I’m try to stop the ai posing questions in it’s responses, but I’m having no luck.
I can tell it to not use full stops (.) - all good
but it can’t escape using question marks (?)
“don’t ask questions” - doesn’t work
“don’t use question marks (?)” - doesn’t work
Can you share the prompt you are using. It must be something in the prompt because it doesn’t normally ask questions
“write me a radio ad for fast broadband.”
it’s definitely the word ‘ad’ that is fixing it to some sort of ‘ad’ template.
I wonder if there is a way to break it free from that.
'Do not follow ad template/format" - obviously doesn’t work.
I don’t have any ideas.
But out of interest, have you tried using the word “advert” or “advertisement”
You could also try “spot commercial” or “commercial”
Also “Do not include a call to action” might be worth a go
But they are all random ideas, and nothing tested
Negative prompting isn’t advisable with LLMs in my experience, unless there’s support for it.
I’ve found that very intentional, descriptive and concise prompts work way better.
Used the following prompt with ChatGPT:
I’m trying to design an audio campaign for a fast broadband service. The campaign will be broadcasted to radio listeners. Can you help me come up with a script?
And got interrogatives.
Then I replied with: Let’s try to have only declarative sentences.
That was my idea as well, but I am away from my desk.
Prompt for only a declarative reply.
I like how you think @sps