cross-posted from: https://beehaw.org/post/27795833
In a study published in the journal Judgment and Decision Making, 1,682 adults were asked to read one of six short stories, three of which were written by humans and three by ChatGPT. Each AI story had a similar theme to one of the human-authored works.
The team told participants whether their story was written by a human or AI, but this information was not always correct. The researchers then asked participants to rate how absorbing and engaging they found the story, and its quality.
Participants who read an AI-generated story rated it as more absorbing and of higher quality than those who read a story written by a human. However, participants gave higher ratings to stories they had been told were written by people.
Dr Deena Skolnick Weisberg, a senior author of the research from Villanova University in Pennsylvania, said: “AI systems can already generate short stories that are seen as being at least as good as – if not better than – human-written stories. We should update our views of AI’s abilities accordingly.”
However, Weisberg, who is herself a creative writer, said that did not mean writing should be left to AI, noting that novels produced by tech were probably going to be different from those written by humans.
“We may need to make room for AI-generated novels, and for AI/human co-written novels, but that doesn’t mean that there’s no longer space for us to appreciate the process of human creativity,” she said.
I didn’t read the article, but from the summary, it’s not obvious which humans wrote the stories. Famously, the ability of humans for writing is not the same for everyone. The average person writes like shit. The average writer writes kind of ok. The top few percentile of writers write really well, and the rest of humans like to read what those writers write. So if in the study, they asked a 6 year old, a plumber, and an accountant for a story, I completely understand that ai rated better. But even then, I would rather read 10 bad stories by random people than 10 passable-appearing ai stories.
Stories. We used three fictional short stories written by human authors, which were published in a reputable literary journal or short story collection. We then used ChatGPT to generate three corresponding fictional short stories. All stories had word counts of approximately 1,000 words (equating to approximately a five-minute read). This length was long enough for participants to have a sense of the writing style and be potentially absorbed by the story and also short enough for participants to be fully engaged throughout the whole story.
From the study. They go on to list out all the stories, where they were published, when, the author, and the prompt they used for the AI equivalent. (It was a lot to copy here, though, so I didn’t.)
But even then, I would rather read 10 bad stories by random people than 10 passable-appearing ai stories.
Part of the study is that you probably wouldn’t be able to tell, and that if you were told that a story was written by AI, and you are biased against AI, you’d rate that story as worse, even if it were written by a human.
Don’t underestimate an average person’s love for slop content. Yes it’s true AI systems have gotten better and will continue to get better, but it’s also not what most people care. My mom watches AI generated drama everyday. My dad too has no problem with AI short form content.
It sucks but that’s the state of the world right now.
Edit: thanks to the guy who posted the link to the study below. In that study it’s written that a similar test was performed in 2024 and they had similar results. Somehow only proving my point.
The first AI story I read: sure.
After a few more? I felt a certain sameness to them.
Do you have data to support this claim? Or do you mean if you keep giving the same prompt you’ll get very similar outputs?
Personal experience.
Okay, your opinion isn’t very valuable in this context, but maybe we can salvage something. How many AI stories have you read?
I mean… yeah? All authors have their own styles and they sound the same if you read a decent chunk of a single author.
A different AI and different prompts would be like a different author and would relieve that issue.
It’s emulating real life pretty well if that’s the case.
Do you have any examples? The little I’ve played with Ai the different models can give wildly different results from even just asking for a synopsis of an email.
If you are just using the same Ai and similar prompts like “write a murder mystery” I could see it happening. But that’s just not understating AI at that point.
But at the same time, ask the same author to write 10 murder mysteries and they’ll sound similar too.
I don’t give two good shits if AI does write better (which I doubt). I don’t want to read artificially created writing based on material stolen from its human authors.
Damnit I’m gonna see this all over now aren’t I?
