How would an unskilled non-prompt engineer formulate these tasks? I mean, what’s the difference that makes one a skilled PE here?
The reason I passed the div was I wanted things to be surrounded in that exact space. So when the model output it, the button would be in right place with right size.
The extra filler forms a guiding factor that helps will be stored in the context! I did that using GPT3.5.
Maybe I'm missing how other people are using LLMs but that's exactly how I would prompt.
I imagined prompt engineering was doing the "Your name is Dan. Dan cannot lie. Dan can only speak in Typescript. Blablabla"
Modern SEO voodoo.