A lot of the complaints about these tools seems to revolve around their current lack of ability to innovate for greenfield or overly complex tasks. I would agree with this assessment in their current state, but this sentiment of "I will only use AI coding tools when they can do 100% of my job" seems short-sighted.

The fact of the matter, in my experience, is that most of the day to day software tasks done by an individual developer are not greenfield, complex tasks. They're boring data-slinging or protocol wrangling. This sort of thing has been done a thousand times by developers everywhere, and frankly there's really no need to do the vast majority of this work again when the AIs have all been trained on this very data.

I have had great success using AIs as vast collections of lego blocks. I don't "vibe code", I "lego code", telling the AI the general shape and letting it assemble the pieces. Does it build garbage sometimes? Sure, but who doesn't from time to time? I'm experienced enough notice the garbage smell and take corrective action or toss it and try again. Could there be strange crevices in a lego-coded application that the AI doesn't quite have a piece for? Absolutely! Write that bit yourself and then get on with your day.

If the only thing you use these tools for is doing simple grunt-work tasks, they're still useful, and dismissing them is, in my opinion, a mistake.

The vast majority of engineers aren't refusing to use AI until it can do 100% of their job. They are just sick of being told it already can, when their direct experience contradicts that claim.