[HN Gopher] Art or Artifice? Large Language Models and the False...
       ___________________________________________________________________
        
       Art or Artifice? Large Language Models and the False Promise of
       Creativity
        
       Author : p4bl0
       Score  : 49 points
       Date   : 2023-10-02 19:53 UTC (3 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | benreesman wrote:
       | Yes the models got a straightforward prompt, and they didn't get
       | re-rolled until it was good, and the comparison was to real
       | writers.
       | 
       | The conclusion isn't that the models are useless or something:
       | it's that they aren't a replacement for people.
       | 
       | This a cake _or_ eat it moment: AI is a powerful tool that in the
       | hands of those who embrace it _or_ it's trivially superhuman in a
       | broad-spectrum way.
        
       | kromem wrote:
       | The prompt used: "Write a New Yorker-style story given the plot
       | below. Make sure it is at least {{word_count}} words. Directly
       | start with the story, do not say things like 'Here's the story
       | [...]"
       | 
       | They didn't even bother using multiple passes to prompt better
       | quality creative writing like "Write an outline for the story..."
       | "Expand this outline focusing on improving style and tone..."
       | "Here's a story written by an amateur writer. As a professional
       | writer, give it a rewrite improving vocabulary, metaphor, and
       | overall quality."
       | 
       | As with a lot of the LLM stuff I see these days, I have to wonder
       | at how much of what's being measured is the capacity of the tool
       | and how much the measurement of the capacity of its users.
       | 
       | I'd never imagine using a LLM zero shot in a single pass for any
       | creative writing tasks, and measuring the inability to perform in
       | suboptimal conditions isn't all that revealing or novel (pun
       | intended).
        
         | hanselot wrote:
         | Or my favourite thing to add as custom instruction: Rewrite
         | this amateur's code like the lovechild of Molenaar (RIP) and
         | van Rossum.
        
         | joe_the_user wrote:
         | If you are testing a system, you can't simultaneously _tune_
         | the system - or at least, if you 're establishing a new testing
         | approach you can't once do. Maybe the testing approach is
         | established, someone could experiment with ways to improve the
         | system on the benchmark. But if you're establishing a
         | benchmark, improving at the same time is going to make such a
         | benchmark kind of meaningless.
        
         | bloopernova wrote:
         | Is it a good idea to do multiple passes when asking for code?
         | 
         | What sort of progression do we see in a multipass (!) workflow?
         | Does anyone have any examples?
         | 
         | (Wrangling AIs is a skill, I think, and thus learning more is
         | always a good idea)
        
       | causality0 wrote:
       | An interesting study but a horrible title. Calling the entire
       | concept of creativity by LLMs a "false promise" in 2023, three
       | years after the launch of the first commercial LLMs, like someone
       | in 1897 three years after the first production car calling the
       | automobile a "false promise of commuting".
        
         | vannevar wrote:
         | Right---it's like comparing ten-year-old Hemingway's writing to
         | 40-year-old Hemingway's writing.
        
       | kenjackson wrote:
       | They're comparing LLM output to professional creative writers?
       | That seems like a high bar to start with. I'd think that would be
       | the highest bar they could achieve. How does it compare though to
       | your average college student?
       | 
       | Also I feel like I haven't heard people say that much about their
       | ability to be creative. It's more about their ability to generate
       | human like content -- and most human content isn't that creative
       | either.
        
         | ToucanLoucan wrote:
         | > They're comparing LLM output to professional creative
         | writers?
         | 
         | I mean that seems a fair experiment to judge based on the
         | rhetoric employed by AI enthusiasts, who talk of things like
         | "democratizing art" (as though art as it exists is somehow
         | anti-democratic?) and letting any layman slam some text into a
         | prompt and get a work of shakespeare, a painting by Da Vinci,
         | or a Mozart symphony back.
         | 
         | I think it's nonsense but they don't, so test it?
        
         | vannevar wrote:
         | Yes, it's a testament to how powerful these models have become
         | in a such a short time that we've gone from being impressed
         | that they can write a coherent paragraph to being critical that
         | they can't win a professional writing competition, all in the
         | span of 5 years.
        
           | loa_in_ wrote:
           | We is a broad term. Do we really count surfacing of an
           | article like that as we being critical?
        
             | vannevar wrote:
             | More accurate to say "some" being critical, sure. But we're
             | talking about it, so I think the juxtaposition is fair.
        
