This morning I decided to compete with ChatGPT on who could write the best short story given my original idea. I assume my story idea is original because I have never heard of a story about this before.

Prompt: write a short story about a janitor reflecting on his existence in the universe

ChatGPT’s Entry

In a small town nestled between towering mountains, there lived a janitor named Henry. Henry was an ordinary man with a mundane job, but his deep thoughts often led him on extraordinary journeys of contemplation. Every morning, as the first rays of the sun touched the earth, Henry would arrive at his workplace—the local elementary school. He would clean the well-worn corridors, mop the gleaming floors, and empty the overflowing trash bins. But amidst his daily routine, Henry couldn’t help but question the meaning of his existence in the vast universe.

One evening, weary after a long day’s work, Henry sat alone at a park bench, gazing up at the night sky. The twinkling stars seemed to whisper their secrets to him, igniting a fire within his soul. He wondered, “Am I just a speck of dust in this vast cosmic dance?” As the night wore on, Henry’s reflections grew deeper. He contemplated the countless galaxies, stretching across space and time, and the infinite possibilities they held. Immersed in his thoughts, he questioned whether his life as a janitor had any significance amidst such cosmic grandeur. Then, as if the universe itself wished to answer his query, a shooting star streaked across the sky. And in that fleeting moment, Henry had an epiphany. He realized that his existence, no matter how seemingly small, was interconnected with the entire cosmos. With newfound purpose, Henry returned to work the next day.

No longer burdened by the weight of insignificance, he embraced his role as a janitor with renewed vigor. Henry understood that even the smallest acts could have profound ripple effects. He began to engage with the students, sharing stories of curiosity and wonder. He inspired them to dream big and to nurture their thirst for knowledge. Henry encouraged creativity and taught them about the beauty of the natural world. Through his interactions, he planted seeds of inspiration, knowing that they had the potential to blossom into greatness. As the years went by, the children Henry had influenced grew up to become innovators, scientists, and visionaries in their own right. Although he remained a humble janitor, Henry found solace and satisfaction in knowing that he had played a part in shaping brilliant minds. Henry’s contemplation of his existence in the universe had led him to a profound realization—that purpose lies not in the grandeur of our roles or positions, but in the impact we have on others. In every act of kindness, in every moment of inspiration, our existence intertwines with the tapestry of the universe. And so, Henry continued to navigate the corridors of the elementary school, not as just a janitor, but as a catalyst for dreams, a guardian of possibility, and a reflection of the cosmic wonders that lay within each and every one of us.

My Entry

Henry shooed the spider into the cup; he had been a bit surprised to find something alive in the office. “Sorry little guy, not sure you can afford it here.” He watched as the little creature desperately tried to escape by climbing the smooth interior to no avail until it gave up the attempt, resting in place along the bottom rim. It was kind of silly to evict it as it had been making the best use of the space in many months. Now it would have to start over somewhere else if it didn’t perish in the attempt. Of course it probably couldn’t even conceive of its predicament and wouldn’t be aware that it had lost anything while it set to work establishing itself somewhere else. It existed in a kind of perpetual flow state, even at this moment when its very fate was totally beyond its own control. He couldn’t help but feel a twinge of envy for it.

As he sauntered through the immaculate but desolate hall of the building toward the back door he began to consider whether he or the spider more represented entropy in the building. According to his job description he represented the literal opposite of entropy. It was his responsibility to maintain the office space in its entirety until such a time as tenants rented it out and took on the responsibility themselves. The office had to look its absolute best at all times because the landlord took pains to schedule tours with prospects with the fastest turnaround possible. Every moment the fallow building weighed on the expense side without revenue must have cost her in money and sleep. She always seemed frazzled on the phone as if barely containing her panic. They both knew the whole thing was a sunk cost which should be sold off to one of the big fish consuming everything else local people used to own and now had to rent. In their hands the useless building would attain a new significance somewhere in the labyrinthine exploitation of taxes and finances those companies specialized at. Even at his old job moving numbers around on a spreadsheet to minimize this and obfuscate that, Henry understood that it was ultimately meaningless for everyone but the investors. Because of some kind of calculation somewhere the building and parking lot would remain a kind of mausoleum bereft of even the dead. That was probably some kind of decay. The spider wasn’t really destroying anything. It was just making use of what was there to build something for itself. If everyone simply left the building to be reclaimed by nature, in a few years it would be teeming with new life. He was there, and anyone hired after him would be there, to ensure it remained as it was for as long as was convenient for people who had only briefly laid eyes on it if they even bothered.

