Anecdotally, asking LLMs to rewrite what they just said to make it sound less like AI. actually works on the posted AI detectors. Is this a general effect? Is it true that that LMS understand how to make something sound human, but it's just not their first "instinct"?
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{holtzman-does-make-this-2025,
author = {Holtzman, Ari},
title = {Does 'make this sound less like AI' work?},
year = {2025},
url = {https://hypogenic.ai/ideahub/idea/KED86w5dTkJEkUxg6kX6}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!