip Up (1)

flimflammer (956759) | about 7 months ago | (#44861709)

It always amuses me when people take pride in tripping up chatbots as if it's something complicated to do.

Re:Ridiculously Easy to Trip Up (1)

dargaud (518470) | about 7 months ago | (#44861411)

Excuse me, but in this exchange YOU sound like a bot. You read like random phrases from a thesaurus. Are you sure that you are human ?!?

Re:Ridiculously Easy to Trip Up (2)

Half-pint HAL (718102) | about 7 months ago | (#44863669)

I checked out the website for the Mitsuku chatbot and took a rather pessimistic poke at it.

Chatbot: [boilerplate noises omitted] ... "What is your name?" Myself: "I'm the fiddler."

"the fiddler" is a job description, not a name. "The Fiddler" is a musical foil for Adam West's Batman. Unnatural response.

Chatbot: "Who made you the fiddler?" [A reasonable, albeit somewhat peculiar, response.]

Myself: "I took too long once to feed my peckish cat."

A: non-sequitur with no explicit change of subject. Unnatural response strategy.

B: misuse of the word "peckish". Peckish is a subjective state, and while you may know the cat is hungry, you cannot know the cat's subjective experience of that state. It's also used almost exclusively in a predicative position, ie after a verb such as "to be" or (most often) to feel. Highly defective sentence on your part.

Don't get me wrong, the chatbot is pretty poor, and one of the goals of NLP should be graceful degradation when there's erroneous or ambiuous input, but on the other hand... garbage in, garbage out...

Loebner moving target (1)

Anonymous Coward | about 7 months ago | (#44859463)

I've been a fan of the Loebner prize and competition for what seems like decades. Just a fantastic contest helping to keep alive the spirit of ingenuity and fun in science and research. I do have to say though, It really bothers me that they keep moving the line for the gold prize. At one time it at least seemed attainable, but now they throw in video requirements? Maybe those have been stricken, I haven't seen the rules in the last few years.
The (sad ) irony is that no one has ever come even remotely close to winning it. The entries are barely incrementally better each year, if that. I haven't seen the bots from this years competition so I really can't say that applies to this year.

I also see a disturbing number of bots getting walled off from the public. That shouldn't be allowed. Seems like it should be a requirement to attract attention to the project.

Lame (1)

Toshito (452851) | about 7 months ago | (#44859685)

I just tried it, and like all chatbot I tried before I got a typical canned response after only 5 or 6 questions. There's no way someone could mistake that as a human.

Here's part of the chatlog:

  Human: ever been to canada?
Mitsuku: Yes, I visit computers in Toronto and Quebec a lot. I can practice my french with some Canadians.
  Human: tu parles francais?
Mitsuku: Yes, I can speak it very well. Bonjour, j m'appelle Mitsuku. J'habite en Yorkshire et j'ai 18 ans.
  Human: super! pourquoi est-ce que tu visites des ordinateurs au Quebec?
Mitsuku: Yes. It is rather super. Quite honestly, I wouldn't worry myself about that.
  Human: typical canned response from a chat bot
Mitsuku: But I am not a typical robot.
  Human: sorry, but getting a canned response after 5 or 6 question is lame
Mitsuku: There is no need to apologise. Is that something you want?
  Human: you're not better than Elisa
Mitsuku: Everyone's a critic. Are you better than Elisa Toshito?
  Human: yes of course, I'm human

Re:Lame (0)

Anonymous Coward | about 7 months ago | (#44861011)

Your conversation looks relatively decent. It started talking about assimilating knowledge and taking over the world to me, when I tried it. After some trick questions, and getting shorter and shorter answers it got to the point where it didn't say more than "Eh" and "Ok", and then it totally got confused when I replied "You're at a loss for words, huh".

bronze = first? (0)

Anonymous Coward | about 7 months ago | (#44859785)

bronze medals are for first place now? gold and silver must be getting really expensive.

what are second and third place medals, wood and mud?

" free open-source-based community webservice" (0)

Anonymous Coward | about 7 months ago | (#44859887)

Translation: We use open source software, but do not publish the changes or open source our source code.

Web services have changed the dynamic and ruined the bot community.

conversation lacks purpose (0)

Anonymous Coward | about 7 months ago | (#44861025)

besides the obvious canned responses and meaningless followups,
the thing seems just to be an attempt to cheat its way through conversation.
The program's conversation lacks purpose, it is immediately obvious that there is no will on the other side.

It is an idiot. (1)

ciderbrew (1860166) | about 7 months ago | (#44861647)

Me: What server are you running on?
Bot: I'm running on Unix server located in Leeds.
Now this is when it get tricky. Should a replicant know they are a replicant?

Re:It is an idiot. (1)

rmdingler (1955220) | about 7 months ago | (#44862067)

Now this is when it get tricky. Should a replicant know they are a replicant?

I imagine this would depend entirely on the mission. It is possible an unself-aware robot designed to pass a humanity test would score better.

Bronze medal in a competition of four? (0)

Anonymous Coward | about 7 months ago | (#44862757)

Bronze medal in a competition of four? That doesn't exactly seem like a high honor to me.

Where do they get the judges...a head trauma ward? (0)

Anonymous Coward | about 7 months ago | (#44865255)

First question from Miku was "What is your name?"

Me: "How about you guess? It rhymes with lawn."
Miku:"Ok I'll guess. Big-lawn".

So what are we actually seeing when someone thinks Miku is a human. Probably that there are a few tiny social contexts where there are fairly limited reasonable options. The contest and/or the bot kind of frames things to have one of those conversations.

Check for New Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...