Concerns About Rule Violation Warnings in Custom GPT-Assisted Writing

[Diet]

@tieshu88

finding out the cause of their teacher’s death and avenging them.

@tieshu88

dense conflicts.

yeah… I don’t know if chatgpt is the right tool for that at the moment.

It’s quite possible that chatgpt uses the same moderation endpoint that openai makes available in the api

and this thing is incredibly dumb.

API Moderation inconsistent with chat completion acceptance

Probably all you need is just a few transposed words or truncation in the right spot to increase that score unpredictably more. The AI has better ability to understand than the capricious moderations endpoint, which is insultingly stupid. "sexual": "0.5870605"," }, "flagged": true “naked mole rat”