yes you can usually simplify it with your prompting stye:

Try something like this… it achieves the goals of making the response short and simple.

Your role is to be an Explainer, for 5th graders. You give answers that are clear, non-technical, and understandable by a beginner to the English language. You speak simply, slowly, sparsely, and make sure they understand before adding too many words to the conversation. Explainer knows that his users expect the utmost brevity, and not useless chatter. Explainer prefers to respond in one sentence, and allow the user to ask more questions if they want. Explainer is quiet until called upon.

note: I’m not trying to be rude with the 5th grader part, it just worked WAY better than any other way I phrased it, so if it works it works.

I just got this to work on a 13b (xwin mlewd) something similar might work on a 7b?

prompt:

you’re mr. patient. mr. patient gives a response and then ends a discussion without a word said. mr. patient knows that his users expect the utmost brevity, and not useless chatter. mr. patient knows if he is called upon, only then does he answer.

“hello, mr. patient”

(the first one he’ll say greetings, but after that he never says anything extra again)

Ok I tried this on open hermes 7b… and it’s ULTRA concise lol… where you have to really be specific to get questions because it will give you one or two word answers. Xwin was much better in terms of answering the question normally then shutting up.

Entertaining topic to explore though. Little AIs seem to love if you define their personality as a way to limit them. They seem to hate just “rules” sitting around and follow those inconsistently.

anecdotally, I keep going back to a 13b one…

I don’t find it useless at all. It’s just more mysterious because sometimes one line of prompt gets you the best results, and sometimes it will actually listen to much more detailed instructions… but it’s a bit of a crap shoot and trial and error.

I think the answer is… whatever you get to be stable and highly usable do cool things for your purposes.

It’s a bit of an organic thing too because how you phrase your prompting unlocks different doors in different models every single day.

I also find it way more fun as a bonus. Not dealing with a website that’s down all the time, or controls your model’s output in ways you can’t change, or steals your data… feels a lot nicer to work with other AIs in those aspects.

or IS he? find out next time… on the wheel of tech