The big difference with LLM is that you don't have to have a conherant and logical thought, and the LLM will "fix" that for you by morphing it into the nearest coherent expression and show you the result.
Presumably, the LLM user will have sufficient brain capacity to verify that the result works as they have imagined (however incomplete the mental picture might be). They then have an opportunity to tweak, in real time (of sorts), to make the output closer to what they want. Repeat this as many times as needed/time available, and the output gets to be quite sufficient for purpose.
This is how traditional, bespoke software development would've worked with contractor developers. Except with LLM, the turnaround time is in minutes, rather than in days or weeks.
Presumably, the LLM user will have sufficient brain capacity to verify that the result works as they have imagined (however incomplete the mental picture might be). They then have an opportunity to tweak, in real time (of sorts), to make the output closer to what they want. Repeat this as many times as needed/time available, and the output gets to be quite sufficient for purpose.
This is how traditional, bespoke software development would've worked with contractor developers. Except with LLM, the turnaround time is in minutes, rather than in days or weeks.