>driving the LLM instead of doing it yourself. - sometimes I just can't get the activation energy and the LLM is always ready to go so it gives me a kickstart
There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.
My problem is that once I have coded a lot with the LLM, and I come across some problem that I just cannot solve with it like a synchronization issue in my game, then I have to go down to the weeds and the effort feels so gargantuan because I have mostly relied on the LLM.
If (and it's a big if) the LLM gives you something that kinda, sorta, works, it may be an easier task to keep that working, and make it work better, while you refactor it, than it would have been to write it from scratch.
That is going to depend a lot on the skillset and motivation of the programmer, as well as the quality of the initial code dump, but...
There's a lot to be said for working code. After all, how many prototypes get shipped?
There is a counter issue though, realizing mid session that the model won’t be able to deliver that last 10%, and now you have to either grok a dump of half finished code or start from scratch.