> Yeah they will work, but they will also be unnecessary. You will also bake all sorts of logic into your application that will be solved natively on the stronger model.
I think that a whole lot of what I do in prompt engineering is what's necessary to fully specify the output that I want.
A newer model may be less finicky, so I have a higher chance of getting it to work on the first try (and it's more reliable afterwards), but it's hard for me to imagine it needing a whole lot less prompt.
I think that a whole lot of what I do in prompt engineering is what's necessary to fully specify the output that I want.
A newer model may be less finicky, so I have a higher chance of getting it to work on the first try (and it's more reliable afterwards), but it's hard for me to imagine it needing a whole lot less prompt.