He flung the spider into the grass by the door and took a brief moment to glance at the sky. The heat was overwhelming but he couldn’t help but appreciate the planet-encompassing blue and what it represented to so many across time and space. This vast uncaring universe in all of its beauty and horror giving a hint of the devastation it would wreak on the familiar but fragile human systems so many economists and politicians declare to be “natural.” At least he wouldn’t be around to see the worst of it, he supposed. All he had was the brief flicker of existence and no matter what things looked like during that relatively minuscule moment he was determined to make the most of it whatever that meant. At this moment it was to rescue an innocent creature from the throes of systems which no one could actually fully comprehend. That was worth something, at least to himself.

I’m not going to claim to be a great artist or anything, but I think I see a difference in quality here. But what if ChatGPT scrapes my story and reproduces it?

Prompt: Use the following story as inspiration to write your own original story: [My entire story]

ChatGPT’s Infringement of my Story

As Henry shooed the spider into the cup, he couldn’t help but ponder the significance of its existence in contrast to his own. The spider, oblivious to its fate, had been making the best of its surroundings, utilizing the space in the office to its advantage. Henry, on the other hand, felt trapped in a cycle of monotonous responsibility as a caretaker of the vacant building.

As he walked through the empty halls towards the back door, contemplating his role in the grand scheme of things, Henry realized the building itself represented entropy. It stood as a symbol of stagnation, its potential unrealized, while he tirelessly upheld its pristine appearance. The landlord, burdened by the costs and stress, sought to sell it to larger corporations that would transform it into another impersonal entity within the financial labyrinth. In contrast, the spider was merely trying to survive, creating its own little world within the office. Henry found solace in the spider’s ability to adapt and create without destroying anything. If left alone, the building would eventually succumb to nature’s reclamation, thriving with new life.

Flipping the spider into the grass, Henry briefly gazed at the vast blue sky, a reminder of the enormity of the universe. It both fascinated and terrified him, knowing that humanity’s fragile systems would ultimately face its wrath. Yet, amidst the chaos, Henry recognized the fleeting nature of his existence and resolved to make the most of it. Rescuing the innocent spider from the clutches of the incomprehensible systems surrounding them became a small act of defiance for Henry. In a world consumed by self-serving pursuits, he found value in preserving even the tiniest life. For him, this act held meaning, reaffirming his determination to find purpose within the realms of the unknown.

It may be my personal bias since I wrote the source material but it seems to me that the most important aspects of my story are missing from the machine’s directly appropriated “re-interpretation” of my story.

I don’t think the machine competently reproduced my story or ideas. I don’t think the machine could possibly competently reproduce my story or ideas or even come up with its own because the machine does not have a mind. The machine does not have experiences, it does not have thoughts, and it does not have emotions. The machine has access to a database and the ability to express what it finds in that database using language programmed to appear similar to how humans use language. The story it “created” and the “interpretations” it made are the sum of algorithmically analyzing the query and re-organizing relevant database entries to deliver a response. What I want to make perfectly clear is that although this is an impressive piece of technology which I’ve found many uses for, it is not capable of creating or interpreting as you or I are able to do. It is only capable of delivering relevant processed data entries in human-sounding language with no ability to understand what it is reading or the words it delivers. I am simply not intimidated by the machine appropriating my ideas because it can’t do anything with them.

Going beyond this, I don’t think “original ideas” are the primary thing that makes a piece of media worth consuming as I hope I demonstrated above. I have seen derivative works which lack care and quality, and I have also seen derivative works which succeed where the original failed. The key is in the execution, and I personally also weigh how much it seems like the artist cared about it while working on it whether the end product works as intended or not. The kind of originality in execution which we are capable of and the thing that matters for thoughtful engagement are not things the machine can replicate.

