The Aeneid is an epic poem by Virgil that tells the story of Aeneas and, more broadly, gives a sort of mythic legitimacy to Rome. It ties the founding of Rome to the legends of Troy as descendants of Aeneas. It also took the traditional Roman values and elevated them to divine values.
It did this by directly drawing on the narrative structure, characters, and storytelling approach of Homer’s epics.
The Aeneid is divided into 12 books — Homer’s epics have 24 books each.
Books 1-6 directly parallel the Odyssey, and Books 7-12 directly parallel the Iliad.
Direct references and allusions to Homer’s characters and events
Characters map nearly one-to-one with those in Homer’s epics
The Aeneid isn’t the only book that does this. Paradise Lost (Milton) and the Divine Comedy (Dante), Ulysses (Joyce), and Odyssey (Homer), to name a few. There are even more examples if you expand outside just writing (e.g., West Side Story / Romeo and Juliet).
But text-to-text is the most interesting. Why?
AI might be best equipped to write this type of story first. Imagine Homer’s epics as a vector embedding (possibly book by book, surely high dimensional). Also, imagine that we know what many of these dimensions encode (plot, characters, setting, style, etc.).
Now, what if we just changed a few of these? Just like one of the most entertaining use cases of early ChatGPT was writing a letter in the style of Shakespeare or Yoda, we might do that for a whole book (and not just style, but mapping characters or style or other key elements that we want to change).
The method might solve many of the context-dependent problems with writing a book — it’s hard to keep track of plot twists and turns over the course of hundreds of pages (if you’re an LLM). But if we just borrow that structure from existing works, it might be easier for LLMs to generate (and for humans to pattern match against).
Could most of the heavy lifting just be reduced to vector math? Then, it would only be up to the human writers to decide the important themes and perspectives that they want to share.
I’d love to see the copyright law evolve to accommodate some of this while still honoring living rights holders. You could imagine a system not unlike existing streaming services that would pay royalties out of some superfund that the model providers collect such that prompts using particular artists by name (e.g. “write me a song in the style of Taylor Swift”, etc) would pay at prompt time (like a stream) and embed a credit into the result in case the generated material goes on to commercial release and generates additional revenue. Also would provide some nuance for prompts that are not calling an artist out by name. Then the prompting becomes part of the art.