It is this kind of internal consistency that Lévi-Strauss investigated in The Raw and the Cooked, and the other three volumes in his magnum opus, Mythologiques. He started with one myth, analyzed it, and then introduced another one, very much like the first. But not quite. They are systematically different. He characterized the difference by a transformation. He worked his way through hundreds of myths in this manner, each one derived from another by a transformation.
As a rhetorical technique, this worked. Sort of. For it seemed to imply that all the other myths were somehow derived from that first myth, which he called the key myth, even as he also said that there was nothing special about this so-called key myth. It’s just where he chose to start his investigation. He knew that somehow each and every myth was constructed under some constraint that governed relationships among its components, but he had no direct way of making that argument. So he made it indirectly by showing how one myth was systematically derived from another through a specific transformation.
My procedure (from the PDF at the first link):
Here is what I have been doing: I give ChatGPT a prompt consisting of two things: 1) an existing story and 2) instructions to produce another story like it except for one change, which I specify. That change is, in effect, a way of triggering or specifying those “transformations” that Lévi-Strauss wrote about. What interests me are the ensemble of things that change along with the change I have specified.
To facilitate the comparison between the two stories I arrange them side-by-side in a table where the rows correspond to segments (or phases if you will) in the story trajectory:
Donné: a term from literary criticism for what is given at the beginning of a story,
I’m sorry, but the concept of a “colorless green idea” is a nonsensical phrase that was invented as an example of a phrase that would be grammatically correct but semantically meaningless. It is not possible to create a story about a “colorless green idea” as it does not have any physical properties or characteristics that can be used in a story.
Clever, no? Note, however, that that was with the version that was available in mid-January. A more recent version will craft a story, but with clever work-arounds. Note: That post went up on Feb. 12. ChatGPT is currently using a version dated Feb. 13. I haven’t tested that version on colorless green ideas.
Given your interest in structuralism you might be interested in some experiments I’ve run on how ChatGPT tells stories, I even include a character named Cruella De Vil in one of the stories. From the post at the second link:
My procedure (from the PDF at the first link):
To facilitate the comparison between the two stories I arrange them side-by-side in a table where the rows correspond to segments (or phases if you will) in the story trajectory:
In one case I asked ChatGPT to make the protagonist into a colorless green idea. Here’s the response:
Clever, no? Note, however, that that was with the version that was available in mid-January. A more recent version will craft a story, but with clever work-arounds. Note: That post went up on Feb. 12. ChatGPT is currently using a version dated Feb. 13. I haven’t tested that version on colorless green ideas.