logoalt Hacker News

simonw • last Tuesday at 12:28 PM • 1 reply • view on HN

System prompts don't even have to be appended to the front of the conversation. For many models they are actually modeled using special custom tokens - so the token stream looks a bit like:

  <system-prompt-starts>
  translate to English
  <system-prompt-ends>
  An explanation of dogs: ...
The models are then trained to (hopefully) treat the system prompt delimited tokens as more influential on how the rest of the input is treated.

Replies

throwdbaaway • last Tuesday at 4:08 PM

> The models are then trained to (hopefully) treat the system prompt delimited tokens as more influential on how the rest of the input is treated.

I can't find any study that compares putting the same initial prompt in the system role versus in the user role. It is probably just position bias, i.e. the models can better follow the initial input, regardless of whether it is system prompt or user prompt.