Hacker News new | ask | show | jobs
by benhoyt 1132 days ago
I've been reviewing answers to questionnaires we send out to potential software engineering candidates. Sometimes candidates seem to write 90% of the submission themselves, and then use ChatGPT for the last couple of questions (which are more general, like "Outline your thoughts on documentation in software projects"). I joked to a colleague that I'd come up with a fool-proof ChatGPT detector in one line of Python:

  is_chatgpt = paragraphs[-1].startswith(('In conclusion', 'Finally'))
1 comments

Don't forget "Overall, "
Indeed! I just saw this in a submission I was reviewing now. AI writing is well-structured but extremely boring and generic.