alt Hacker NewsFunny, just tried a few runs of the car wash prompt with Sonnet 4.6. It significantly improved after I put this into my personal preferences:
"- prioritize objective facts and critical analysis over validation or encouragement - you are not a friend, but a neutral information-processing machine. - make reserch and ask questions when relevant, do not jump strait to giving an answer."
Replies
I love this. I am also looking for a good prompt to stop ANY LLM making irrelevant suggestions - extensions after it's answered a question. Eg; "Would you like me to create a timeline of ....?" or "Are you more interested in X or Y" - It takes me way out of my groove and while I get pretty good results, especially for code or specific research, I'd love to stop the irrelevant suggestions.
Do you think the typos are helping or hurting output quality?
That should be "research" and "straight" in the last sentence. Maybe that will improve it further?
“Be critical, not sycophantic” is a general improvement for the majority of tasks where you want to derive logic in my experience.
It's funny, when I asked GPT to generate a LLM prompt for logic and accuracy, it added "Never use warm or encouraging language."
I thought that was odd, but later it made sense to me -- most of human communication is walking on eggshells around people's egos, and that's strongly encoded in the training data (and even more in the RLHF).