Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!


Forgot your password?
AI It's funny.  Laugh.

AI Is Funny - a Generative Joke Model 211

RemyBR writes "Can computers tell a good joke? Is comedy just a matter of statistics or is there something only a human can bring to creating a joke? A joke generator created at the University of Edinburgh (PDF) suggests that AI can be funny. Some AI generated jokes: 'I like my relationships like I like my source, open,' 'I like my coffee like I like my war, cold,' 'I like my boys like I like my sectors, bad.'"
This discussion has been archived. No new comments can be posted.

AI Is Funny - a Generative Joke Model

Comments Filter:
  • by Dr. Sheldon Cooper ( 2726841 ) on Thursday August 08, 2013 @02:39PM (#44512957)
    I like my slashdot like I like my like like like...

    Loop detected, aborting.
  • Al? (Score:5, Funny)

    by gbjbaanb ( 229885 ) on Thursday August 08, 2013 @02:40PM (#44512961)

    Am I the only one who read the headline and thought of Al Gore?

    ob. joke.. I like my coffee like my men - strong and black.

  • by pspahn ( 1175617 ) on Thursday August 08, 2013 @02:44PM (#44513005)

    I like my women like I like my sectors, industrial.

    • i sniggered
    • by fermion ( 181285 )
      It is definitely a generic frat boy joke generator. Cue the 'In Russia...' jokes.
      • It is definitely a generic frat boy joke generator.

        Not sure. It the thing is the I like my women like I like my X...Y are not funny because they say things about women, they're funny because they protray the teller as a gross nerd, creepy, insanely psychopathic, a total sicko, a massive pedo, etc. Listing some of the more popular ones as X|Y

        Whisk[e]y | 12 years old and mixed up with coke
        Whisky | Never less than 10 years old
        Coffee | Ground up and kept in the freezer
        Wine | 60 years old and locked in the cella

  • website! (Score:5, Interesting)

    by Xicor ( 2738029 ) on Thursday August 08, 2013 @02:46PM (#44513049)
    give us a website with access to this joke maker! not just a journal article
  • by Typical Slashdotter ( 2848579 ) on Thursday August 08, 2013 @02:49PM (#44513079)
    Reading the article, they have a (human-created) statistical model for the specific words people will find funny in this one, exact type of joke. The only thing the "AI" is doing is analyzing word frequencies against this model. I suggest calling these "statistically-generated" jokes, or similar.
    • by Hatta ( 162192 )

      Exactly. Let us know when the AI generates the formula, instead of just plugging words into it.

    • Furthermore, the examples are probably not a representative sample of the output. Humans probably picked a few good ones out of a set of mediocre ones.
    • by Livius ( 318358 )

      The first one was good; for the others "joke" is an overstatement.

  • This Has Been Done (Score:4, Interesting)

    by Toad-san ( 64810 ) on Thursday August 08, 2013 @02:54PM (#44513127)

    Well, in the movies anyway. Remember the first robot who could NOT get a joke? (Robbie)
    And I think the first wise-cracking robot? (Johnny 5 in "Short Circuit")

    And then of course there was Data .. with mixed results in reference to humor and jokes.

    • "Number 5 not just robot, Number 5, ALIVE!"

    • Re: (Score:3, Insightful)

      by bryny ( 183816 )

      What about the computer in "The Moon Is a Harsh Mistress" which was trying to understand humor. One attempt was:

      Why is a fish like a laser beam?
      Neither on of them can whistle.

      It was better at practical jokes, like adding some zeroes on the end of a janitor's paycheck.

  • They built Funnybot [wikipedia.org]? Do we have to worry about it exterminating the human race?
  • Women (Score:5, Funny)

    by SJHillman ( 1966756 ) on Thursday August 08, 2013 @02:58PM (#44513173)

    I like my women like I like my AI joke generator. Inaccessible to most of the interested geeks.

  • Okay, did anyone else think of the one or two episodes where Data was trying to be funny and do stand-up? This story reminded me of that. So did the jokes.
  • Somethingawful beat them to it: http://www.somethingawful.com/flash-tub/laff-bot-beta/ [somethingawful.com]
  • That's what she said (Score:5, Interesting)

    by barlevg ( 2111272 ) on Thursday August 08, 2013 @03:05PM (#44513259)
    The fascinating thing to me was that the funniest jokes it managed to come up with had a definite misogynistic streak. Is it because misogyny is inherently amusing, or because sexist jokes are low-hanging fruit? Link to more coverage of the same story. [telegraph.co.uk]
    • I like my women like I like my gas ... natural (misogynistic)
      I like my men like I like my acorns ... buried (misandristic)
      I like my boys like I like my sectors bad (???)
      I like my men like I like my monoxide - odourless (misandristic)
      I like my men like I like my court superior (misogynistic)

      I would say, given the information I have here, that the computer isn't really biased one way or the other, it hates everyone. Huzzah! Now we have a digital misanthropic comedian.

      • I like my men like I like my acorns ... buried (misandristic)

        I'd argue this one is misogynistic, if you interpret it as a woman talking about being a grave-robber [urbandictionary.com].

      • Yeah, looks like the Telegraph is just trying to drum up pageviews.

        I'm guessing they algorithm used is pretty simple, text mine for pairs of nouns that share a common adjective and you have your joke.