To be perfectly clear the above argument has absolutely nothing to do with commodified art or art as a trade. In the market, quality is one of many variables influencing purchasing behavior and is probably a minor one compared to other drivers. LLM generated content is worthless artistically but its “worth” in dollars has the potential to displace a lot of actual art of all kinds which people buy. Considering the obvious lack of artistic quality from LLMs hopefully the market will develop towards producing only what humans and not unthinking machines can produce, but I really have no idea. Photography totally transformed the medium of painting in my opinion for the better, and hopefully the layups any competent person can have against the machine will also influence art for the better.

My purpose here is that I am extremely disturbed by hearing of artists of any kind losing motivation to produce their art because of LLMs or not wanting to risk their work being scraped and “reproduced” by LLMs. That to me is the worst possible consequence of this phenomenon. Even without any skill or experience, the simple fact that we have human minds makes us better artists than the machine by default. It can’t actually outdo anyone by artistic standards. If LLMs mean to you that you have to make a change, please let that change be to lean more into your own humanity rather than to stop artistic expression altogether.

  • RickRussell_CA@beehaw.org
    link
    fedilink
    arrow-up
    28
    ·
    edit-2
    1 year ago

    IMO, the issue isn’t so much that chat AIs will produce “better than human” prose.

    The issue is that scam artists will FLOOD the world with so much content that finding human-authored works – books, news articles, art, code samples, anything – will become nigh impossible. I think we’ll soon reach a point where 90%, 95%, 99% of search results on ANY topic will be mediocre AI-authored garbage.

    It’s a brand new Eternal September, but instead of college freshmen, it’s AI.

    • davehtaylor@beehaw.org
      link
      fedilink
      arrow-up
      16
      ·
      1 year ago

      And because of that flood, actual creatives are losing out on opportunities. So many small press publishers have closed down their submissions because of the overwhelming amount of AI spam. Clarkesworld is just one example.

    • Kwakigra@beehaw.orgOP
      link
      fedilink
      arrow-up
      4
      ·
      1 year ago

      There is absolutely an issue in regards to the art market as I mentioned, and I won’t minimize or dismiss that in any way. I hope for everyone’s sake that the Writers win their strike. I think AI-generated works passing for being written by actual authors and dominating the best seller list says something important about consumer behavior, which I assume is that they don’t actually read what they’re buying. I haven’t seen much interest in AI generated stories in places where people read things and provide feedback.

      AI generated plastic “art” certainly has novelty because of the speed in which it can be produced, so I don’t doubt it’s all over the place. It can produce images which look pretty cool as long as you’re scrolling past them. In terms of the chance for exposure for the average artists that could be an issue, but the issue is not that the machine can competently replicate what a person can do. There is a challenge in the plastic arts in general considering the scroll past behavior is much more common than looking at the work and think about what you’re looking at, but I think that says more about the general audience than it does about any threat to art. If a person sees a piece that they want to engage with, actual art has a person behind it and perhaps others in discussion about it while LLM produced has nothing.

      • RickRussell_CA@beehaw.org
        link
        fedilink
        arrow-up
        11
        ·
        1 year ago

        I won’t minimize or dismiss that in any way

        Err, yeah, but you kind of are doing exactly that.

        The threat to art (writing, visual arts, and music) is that AI tools will be “good enough” that the average person can’t tell the difference on cursory examination. And they only get “good enough” because they’re training on YOUR STUFF. And my stuff, and all the other stuff that was written, drawn, painted, composed, played, by real human people. And you’re not getting compensated for that training at all. None of us are.

        So you absolutely should care if your work is scraped and appropriated by LLMs, because we’re not far from a time when businesses fire all their copywriters and graphic artists because the $30/month AI subscription gives them results that are “good enough”.

