Comment by gcanyon

I had an idea for a hard science science fiction short story about five months ago. I had grown tired of Star Trek digging their way out of every problem by throwing techno-babble at it, so I wanted to write something where one scientific leap is made and everything else holds as we understand it.

I thought to experiment with having an LLM help me write it. I wrote a bullet-point outline and had the LLM revise it -- that went pretty well, although it's not the outline I ended up using.

I asked the LLM to write the first section based on that outline. The result was (surprisingly) awful. LLMs are way worse at writing fiction than they are at writing business communication Or maybe I'm way worse at prompting, but the results of this contest make me think the former.

In particular, LLMs are incredibly terse -- the LLM took the bullet point outline and turned it into a twice-as-long bullet point outline.

I wrote the first section myself (expanding from the bullet points by something like 10-20x, and asked the LLM to write the second section, and it failed miserably again. I tried multiple ways to get it to do the job properly, and nothing came out the way I wanted.

So I wrote the whole thing myself, with LLMs serving two purposes: physics review for accuracy -- the story heavily involves special and general relativity, which I'm familiar with, but nowhere near competent enough at to keep the math aligned; and feedback on the story structure.

So I ended up writing the whole thing myself, with LLM consultation on a few bits. In the end it turned into a novella, and I had to re-write based on physics issues (I found about 30% of them, Gemini found 50%, ChatGPT and Claude found 10%, and Fable found 10% late in the game -- Fable's review was amazingly thoughtful) so many times I probably ended up writing a novel in the process :-)

In case anyone is curious: https://docs.google.com/document/d/19e3HfnK1lNHHBef-5c-KvNdD...