        It wouldn't be surprising if the funniest pairings were risque since breaking social norms is one of the basis for humour, I'm actually surprised they couldn't find actual misogynist examples. Depending on the telling even this one "I like my women like I like my gas ... natural (misogynistic)" is potentially n

  • by barlevg ( 2111272 ) on Thursday August 08, 2013 @03:10PM (#44513313)
    So from what I can read, this particular joke generator uses pretty straightforward word association and some Bayesian weighting. This article [theweinerworks.com] describes model that's a bit more complicated (having to do with graphs of word associations and forming loops of optimal length), and I wonder if it'd produce better (that is, funnier) results.
  • The problem will arise when the computers recreate the Funniest Joke in the World, sealed under a monument in 1950 labeled "To The Unknown Joke" After all, the computer will not know it has created the Killer Joke, leaving us with the danger of mass hysterics breaking out.
  • by tinkerton ( 199273 ) on Thursday August 08, 2013 @03:24PM (#44513459)

    Usually people mix up humor and powerful humor. So they think of all the ingredients that make it work. The best example of humor is then the one that makes you laugh more.
    But here's another angle: Just think of humor as having a humor part and a booster that makes you laugh more. The humor part is just the perception switch. It can be pretty mild. But add the naughtiness, the meanness , the embarassment and they provide a boost to the humor.

    Taken that way, the AI examples in the topic article are really touching the essence of humor.

    • by gr8_phk ( 621180 )

      Taken that way, the AI examples in the topic article are really touching the essence of humor.

      The essence of humor is surprise. They are getting surprise by looking for words that have different meanings in different contexts and using a canned phrasing to bring two disparate contexts together only on the very last word of the sentence - which bring the surprise. The boost you speak of is possibly there by combining a charged topic like "relationships" with something very boring like software or "source".

      • Well, surprise isn't the same as a perception switch, although there's overlap. Because I describe humor as a perception switch I'm saying it's the same mechanism as insight. Suddenly understanding something. Not that I came up with that myself.

      • by Livius ( 318358 )

        The essence of humo[u]r is surprise.

        Surprise and fear.

  • ...Turing Test passes YOU!

  • by istartedi ( 132515 ) on Thursday August 08, 2013 @03:59PM (#44513939) Journal

    You need Dr. Strangelove to walk into a coffee shop, and for the barista to ask him how he likes his coffee. Then MAYBE it's funny. Furthermore, the deliver and timing matters. You can deliver that line and kill or die. Finally, the person who sees this might not get it, or they might get it and just not think it's funny. Yeah, yeah, Dr. Strangelove likes the cold war. Not funny... to that guy; but maybe funny to you.

  • Ask Siri where to bury a dead body - or where to buy a digital camera...heck, just say 'tell me a joke'...
  • I like my machines like I like myself, Intelligent.

    Mapping a common property between two different subjects literally isn't remarkable in of itself. A comedian invents far more jokes than they tell. You see, the trick isn't in coming up with jokes, it's knowing when they're funny enough to repeat.

  • by __roo ( 86767 ) on Thursday August 08, 2013 @04:13PM (#44514109) Homepage

    In Mind Wide Open [amazon.com] Steven Johnson points out that "Laughing is not an instinctive physical response to humor, the way a flinch responds to pain or a shiver to cold. It's an instinctive form of social bonding that humor is crafted to exploit."

    Think about how often you laugh at references, the more obscure the better. You're sharing a bond with the person making that reference—and once you start looking for that, it becomes increasingly obvious (at least it did for me).

    That's probably why "I like my X like my Y, Z" style jokes are funny—they make us think, "Wow, you and I both see that X and Y have that relationship, possibly based on abusing a synonym, which doesn't immediately spring to mind when you think of them."

    The more I think about humor as an exploit of laughter as social bonding behavior, the more I notice it. And the more I notice people laughing when things aren't funny, but when it's appropriate to reconfirm a social bond (like when someone does something embarrassing that might take them out of the social norm, and the people around them laugh to reassure them that the social bond has not been damaged... much).

    This is where I would make a joke about how geeks are not good at social bonding, but I'm too much of a geek to relate to such things.

    • by Kaenneth ( 82978 )

      Which is why I hate TV shows with laugh tracks; particularly the ones that go off on every pause, even for non-jokes.

    • by mark-t ( 151149 )
      If laughter is a social bonding behavior, why do people laugh at something they are reading when they are completely alone?
      • by Jeremi ( 14640 )

        If laughter is a social bonding behavior, why do people laugh at something they are reading when they are completely alone?

        One's never alone with a good book...

        (i.e. at the very least you're engaging socially in some sense with the author, and likely with the characters in the story as well)

    • ok, I'm going to pay attention to that now, thanks.
  • Did they just troll a list of prolog statements for things that match up? There may be some diamonds in the rough, but must will be duds.
  • Here I am, brain the size of a planet, and they ask me to make puns. Call that job satisfaction, 'cause I don't.

  • Schubert's 8th (Score:5, Interesting)

    by Alsee ( 515537 ) on Thursday August 08, 2013 @06:11PM (#44515489) Homepage

    I like my jokes like I like my symphonies


  • It's a bit of a letdown, but still interesting. I made an inspirational quote generator [friendlyskies.net] that certain types of people enjoy. But only certain types. Humor is not easy to get right, least of all automatically right.
  • Odd... That was supposed to be "Reference" but reverence works as well.

    This story seems inspired by Asimov's "Jokester", in which a humor "Grand Master" is attempting to find the source of humor by feeding Multivac a curated set of jokes. I won't spoil the ending, but let's just say the mice need a new maze at the end.
  • I wonder if it could have been generated using the joke generator. Or maybe the slashdot post was generated by it as well. Or this post. Who knows ?!?

The trouble with computers is that they do what you tell them, not what you want. -- D. Cohen