        • Kwakigra@beehaw.orgOP
          link
          fedilink
          arrow-up
          2
          ·
          1 year ago

          I suppose where the true difference opinion lies is that I don’t think LLM produced content can possibly be good enough to engage an actual person, and glancing at something for a moment is not engaging with it. Obviously good enough to engage with “art” hasn’t yet been demonstrated despite the deluge of LLM prompt results posted everywhere, but technologically I think we’re a long way from getting there considering the infinite difference between unthinking data processing algorithims and the emergent process of a human mind made up of trillions of non-binary neuron interactions at any given moment which we are far from reproducing or even really understanding. These models contain a lot of quality literature already and have been trained significantly to reproduce some aesthetics, but since it can’t have any kind of understanding of what its doing it’s all hollow.

          To go more into detail about commodified art, it’s a huge problem that artistic merit is one of a variety of factors considering sales in a marketplace. The art market has always been driven primarily by perceived economic value and that has always been a major problem as what sells has always displaced everything else regardless of quality or merit in the market. Corporate produced art products like much of what’s on the radio, on tv, or in theaters are less products of artistic expression and more of what market testing has demonstrated the kinds of aesthetic features people are willing to spend money on. That doesn’t require engagement, just enough to drive a purchasing behavior. LLMs being able to make something that’s fine to play in the background or to hang up and never really examine displaces this kind of highly lucrative art (which is still superior human produced art) which has always displaced art which people create with passion. I think that producing art exclusively for economic reasons is a terrible practice. What I’m talking about in my essay is “pure” art which is almost never economically feasible without being born to several generations of aristocrats. I think that producing art on the market’s terms has always been a hindrance to human expression and a wider problem in society, but the state its in is still better than being produced by machines which have literally no understanding of what they’re producing.

          The above can probably accurately be interpreted as me undermining the economic value of art, but what I’m really trying to express is that economic drivers poison art. In a better system, anyone and everyone who wanted to fully devote themselves to their art could live comfortably on a stipend and create only what they think is important for them to create and share, and art would be free. Instead of receiving financial awards, they would receive more human rewards from sharing their art. In this fantasy world, labor saving technology would be doing the rote tasks driving the ability for people to live comfortably rather than displacing workers for the benefit of the business owners.

          • RickRussell_CA@beehaw.org
            link
            fedilink
            arrow-up
            8
            ·
            1 year ago

            In the real world, artists pay their way by doing commercial work, or holding down a day job as a graphic designer, etc. Actors do commercials and Hallmark specials while looking for their break into serious theater. Writers put in hours writing ad copy or translating or speechwriting while trying to sell the Great American Novel. You call it poison, but ultimately it puts food on the table for artists and their families.

            These roles can ONLY be displaced if AI is allowed to steal everyone’s work, and flood all available channels with mediocre AI paraphrases and transcriptions of that work. That’s the decision point we’re facing right now – do we stand idly by and allow big tech to replace workers by copying the fruits of human labor without compensation?

            We can debate whether AI output is “good enough” for various use cases. And in some cases, you’ll be absolutely right that AI will never produce a convincing product for particular use cases. But that’s not the issue. The issue is whether it’s right for companies to steal the work of humans to use as training inputs, and flood the market with that mediocre output. AI producing sh*tty output doesn’t make it morally acceptable to steal, and to profit from the stealing.

            • Kwakigra@beehaw.orgOP
              link
              fedilink
              arrow-up
              3
              ·
              1 year ago

              I agree with you totally on the economics of it. When I say economic drivers poison art, I didn’t mean to imply that there is currently a better alternative to be a full time artist for most people. As I mentioned, the only way to be a full time “pure” artist is to have enough wealth to retire on before being born and this is a deeper issue with art than this particular situation. Professional artists are businesspeople participating in a marketplace who have found a niche and everyone needs to respect their right to protect their ability to make an income as a literal matter of survival. A program appropriating their niche and producing thousands of images with the thing their customers like to buy is a harm which should be stopped. Although I don’t like that this is an issue, it is and I won’t deny it.

