When asking for change, there are the choices you know about and the ones you don't. I've gotten in the habit of describing some of the current state as well as my desired state, and using that to focus the LLM on the areas I'd like to have a stronger voice in.
Of course, I definitely appreciate when it makes choices that I don't know I need to make, and it chooses reasonable defaults.
I mean, I could say "make the visualization three columns", but there's a lot of ambiguity in that kind of thing, and the LLM is going to make a lot of choices about my intent.
Instead, "each team/quarter currently has a vertically stacked list of people assigned to that team, with two columns (staying on team, leaving team). change that to being three columns (entering team, staying on team, leaving team)."
As a bonus, it's much, much clearer to somebody reading the history later what the intent was.
Of course, I definitely appreciate when it makes choices that I don't know I need to make, and it chooses reasonable defaults.
I mean, I could say "make the visualization three columns", but there's a lot of ambiguity in that kind of thing, and the LLM is going to make a lot of choices about my intent.
Instead, "each team/quarter currently has a vertically stacked list of people assigned to that team, with two columns (staying on team, leaving team). change that to being three columns (entering team, staying on team, leaving team)."
As a bonus, it's much, much clearer to somebody reading the history later what the intent was.