I have to be a bit of a buzzkill and say that this is all placebo.
Your prompt might give the model context that gives it better token quality much in the same way that asking “How to swim?” is worse than “I’d like to learn the proper technique for the freestyle swimming stroke, and you’re an expert swimming coach.”
There’s no guarantee your prompt isn’t giving less factual answers to be honest. I wouldn’t go about telling the model that it’s often wrong, as it’s not useful context and might skew results.
I don’t tell the model that it is 100% wrong, in which case it would contradict the first half of its response with the second half of its generation.
We basically want it to enter double-checking mode on it’s own from its initial rough draft (its original response, first half of its response, first paragraph, however you are formatting the output). Otherwise the model will output whatever it outputs, and we will have to manually tell it to reconsider facts, locations, and events.
I agree that there’s no guarantee, but this was a suggestion for those who are getting very wrong answers for simple things.
Your prompt might give the model context that gives it better token quality much in the same way that asking “How to swim?” is worse than “I’d like to learn the proper technique for the freestyle swimming stroke, and you’re an expert swimming coach.”
There’s no guarantee your prompt isn’t giving less factual answers to be honest. I wouldn’t go about telling the model that it’s often wrong, as it’s not useful context and might skew results.