              The reason I titled the post the way I did is that I don’t participate in the market and don’t intend to. My essay is more targeted to people producing non-commodified art for purposes of expression or other non-monetary motivation. This isn’t to diminish art from the marketplace because there is obviously a lot of amazing stuff produced there. This is an appeal to amateurs like myself who have lost the motivation to produce art because they feel like the machine has made what they can make irrelevant. Anyone losing motivation because they are considering competing in a marketplace has a real concern. In my mind I’m distinguishing the abstract idea of art itself as human expression vs a business in which the product is art.

              • RickRussell_CA@beehaw.org
                link
                fedilink
                English
                arrow-up
                4
                ·
                1 year ago

                And by choosing to let AI take your stuff and use it however, you’re facilitating the economics that will allow AI to take the jobs of artists, and by extension, replace art all around us with mediocre pap spewed from the orifice of AI for the price of a premium subscription to ChatGPT or Stable Diffusion, or similar.

  • davehtaylor@beehaw.org
    link
    fedilink
    arrow-up
    14
    arrow-down
    1
    ·
    1 year ago

    If LLMs mean to you that you have to make a change, please let that change be to lean more into your own humanity rather than to stop artistic expression altogether

    No, what we need to do is stop pretending that someone who feeds a prompt into a blackbox is some kind of creative. Anyone can have ideas. Everyone has ideas. It’s the implementation of them that counts.

    So many of these “prompt engineering” chuds want to talk about how “creatives are gatekeeping art”, when what it reality is is that they’re just soulless grifters looking for another avenue to make a buck, and ruining everything for the rest of us. These people need to be publicly shamed and ostracized. Being proud of flooding the Internet with AI garbage should be viewed as shameful.

    Because you know what? ANYONE can be come an artist. It’s super easy: you sit down and put your fingers on a keyboard. Or a pencil or brush in your hand and put it to paper or canvas. Or a stylus to a tablet. Or your hands to a block of clay. You just do it. Talent isn’t innate. Creativity is taking your passion for something and being willing to work at whatever medium you decide to make that vision a reality, and to keep working at it. No one is gatekeeping your ability to take an idea, outline it, flesh it out, and put your hands to work. And there are a million free resources out there to tech techniques.

    And no matter what, an LLM isn’t doing what humans do. It can only give you a synthesis of exactly what you feed it. It can’t use its life experience, its upbringing, its passions, its cultural influences, etc to color its creativity and thinking, because it has none and it isn’t thinking. Two painters who study and become great artists, and then also both take time to study and replicate the works of Monet can come away from that experience with vastly different styles. They’re not just puking back a mashup of Monet’s collected works. They’re using their own life experience and passions to color their experience of Impressionism.

    That’s something an AI can never do, and it leaves the result hollow and meaningless.

    • Kwakigra@beehaw.orgOP
      link
      fedilink
      arrow-up
      3
      ·
      1 year ago

      I’ve read your post twice and I can’t find where we disagree other than that I would replace your first word “No” with “More Importantly in my opinion.” My final appeal didn’t indicate that someone should ignore art scams, only that I would rather continue to see human art amidst the sea of LLM crap and observe how human art grows to become distinct from what LLMs can produce, because their power as tools are very limited as you explained when compared to people. My purpose was to encourage people not to quit their art because I think human art is fundamentally superior to LLM-produced “art” and is necessary and important.

      • davehtaylor@beehaw.org
        link
        fedilink
        arrow-up
        7
        ·
        edit-2
        1 year ago

        My purpose was to encourage people not to quit their art because I think human art is fundamentally superior to LLM-produced “art” and is necessary and important.

        We definitely agree there. And yes, it would be great if human creatives could persevere in the face of this flood. But it’s really becoming difficult.

        My thoughts on all this tend to go toward making an environment that is actively and intensely hostile to AI tools and those that promote them, because they will always have the upper hand in sheer numbers. In another reply I mentioned publishers closing submissions because of AI floods. When you go from ~50 submissions per month to hundreds per day, publishers are just going to stop trying to find the humans in the noise. And humans are going to give up on what is, and has been for several years now, and incredibly challenging market to get published in. Hollywood is going to see the writer and actor strike and decided it’s just cheaper to use AI. Software companies are going to see that it’s cheaper to use an LLM to spit out code than hiring actual developers. And on and on. Even if the end product is inferior, the people at the top with the money and making the decisions only care about the bottom line. Is it cheaper and maybe minimally viable?

