principles.fyi · the brain · concept

system prompt

Hidden instructions set before the chat that tell the model how to behave.

[system instructions] + [user message] -> response

A system prompt is a special block of instructions placed at the very start of the conversation, before the user's messages, that sets the model's persona, rules, and boundaries — like 'You are a helpful assistant; be concise; refuse harmful requests.' Mechanically it is just more conditioning text the decoder attends to, but it is given a privileged position and the model is trained (via instruction-tuning and RLHF) to weight it heavily. It is how an app developer steers the model's overall behavior separately from whatever the end user types.

Appears in

Nearby in the brain