I have been using the “rewrite” prompt to generate improved paragraphs with new wording and sentence structures. However, the new GPT-4o model seems to return text that is nearly identical to the input, with minimal changes or improvements. Even using a more detailed prompt doesn’t help.
This is a significant issue for anyone relying on GPT across various interfaces for rewriting tasks. Has anyone else experienced this problem or have any insights into what might be happening?