I've found the biggest bottleneck is bugs. If you catch a bug during development, it takes the least time to fix.

Catch a bug during PR, you need to fix the code, and the PR needs to happen again.

Catch a bug in QA, and you need to fix the code, do another PR, and get it tested again.

This pattern goes right through UAT, and god help you when a bug makes it to Prod.

There is nothing more time consuming than code that was written quickly.

What's in this article is true, but to be honest I've never seen anyone using lines of code as an optimization metric. Even among the most AI enthusiastic people. I mean: the author of the article seem to be fighting non-existing problem.

This is why my personal use of AI has been focused pretty cleanly on "doing what I already do, more thoroughly" - By not turning it into a "ship more code more faster" machine, it's a "can explore my code and answer questions and help design things more thoroughly" machine.

I tend to go with "AI-augmented" development because I'm shipping the same things I've been shipping - Just with a way to quickly brainstorm and compare ideas on something my team members may not have time for. I can propose my ideas and have some LLM tell me what the downsides of my approach would be - or what I should guard against.

It's crazy to me that folks are treating them like sources of truth when they should just be an untrustworthy second opinion that is faster than you. I think of it as an intern with speed but questionable taste lol.

My problem is that as I grow older and older, I find it harder and harder to be arsed to write any code. LLM fixes that problem beautifully. I have 20+ years experience so it kinda works. If you don't have it might not, at the current moment.

That's part why I don't use VIM for software development, even though I love the motions.

It's a perfect solution... for the wrong problem.

(Other reasons are:

• I like the features that help me handle the code and catch mistakes before running it

-I paid for the entire RAM and I'm going to use the entire RAM )