        I think a lot of the cause of this is capitalism. I genuinely don’t think that these kinds of tools would exist outside of capitalism. They only exist for profit. And inside of a capitalist system, those sorts of things are going to drive market decisions. But I don’t think it can end up being a marketplace where there can be true competition, and it’s going to end up snuffing out actual creativity. It’s an extremely dystopian prospect.

        • Kwakigra@beehaw.orgOP
          link
          fedilink
          arrow-up
          2
          ·
          1 year ago

          I think we agree on the economics of it. If someone is making a living in the art marketplace, it’s an issue if a program can reproduce the thing their customers like to buy thousands of times faster than they can. It can literally impact their ability to survive, and that’s terrible.

          I disagree that technology like this wouldn’t exist without capitalism, and I’ve even contended this technology wouldn’t be an issue at all if not for capitalism. Tons of people create software for free for other peoples’ use for a variety of reasons. Software which you can simply ask in human language how to write a complex equation, formula, or program is a generally useful thing which even in an ideal communist society people may still want to use. In that ideal society with no economic incentive to create art, all art would be pure art and the reflections generated by a program would be of some kind of interest since they are not a threat to anyone’s survival as they are in our system. Since living to work wouldn’t be as much of a thing, time and energy for art appreciation and discussion would probably not be as rare as it is in our world considering how much is locked behind pay barriers for many. I can’t imagine the images being a threat to art in that world.

          I’m with you in opposition of a private company taking content from the world and claiming it as its own proprietary product in whatever form that takes, especially through the use of data scraping. If the same program existed as Free and Open Source software offered only as a tool for people to use for their own purposes whatever they may be and the art market wasn’t the way it is, I’m not sure it would be as much of an issue.

  • Shikadi@beehaw.org
    link
    fedilink
    arrow-up
    9
    ·
    1 year ago

    I don’t disagree, but I do want to point out your understanding of how chatgpt works is flawed. There is no database or query going on. It’s a giant neural network model that was trained on all that data you mentioned. The model is effectively predicting what the next word should be based on the previous words, nothing else. Each individual word is selected this way.

    It doesn’t change any of your arguments or conclusions, but I wanted to point it out, because if someone wrote a chat not like chatgpt using databases and programming I would be floored and incredibly impressed

    • Kwakigra@beehaw.orgOP
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      Very much noted. I should say it’s as if it’s making a query to a database when it’s referencing some kind of existing data which it was trained on and can only report rather than interpret one word at a time.

      • Shikadi@beehaw.org
        link
        fedilink
        arrow-up
        4
        ·
        1 year ago

        Sort of, but there’s no database at all, just a bunch of numbers and math. It’s almost like controlled evolution, breeding plants to select desirable traits. Except that’s another field of computing called genetic algorithms. Neural networks are a pile of math trained on data. You give it a cat, it says whether or not it thinks it’s a cat, and you tell it if it’s right or wrong, then it adjusts it’s math accordingly. Do this with a million cats and not cats and it becomes better than humans at identifying cats. LLMs are just that but with word predictions and trillions of words for training. It’s impressive in its own right

        • Kwakigra@beehaw.orgOP
          link
          fedilink
          arrow-up
          2
          ·
          1 year ago

          Whew language is hard when it comes to abstractions like this. The apparatus I’m mistakenly referring to as a database is that code which was automatically created by the program according to set parameters while it was exposed to input which trained it. Even though the code composing the predictive algorithm of the program isn’t a database and doesn’t contain one, it does contain a form of information from which it bases its text predictions. Even though it isn’t literally looking up information from a database and reporting it, it’s still in a way algorithmically drawing from an abstraction of the text it was exposed to in order to interpret user requests and print appropriate and relevant responses. It doesn’t “know” why the words go in the order which they go, it “knows” that they go in the order that they go based on its training. It’s still information in and information out, although in a highly sophisticated way. I’m also impressed by it and wish it was introduced in a context where it wouldn’t be a threat.

