In general I’ve found fancy prompting and scaffolding techniques don’t really improve the model’s creativity all that much when trying to one-shot a story. Even when I discuss setting and plot details with the model and try to guide it towards something interesting, it mostly seems to latch onto 1 idea and go default mode for everything else. The most satisfying way for me is to use text completion to continuously generate the story a couple hundred tokens at a time (koboldcpp has a mode for that) and edit its output as I go along. At that point it feels like using the LLM as a writing aid rather than treating it as a co-writer though.
In general I’ve found fancy prompting and scaffolding techniques don’t really improve the model’s creativity all that much when trying to one-shot a story. Even when I discuss setting and plot details with the model and try to guide it towards something interesting, it mostly seems to latch onto 1 idea and go default mode for everything else. The most satisfying way for me is to use text completion to continuously generate the story a couple hundred tokens at a time (koboldcpp has a mode for that) and edit its output as I go along. At that point it feels like using the LLM as a writing aid rather than treating it as a co-writer though.
Most of the open-weight models I’ve tried out came from here: https://huggingface.co/TheDrummer
Yeah, I generally don’t even try one-shotting stories. :D
Thanks for the link!