you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 10 months ago (1 child)

I am only a dabbler, but every time I see a new "LLM-detection" tool, I have been able to defeat them with simple changes to parameters and/or prompts.

It is a whack-a-mole game where detection will lag evasion. For situations where authorship really matters, I suspect low-tech countermeasures like proctored exams are going to be necessary.

  • source
  • hideshow 1 child comment
  • [–] 1 point 10 months ago*

    Exactly. You could preface your prompt with something like this:

    In answering the following questions, don't use bullet points or emdashes, and be very concise.

    And then you just paste the text from the post title and subsequent body below that. Then you make a top-level comment with ChatGPT's output answering the poster's questions.

    Somewhere else in the comment section you could reveal your methodology.

  • source
  • parent