Even if true, this kind of response is unhelpful and fosters dismissal of your point. This kind of attitude more broadly paints AI advocates as cultists because they refuse to engage beyond "you're doing it wrong".

How about give pointers on "doing it right?"

My comment is dismissive because the parent comment is also dismissive. But you are right, advice is helpful. It's in my comment, but it may not be obvious to everybody, so here it is:

Work on your project management, communication, and mentorship skills. The AI tools are much more like a team of sloppy but capable junior engineers and not a reliably consistent fabrication machine. Change your perception that one simple prompt is going to magically solve a hard problem the first time. Learn to break projects down, organize them into sub-projects, and implement them in steps. Learn to communicate more clearly, define your requirements more rigorously, and adapt around your "team's" strengths and weaknesses.

We want these things to be rigorous and flawless but reality is messy just like working with a regular team of engineers. They are good at some things, terrible at others, constantly changing, and unreliable. But we've historically built tons of reliable software on unreliable actors by focusing on process, collaboration, and communication.

AKA, not just the hard technical skills, but the soft skills that allow unreliable software teams to thrive. They don't know what they don't know and it's your job to manage that.

Exactly. I'm a huge FP fan. When someone doesn't like FP I don't lecture them on how they're holding it wrong. I usually assume that, unsurprisingly, the tool doesn't suit every problem or there may be a design issue in the tool they ran into

[dead]