I've tried different approaches like feeding it examples of my own writing, giving it a style guide, and iterating a few editing sessions, but it appears the way these models write/talk is rather deeply ingrained, and it usually end up easier for me just to write myself. Has anyone found a good approach to make models write better?
You edit it manually.
That's it. There are no shortcuts to good prose, except perhaps paying a ghost writer.
Good human prose is rarely written in one shot. It is heavily rewritten over a long period. How about getting one ai to write it, one to improve?
Is this just an elaborate scheme to increase in/out token churn or are we hitting some kind of LLM limitations I wonder?