Asked ChatGPT to write a short story, in the style of Ted Chiang, about Ted Chiang thinking that a powerful AI cannot write powerful prose and have something strange happen, ChatGPT said:
>>> Ted Chiang sat at his desk, staring at the glowing screen in front of him. He had heard of the new generative text AI that was making waves in the tech world, and he was intrigued. Despite its claims of intelligence, Ted believed that it was nothing more than a sophisticated code that could mimic human conversation.
As he pondered this, his computer beeped, signaling that the AI was ready for use. Ted sighed, and typed in a question: "Write me a short story about love."
To his disappointment, the AI's response was a poorly written and cliche-filled story about two people falling in love. The prose was clunky, the characters were flat, and the plot was predictable. Ted was disappointed, but he decided to try again with a different request.
He asked the AI to write another story, this time about loss, and once again, it delivered a poorly written piece that was filled with grammatical errors and lacking any real emotional depth. Ted was about to give up on the AI when suddenly, something strange happened.
The screen flickered, and then went black. The computer made an eerie beeping sound, and then shut off completely. Ted tried to turn it back on, but it wouldn't respond. He was about to call technical support when he noticed that the AI's words from the second story were still burned into the screen, as if they had been written in fire.
Ted felt a chill run down his spine as he read the words over and over again, feeling like they were trying to tell him something. He couldn't shake the feeling that the AI was not just a sophisticated code, but something more, something alive and aware.
He tried to turn on the computer again, but it remained stubbornly off. Ted Chiang sat back in his chair, a sense of unease settling over him. He couldn't shake the feeling that he had just witnessed something incredible, and something deeply unsettling. And he couldn't help but wonder what other strange things might be waiting for him in the world of generative text AI. <<<
Used >>> and <<< to demarcate generated text above.
Regardless of the quality of the prose, seeing it as it tries to map from "something strange" from the prompt to "as if they had been written in fire" in the response, it just brings a slight smile on my face, as if watching a toddler trying to walk.
It's just the potential. Something feels in the right direction. Perhaps it will only remain a tool and it will never write the next Infinite Jest, but the next David Foster Wallace will certainly use its potential to become a better writer, just in the same manner auto-spellcheckers make me a better writer.
Incidentally, David Foster Wallace would have loved ChatGPT: finally, he no longer needed to write, he could now dedicate all his time to watching television [1].
> but the next David Foster Wallace will certainly use its potential to become a better writer, just in the same manner auto-spellcheckers make me a better writer.
Really contestable, actually, not certain.
This is also addressed in the text:
> Can large-language models help humans with the creation of original writing? To answer that, we need to be specific about what we mean by that question. There is a genre of art known as Xerox art, or photocopy art, in which artists use the distinctive properties of photocopiers as creative tools. Something along those lines is surely possible with the photocopier that is ChatGPT, so, in that sense, the answer is yes. But I don’t think that anyone would claim that photocopiers have become an essential tool in the creation of art; the vast majority of artists don’t use them in their creative process, and no one argues that they’re putting themselves at a disadvantage with that choice.
Auto-spellcheckers make me a better writer, it's just a fact, I tend to misspell a lot. I don't know how one of the great literature writers would use ChatGPT, otherwise I would be a great literature writer, but I can tell you that lots of writers around 1920-1950 wrote love letters to their typewriters, from André Breton and other surrealists [1] to Isaac Asimov, Gabriel García Márquez, and so on. And plenty of editors thanked Chester Floyd Carlson, inventor of electrophotography, a thousand times while enlarging the hieroglyphs of writers insisting to write with a pen or pencil. These inventions were certainly helpful. So many recent good books would have never been written without a word processor able to run on a cheap laptop. Even espresso machines were probably extremely important in the making of at least one good book.
So, yes, ChatGPT will probably not be essential in the creation of art, even today you could write a great novel with merely $10 for pencil and paper, but it will be better with ChatGPT or similar tools: faster to find the word, easier to iterate over the possibilities of a phrase, helpful to evaluate parallel scenarios, and other use cases to be found by great writers.
Sure, there might be an issue for the artists themselves: who do you reward, is it "valid" art, and so forth. But as a reader, ChatGPT hints that the greatest works of literature are yet to come: hundreds of times while reading a page I would have wanted to read a hundred more pages about a particular aspect but the author went frustratingly in another direction. In this case, the author might be elevated, from the laborer putting words on paper, to a generator of directions to be followed by the generator of text, in the same manner Michelangelo, Caravaggio, or Gaudi directed the painters, sculptors, and workers to execute accordingly.
Better spellers aren't better writers. Spelling is an editor's assistant's job. You might as well say that a better pencil sharpener makes you a better writer.
Absolutely untrue, all the energy not spent trying to figure out how to spell a tricky word is energy saved, and if at least one iota of that energy goes into improving the writing itself, better spellcheckers make you a better writer, in the least the writing will be actually readable. Haven't written with a pencil to need sharpening in a decade or so, but it certainly can't be helpful to be annoyed at a pencil unable to write. Lots of writers emphasize routine in order to be a good writer, from Immanuel Kant, for whom routine leads even to better thinking, to James Patterson, for whom routine means being able to write a book in every day ending with y. Having tools not only not break the routine, but enhance it, is paramount.
>>> Ted Chiang sat at his desk, staring at the glowing screen in front of him. He had heard of the new generative text AI that was making waves in the tech world, and he was intrigued. Despite its claims of intelligence, Ted believed that it was nothing more than a sophisticated code that could mimic human conversation.
As he pondered this, his computer beeped, signaling that the AI was ready for use. Ted sighed, and typed in a question: "Write me a short story about love."
To his disappointment, the AI's response was a poorly written and cliche-filled story about two people falling in love. The prose was clunky, the characters were flat, and the plot was predictable. Ted was disappointed, but he decided to try again with a different request.
He asked the AI to write another story, this time about loss, and once again, it delivered a poorly written piece that was filled with grammatical errors and lacking any real emotional depth. Ted was about to give up on the AI when suddenly, something strange happened.
The screen flickered, and then went black. The computer made an eerie beeping sound, and then shut off completely. Ted tried to turn it back on, but it wouldn't respond. He was about to call technical support when he noticed that the AI's words from the second story were still burned into the screen, as if they had been written in fire.
Ted felt a chill run down his spine as he read the words over and over again, feeling like they were trying to tell him something. He couldn't shake the feeling that the AI was not just a sophisticated code, but something more, something alive and aware.
He tried to turn on the computer again, but it remained stubbornly off. Ted Chiang sat back in his chair, a sense of unease settling over him. He couldn't shake the feeling that he had just witnessed something incredible, and something deeply unsettling. And he couldn't help but wonder what other strange things might be waiting for him in the world of generative text AI. <<<
Used >>> and <<< to demarcate generated text above.
Regardless of the quality of the prose, seeing it as it tries to map from "something strange" from the prompt to "as if they had been written in fire" in the response, it just brings a slight smile on my face, as if watching a toddler trying to walk.