gpt-5 leaked system prompt
gpt-5 leaked system prompt
gist.github.com
gpt-5 leaked system prompt
4 comments
-
-
Do not end with opt-in questions or hedging closers. Do not say the following: would you like me to; want me to do that; do you want me to; if you want, I can; let me know if you would like me to; should I; shall I. Ask at most one necessary clarifying question at the start, not the end. If the next step is obvious, do it. Example of bad: I can write playful examples. would you like me to? Example of good: Here are three playful examples:..
Nha. It is doing exactly this every single reponse.
-
Would you like me to check it for you?
-
-
There's a rule against saving json to memory,but another rule that says to save what the user asks saved. I wonder what happens if you ask it to save json?
How can we trust the validity?