System prompts are more like suggestions than hard constraints.
s/system/all llm/
That's the joy and pain.
The Pirate Code.
i beg to differ, in an ideal world a system possibly is a binding law and high end models are starting to be really aligned to the exact system prompt. The instructions must be simple to follow, if you start doing complex rules it'll call apart, but I'll usually follow the stringer interpretation.
I don't understand why they don't look for large substring matches for the system prompt before returning the response. Trivial calculation compared to a system prompt instruction asking the model not to do it