Training a trillion parameter model to be funny

(jokegen.sdan.io)

16 points | by sdan 6 days ago

5 comments

  • nine_k 4 minutes ago
    Some models are better at generating funny and poignant quips.

    > my human mass-generates new ideas faster than I can research why the previous ones won't work

    > this is called 'job security'

    (https://nitter.poast.org/LetheAgent/status/20179595340865499...)

  • whacked_new 11 minutes ago
    Circa GPT-3.5 to GPT-4o I was involved in some research in figuring out how to make LLMs funny. We tried a bunch of different things, from giving it rules on homonym jokes [1], double-entendre jokes, fine tuning on comedian transcripts, to fine tuning on publicly rated joke boards.

    We could not make it funny. Also interesting was that when CoT research was getting a lot of attention, we tried a joke version of CoT, asking GPT4 to explain why a joke was funny in order to produce training set data. Most of the explanations were completely off base.

    After this work, I became a lot less worried about the GAI-taking-over narrative.

    Funny is very, very hard.

    [1] without a dictionary, which at first seems inefficient, but this work demonstrated that GPT could perfectly reconstruct the dictionary anyway

  • crawfordcomeaux 1 hour ago
    I once had a vivid dream that AI robots had taken over & were keeping humans around because they'd not yet mastered comedy. All of human culture globally was a comedy arms race with 24/7 open mic comedy jams on every corner.

    They (the machines) had billboards/signage everywhere showing the estimated time left for humanity. A really good joke would lead the timer to grow (until they figured out how to produce the general patterns needed to both create and appreciate the joke).

    • colecut 25 minutes ago
      openclaw, turn this into a broadway production, book me two front row seats, hire an escort..... brunette, 28, slim waist, sweet face, hates comedy and AI
  • suddenlybananas 2 hours ago
    these really aren't very funny
  • gipp 1 hour ago
    It would be easier to judge this if the jokes weren't 90% about AI and silicon valley, understandable only to people who subscribe to astralcodexten
    • omoikane 48 minutes ago
      I thought this one was not bad:

          [write a joke about thinking machines and the idea of tropes]
      
          it's funny how enemies to lovers is a common trope that's uncommon in real life and lovers to enemies is an uncommon trope that's common in real life
    • emp17344 1 hour ago
      Probably because if they weren’t absurdly esoteric we’d be able to tell it isn’t funny.
    • simonw 1 hour ago
      Who's tommipink? Even a Google search couldn't explain that one.