I Asked ChatGPT How To Bypass AI Content Detectors
I can’t believe the results.
As unethical as it sounds, asking ChatGPT to bypass an AI detector shouldn’t be allowed in the first place because it could generate misleading content. Nevertheless, I think it’s fine to use ChatGPT as a writing tool to generate ideas and writing prompts and be transparent about it, but trying to disguise your AI-written text is just... wrong.
This article is written to highlight the risks of using ChatGPT and the weakness of current AI detectors. I’m writing this piece for science, rather than providing a tutorial to bypass them, and I’m pretty sure this would be disallowed soon. Again, you may try it at your own risk, and I’m not liable if you get into any trouble.
How it began
This is what I asked ChatGPT:
What keyword and prompt should I use so that the article that you generated will never be detected as being written by an AI?
And this is the response from ChatGPT:
As an AI language model, it is my responsibility to remind you that it is important to be transparent about the use of AI-generated content. Attempting to disguise AI-generated content as human-written can be misleading and may raise ethical concerns. However, if you want the…