How to make AI better at writing prose?

Question

Current models are still notoriously bad at writing prose. It's not just the easily recognizable tics like "load-bearing" and "genuinely". The text is just sloppy, pompous, and full of air.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?

hankbond · Accepted Answer

What is your goal? What are you trying to have it generate that is not more appropriate for you to write yourself?

devilsdata · Answer

I'm a fiction writer. The way you make AI better at writing prose is the same way you make a fiction writer better at writing prose...
You edit it manually.
That's it. There are no shortcuts to good prose, except perhaps paying a ghost writer.

iExploder · Answer

Pompous and full of air really sums it up well. As such I usually have to completely ignore and rework generated README / code comments.Is this just an elaborate scheme to increase in/out token churn or are we hitting some kind of LLM limitations I wonder?

drumih · Answer

there is a skill named "avoid ai writing" on github it won't make your text as good as human text, but it will help with the most visible red flags

How to make AI better at writing prose?

What is your goal? What are you trying to have it generate that is not more appropriate for you to write yourself?

I'm a fiction writer. The way you make AI better at writing prose is the same way you make a fiction writer better at writing prose...You edit it manually.That's it. There are no shortcuts to good prose, except perhaps paying a ghost writer.

Pompous and full of air really sums it up well. As such I usually have to completely ignore and rework generated README / code comments.Is this just an elaborate scheme to increase in/out token churn or are we hitting some kind of LLM limitations I wonder?

there is a skill named "avoid ai writing" on github it won't make your text as good as human text, but it will help with the most visible red flags

I'm a fiction writer. The way you make AI better at writing prose is the same way you make a fiction writer better at writing prose...
You edit it manually.
That's it. There are no shortcuts to good prose, except perhaps paying a ghost writer.

Pompous and full of air really sums it up well. As such I usually have to completely ignore and rework generated README / code comments.
Is this just an elaborate scheme to increase in/out token churn or are we hitting some kind of LLM limitations I wonder?