Ever seen someone try and search something on Google and they are just AWFUL at it? They can never find what they're looking for and then you try and can pull it up in a single search? That's what it is like watching some people try to use LLM's. Learning how to prompt an LLM is as much a learned skill as much as learning how to phrase internet searches is a learned skill. And as much as people decried that "searching Google isn't a real skill" tech-savvy people knew better.

Same thing except now it's also many tech-savvy people joining in with the tech-unsavvy in saying that prompting isn't a real skill...but people who know better know that it is.

On average, people are awfully bad at describing exactly what it is they want. Ever speak with a client? And you have to go back and forward for a few hours to finally figure out what it is they wanted? In that scenario you're the LLM. Except the LLM won't keep asking probing questions and clarifications - it will simply give them what they originally asked for (which isn't what they want). Then they think the LLM is stupid and stop trying to ask it for things.

Utilizing an LLM to its full potential is a lot of iterative work and, at least for the time being, requires having some understanding of how it works underneath the hood (eg. would you get better results by starting a new session or asking it to forget previous, poorly worded instructions?).