It works well for me. I wouldn't have said that about 3 or 4 months ago but now it does work. How well it works seems to be highly project-dependant, my friends have much more trouble to get usable things out of LLMs.
The projects I work on are relatively small, two frontend with about 30k loc and a middleware with about 50k loc.
All project were started with no llms and were pretty clean.
I use Augment and Intent with Opus 4.6
The main challenge is to avoid over engineering. It's honestly pretty hard to rein it in and get simple code, most of the time I let it do its thing and then tell it to remove some section, simplify that etc.
So I still have to tell it how to do stuff, and not just what to do.
But overall it has surpassed what I thought it would be able to do, like calling external services by itself to get the shape of the data for example.
Another win was making a mermaid chart of the whole arborescence of the projects, with special annotations on a specific type of components. Something that would be highly repetitive and a bit frustrating was done quickly with a very short prompt.
Code refactoring is also much easier for some tasks, like separating a service into multiple services depending on a certain criteria, usually by domain. When it's easy to describe but the work requires a lot of edits, LLMs usually do better than I would do manually.
team size is 2, and I have been a frontend developer for about 12 years.