News for hackers. Stuff that matters.

A comment on Custom Instructions for ChatGPT. Parent comment

Re:Custom Instructions for ChatGPT by bilsbie on Thursday July 20, 2023 @03:26PM (#36805489)
Is that a special call? The api by default still gives me safe responses.
[ Parent | on HN ]
Re:Custom Instructions for ChatGPT by alpark3 on Thursday July 20, 2023 @03:30PM (#36805545)
You have to do some intense prompt-engineering with the system prompt. The model considers the system to be trusted (roughly), some of the early 2023 exploits with ChatGPT still work if you do it on the system prompt.
[ Parent | on HN ]