Do you have anything to improve remote (SSH?) development? Meaning: the frontend is GPU accelerated, and that is great, but if you are fetching pages from the server instead of caching the buffers and intelligently fetching the LSP (or whatever language backend is used) updates, we are bottlenecked by the SSH connection latency
No. Code will contain bugs, won't be self-contained (will depend on 3rd party libraries and frameworks), and often will not be complete as TODO features can't possibly be a spec
I'm lucky enough to have upper management not pressuring to use it this or that way, and I'm using mostly to assist with programming languages/frameworks I'm not familiar with. Also, test cases (these sometimes comes wrong and I need to review thoroughly), updating documentation, my rubber duck, and some other repetitive/time consuming tasks.
Sometimes, if I have a simple, self-contained bug scenario where extensive debug won't be required, I ask it to find the reason. I have a high rate of success here.
However, it will not help you with avoiding anti-patterns. If you introduce one, it will indulge instead of pointing the problem out.
I did give it a shot on full vibe-coding a library into production code, and the experience was successful; I'm using the library - https://youtu.be/wRpRFM6dpuc
Rust's widely used serde library presents a large serialization overhead due to its visitor pattern, that is inefficient when compared to serialization implementations that simply follows the static declarations.