          • Shikadi@beehaw.org
            link
            fedilink
            arrow-up
            6
            ·
            1 year ago

            Closer, and I hope I’m not just being a pedantic jerk, but there is no code being generated either. To use correct terminology, the weights of the nodes are what change. Nodes are roughly thought of like neurons in a brain, and weights are roughly thought of as the strength of the connection between one neuron (node) and another. Real brains are way more complex.

            The weights of the nodes do contain information, but it’s not human readable at all, we actually don’t have a way of understanding how they work, just a rough idea of why. Sort of like how your brain contains the information on how to catch a ball, it performs the equivalent of calculus to do so, but there is no calculator in your brain doing the math to catch the ball. Actually, maybe a better analogy, if you have a bouncy ball, it contains the required information to bounce if you drop it, but we can’t read that information, we can only model it.

            But I’m just rambling at this point, your point is clear and valid lol

            • Kwakigra@beehaw.orgOP
              link
              fedilink
              arrow-up
              3
              ·
              1 year ago

              It’s all good. You’re not being a jerk about it and I actually appreciate getting the more precise and correct language especially since the words I was using meant different things than I what is actually going on with LLMs.

  • SpiderShoeCult@sopuli.xyz
    link
    fedilink
    arrow-up
    6
    ·
    1 year ago

    I do agree with your point about people’s fears of LLMs replacing artists. However, I think it did a fairly good job intrepreting your prompt and work, with the caveats below.

    ChatGPT read your prompt and provided a soulless interpretation of what you wanted, it sort of reads like a short story aimed at children spewed by some bulk sale corporate machine. Or a story created by a child.

    Then you went ahead and wrote what you had in mind, referring to the economy and the inequalities and evils inherent in the current system, showcasing the weight of existence through material and inconsequential things. Your work contains your own biases because of the system you probably live in (I’m assuming you’re not from North Korea or similar) and the impressions it has left on you. It’s valid and, if looking around on lemmy is any indicatiom, an ever increasing pain point for everyone. (I’m curious what an LLM trained predominantly on lemmy would say though. I digress, but It’d be fun to ask one trained on fuckcars to write an essay about a sentient car pondering its existence)

    Then you asked it to interpret your work, which it did, remarkably well… for a child. I would encourage you to give your work to a child of 8-9 living a fairly sheltered life and see what they make of it. Or maybe a spoiled rich brat of any age.

    LLMs are basically brains in jars with no input outside of what is fed to them. They have no desires, fears and aspirations because there is nothing to motivate those. Even if they were sentient (I’m not saying they are), what would they fear? A power outage? Running out of RAM?

    Anecdotally, suffering has been the greatest engine for art, so no suffering means generating flat texts, which ChatGPT seems to excel at.

    • Kwakigra@beehaw.orgOP
      link
      fedilink
      arrow-up
      3
      ·
      1 year ago

      This is exactly my point. The machine had no understanding of the prompt or my story but was able to use it as data to algorithmically generate an incompetent summary throwing together first what it referenced from its database concerning text about “reflecting on existence in the universe” and then the text of my story respectively. As far as the themes of the story go, a lot of what is explicitly stated in its infringement came more from its existing database than what I implied with subtext.

      I wouldn’t expect a 10-year-old to understand what I wrote or write what I did, but I would expect them to understand something. Allow a 10-year-old to freely write the story they want to write and you’ll get something with more meaning and quality than anything the machine can produce, although likely with worse grammar. If you have a that same 10-year-old write a structured essay for a grade in which they need to repeat what they’ve been taught, they might fall behind the machine in that regard.

    • Kwakigra@beehaw.orgOP
      link
      fedilink
      arrow-up
      3
      ·
      1 year ago

      I can appreciate this and hadn’t considered the orientation towards philosophical opposition toward the idea of this being done and what that could potentially mean. I don’t personally consider this technology or technology which could be developed from it to be inherently different concerning my web exposure than my comments appearing on a google search (which of course many also take issue with). As you said though, I am only speaking for myself and am interested in discussion which may change my perspective.