Nice! I used to do this by starting a session with a random question or string to introduce some noise, but it stopped working as models became more capable.
I'm curious how you extract decisions from the prompt in your tool, is it another model breaking it down?
Or someone could have 50 grams of creativity and explain what they want the name to evoke. So your system throws in sufficient randomness so that even the laziest of prompts have output diversity.
Realistically, a lot of coffee shop owners couldn't manage that in the first place without AI. The number of real coffee shops that have some variation on "Common Ground" is fairly significant. In the US, there's so many that it's hard to tell if it's just the first mover per state to register the name.
[–] Benjaminsen 4 days ago
[–] ricardobeat 4 days ago
I'm curious how you extract decisions from the prompt in your tool, is it another model breaking it down?
[–] aktenlage 4 days ago
[–] genxy 4 days ago
Or someone could have 50 grams of creativity and explain what they want the name to evoke. So your system throws in sufficient randomness so that even the laziest of prompts have output diversity.
[–] 3RTB297 4 days ago
[–] fennecfoxy 4 days ago
>output diversity
I think you're looking in the wrong place there, in the grand scheme of things.