lol have you actually tried to build anything useful e2e? Leaving the AI to itself gives horrendous results.
Some even for large clients, and they work well in production, clients are happy, yet I feel no connection to the work. If the client says something, I just copy-paste it to the AI and it fixes it/implements it.
There is too much code and complexity to check if the changes are ok, apart from seeing it if it seems visually ok and if the problem is fixed live. It almost always works, but it definitely doesn't have the same feeling as thinking of the problem, finding a solution, and implementing it, part which most developers enjoy in their work.
To me, the challenge in software is to reduce this complexity to keep it manageable. Probably AI can manage more complexity than a human being, but it seems to be difficult to prevent or reduce that complexity in the first place. How is your experience once the complexity is too hard for a frontier LLM to handle, or for you to prompt the correct direction towards it?
Tell it stuff like "use caching", "use library X", "make sure that it works when offline", etc.
And then basically live test it and see if it works as expected, and tell it more improvements/changes to make.
Almost all my projects are continously updated almost daily, based on my feedback and some automated systems (i.e. SEO feedback loops)