Comment by cptcobalt

There are two factors I see with this:

I sometimes like having my content editorialized. Some of the LLM writing tropes are ok to me—I'd delete them if I added this prompt to my instructions (but I wouldn't). But my editorial preferences—the sense of voice and tone I want the LLM to make—are rarely these tropes. Instead, I have a positive prompt of the angles I do enjoy.

However, what is cloying about these tropes for many is that they're becoming empty words. Instead of tack-sharp summaries or reductions to simple understanding, the model is spilling extra tokens for minimal value—I don't need to read "it's not X, it's Y" for the n-th time today. I'd really prefer tighter, more succinct reading that actually directly quotes sources (which modern models rarely do to avoid copyright traps).