A guidance language for controlling LLMs

Re:A guidance language for controlling LLMs by pxtail on Tuesday May 16, 2023 @06:54PM (#35968847)

I'm not interested in pleasant, formal "conversation" with the thing roleplaying as human and wasting, time, keystrokes and money, I want data as fast and condensed as possible without dumb fluff. Yes, it's funny for few first times but not much after that

[ Parent | on HN ]

Re:A guidance language for controlling LLMs by Nevermark on Tuesday May 16, 2023 @07:47PM (#35969363)

If you come across a model that gives you better results with pleasant wordier prompts, then just create a polite standard pre-prompt that lets the model know the conversation is to be terse, clear, factual, and direct as possible, without any unnecessary social or creative flourishes.

I mean, whatever gets the best results is what gets the best results, right? It's not a question of "funny" or "fluff".

[ Parent | on HN ]