I use ChatGPT as a copy editor, and I am constantly bouncing ideas off it. If only I had some available alpha readers. lol
This afternoon, I had it review passages, especially since I recently consolidated characters. Because of this, ChatGPT felt that I should elevate the Detective Sergeant from a secondary B-level character to a B+ character. Therefore, I should flesh her out more to make her more memorable. And I should expose the reader to more of her internal dialogue.
I took this advice to heart and reviewed the sections I had shared. I tend to indicate internal dialogue in italics, and there was plenty of italics. Of course, ChatGPT doesn’t have access to this markup, so I manually wrapped curly braces around {internal dialogue}, thusly.
I copy-pasted the section back into ChatGPT and asked for an analysis. This time, it was all praise.
This is something worth keeping in mind. You might have to do some extra throwaway markup for your AI editor to keep it honest.
Pro Tip: Another thing I do, is I place my [author comments] in square brackets and instruct the AI to ignore these in the analysis. I use author comments as placeholders for my own exposition, notes for later clarification, and so forth. With the brackets, I can just tell ChatGPT or Claude something like:
Analyse and evaluate this section. Inner dialogue is in curly braces, { }. Ignore content is square brackets, [ ]. This seems to work for me. YMMV
Ridley Park 