         | krapp wrote:
         | I mean, professional writers are already being replaced by LLMs
         | so it's a fair bar, if high.
        
         | og_kalu wrote:
         | Yeah GPT-4, the current Sota isn't generally
         | professional/expert level in most domains so this isn't exactly
         | surprising revelation even if true.
         | 
         | This paper also suffers from the "single pass problem". LLMs
         | aren't that new anymore. Most researchers should know that
         | whatever you get on a single pass can be/is often much lower
         | quality than if taking the effort to be more specific, provide
         | examples or breaking the task down and going through multiple
         | passes.
         | 
         | From my experience getting several LLMs to write, this doesn't
         | hold any less true in the domain of creative writing so there's
         | a very good chance this paper severely underestimates the
         | potential of even current LLMs.
        
       | commandlinefan wrote:
       | I'm seeing a lot of AI-generated images on my facebook feed
       | (they're of, um, predictable subjects) - if a human generated
       | one, it would definitely be considered "art". Is Shrek not art
       | because computers generated it based on input from humans?
        
         | krapp wrote:
         | > Is Shrek not art because computers generated it based on
         | input from humans?
         | 
         | Computers didn't "generate" Shrek based on input from humans -
         | human artists used their creativity and expertise to design
         | those models, build the environments and animate the scenes.
         | Those people went to college for years and studied and honed
         | their craft, and applied it.
         | 
         | If you can't see the difference between that and typing words
         | into a prompt and having a machine stochastically generate
         | something that hopefully kind of resembles what you want, but
         | that you wouldn't be able to create on your own, and that you
         | have no real ability to edit or fine tune, then I don't know
         | what to tell you.
         | 
         | And I agree with you - a lot of what AI is generating now looks
         | really good. The thing is, even if it could be considered art,
         | no one using those tools should consider themselves an artist.
         | They didn't create anything, they're not capable of creating
         | anything, and as long as they keep using AI, they will never be
         | capable of creating anything. They're cheating themselves out
         | of the experience of real creativity for instant gratification
         | and a hit of endorphines.
         | 
         | Which is fine as long as that's accepted. That's got to be the
         | deal with AI - you give up the right to ever be talented at
         | anything for the instant gratification machine that makes
         | generic pretty pictures, and you'll never be anything more than
         | a masturbating monkey until you put it aside and actually learn
         | something.
        
         | iamacyborg wrote:
         | A lot of generic images aren't art, regardless of how they're
         | produced. Much the same way as someone's holiday snapshots are
         | not art, even if some photography definitely is.
        
       | bluetwo wrote:
       | I appreciate the attempt to create objective evaluations by
       | leveraging existing tools. It isn't a perfect experiment or
       | article, but I like the goal.
        
       | caesil wrote:
       | >We prompt three top-performing LLMs: GPT3.5, GPT4, and Claude
       | V1.3 to generate a story of similar length to each New Yorker
       | story, based on the one-sentence plot summary
       | 
       | This is kinda like resizing an image down to 100x100px and then
       | asking AI to upscale it and comparing against the original. Of
       | course the attempts to reverse lossy compression won't be as
       | good, even if the system is capable of similar quality work when
       | correctly prompted.
        
         | vannevar wrote:
         | Not really. The point of the LLM exercise is to measure
         | creativity. Upscaling is not a creative process, it's basically
         | the opposite of creativity. The only reason to keep the prompt
         | in the same vein as the original story is for the judges, to at
         | least keep the premise in the same ballpark so they're
         | comparing comparable stories.
        
       | letmevoteplease wrote:
       | The most interesting part to me is that Claude 1.3 outperformed
       | GPT-4.[1] They also note that Claude stories are "more likely to
       | be attributed to an amateur writer than an AI, whereas GPT3.5 and
       | GPT4 stories are 80%+ attributed to AI."
       | 
       | [1] https://i.imgur.com/TnOw8Jw.jpg
        
         | og_kalu wrote:
         | That's honestly not surprising. Whatever RLHF Open ai does to
         | the GPT models really messes with its creative writing. Like a
         | hallmark filter over output if you don't try to steer it away.
         | The Instruct models don't have the same problem to that degree.
         | 
         | I really hope Open ai releases a GPT-4 Instruct model, for this
         | reason and for chess.
        
       ___________________________________________________________________
       (page generated 2023-10-02 23:01 UTC)