Complex SQL requires knowledge about relational algebra (Cartesian products, set theory, domain relational calculus yada yada) and understanding of how RDBMS and their query planners work. At least, if performance is important to you.

I don't see this in this prompt engineering. In my limited experience (I played a few hours with Stable Diffusion and more hours with the OAI davinci-003 model), you can get good at it within a few days.

I spent a few hours learning SQL. I can get “good” at writing SQL queries within a few days. Do you want to hire me as someone who’s primary role is to write SQL queries?

I commend you for this stunning display of the Dunning-Kruger effect.

I don’t think that’s Dunning-Kruger but I get what you’re saying.

Not? "After a few hours of playing with it I give the opinion that it can't be that hard" is kinda the essence of basically not having a clue but feeling competent to express such a judgement nevertheless.

Fair enough. I think at the time I felt that just one data point wasn't enough to evoke the effect. Maybe I'm just biased against the effect since it was dis-proven: https://economicsfromthetopdown.com/2022/04/08/the-dunning-k...

At this point, we're very much at an exploratory stage of LLM queries - you could of course be a ML/DL researcher or engineer that's intimately knowledgeable with the current architectures, but still - they're very large and very complex due to the sheer parameter size, so you'd still have to map out what inputs will predictably give what outputs on a finished model.

I'd imagine that being a "prompt engineer" entails finding out and mapping the structures that gives you the desired result. Think of it as a novice user of search engines VS expert user of search engines.