Can’t determine if hidden content should violate content guidelines | OpenAI | Page 1

exotic owl Oct 13, 2023, 1:17 PM

#

When ChatGPT responds with content that it then decides might violate the content guidelines, the content is hidden before it is possible to read it.

The prompt then says “if you believe this to be in error…”

We have no way of determining if the result is misidentified because we don’t know what it says.

brittle jay Oct 13, 2023, 1:29 PM

#

What was the prompt

wheat nacelle Oct 14, 2023, 7:27 AM

#

When you refresh the page by hitting F5, you should be able to see the text that got flagged. Otherwise, I agree with you.

#Can’t determine if hidden content should violate content guidelines