Study: AI-generated stories rated better quality than human-written ones

Latte And Now For That Latte
1

I’m not trying to upset everyone. But this is interesting. And beyond these paragraphs, there are some good comments from the researcher:

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.

Whole article, with a link to the study:

2

It’s a similar story with music.

3

It strikes me that telling participants, correctly or incorrectly, about authorship invites bias either way.

4

I feel very suspect about this. Like, wanting to make sure an AI firm isn’t paying for the study directly or through cutouts. Seriously, either it’s a complete troll job, or…. The tiktokers have fully developed what they expect from fiction based on the slop that is all they are fed, and have no tools to digest proper human-written prose.

I shall prepare the tissues for I fear I shall be weeping for my antecedents soon.

1 Like
5

I’m suspect of this study in general, as @Dain says below, but this just implies that people prefer art made by other people, regardless of its quality.

That they’d rather consume things made by people than slop made by a machine, isn’t as much bias as it is just natural.

6

You can click through to the study to read the authors’ funding and competing interest statements.