Fine-tuning an LLM into a style guide editor

Hello! This is my first post on these forums. I have been exploring generative AI from a technical writing perspective over at for the last month or so.

I thought you all would like to hear about my latest experiment. Last weekend I experimented with using fine-tuning to turn ada into a style guide editor. The initial results seem to suggest that it could work. Fine-tuning an LLM into a style guide editor

I am a total n00b in the GenAI space though so please do let me know if it seems like I’m fundamentally misunderstanding or misinterpreting anything. Also if this approach is a dead-end or an “already solved” problem then that would definitely be relevant to my interests also!

(P.S. the forum UI told me to choose a tag but none of them seemed related to what I was working on so I just chose the closest one.)