It has basically eliminated surprises like that.

Hasn't happened in a long time. Opus 4.6 is a miracle improvement.

It has examples of all the parts of a web app written, over many years, to be my own ideal structure. When the LLM era arrived, I added a ton of comments explaining what, why and how.

It turns out to serves as a sort of seed crystal for decent code. Though, if I do not remind it to mimic that architecture, it sometimes doesn't and that's very weird.

Still, that's a tip I suggest. Give it examples of good code that are commented to explain why its good.

I suppose if you are doing something that truly can be decided based on a test but, I just don't see it, at least for anything I do.

You have to figure out what you want before the AI codes. The thinking BEFORE is the entire game.

Though I will also say that I use Claude for working out designs a lot. Literally hours sometimes with long periods of me thinking it through.

And I still get a ton more done and often use tech that I would never have approached before these glory days.

I do a ton of programming but I also use it to learn all kinds of stuff. I'm into physics, history and philosophy and have done wonderful explorations.

Now I tell it what I had for breakfast just to see what it says. Half the time it says something interesting and I end up exploring another new thing.

"My people" for sure and everyone is mad at me because I think that.

Also, I don't care what they think. I am all about the fun.

Having an infinitely patient, super smart colleague available all the time is amazing.

I use NodeJS with a highly structured ExpressJS app for the API. It uses an npm module, tools-library-dot-d to implement a carefully scooped plugin structure for endpoints, data model and data mapping. It has built-in authentication and database (sqlite).

Nuxt/Vue/Vuetify/Pinia for the UI. It has a few components that implement things (like navigation) the way I like. It supports login and user editing.

The stack includes a utility that looks at a directory for executable CLI tools (usually NodeJS or BASH) and adds them to the session PATH. The API stack has boilerplate to treat CLI apps as data-model services.

Does that help?

I'm having more fun than I've had in years.

Your description of the experience tells me that you have not figured out how to do it correctly.

I NEVER have bad experiences like that. I absolutely DO create production grade software reliably every day.

Treat it as collaborator instead of as a servant. You will get much better results.

You don't have any choice. Good or bad. It's here. Get over it.

I know that back in the day, people said automobiles were bad and evil and costing the buggywhip makers their jobs. Unfortunately for them, the decision to use cars had already been made.

I do AI with fervor because I live in the real world and the decision has already been made. You can't stop AI by pretending it's optional.

Adapt or die.

The people who are pained by AI subsuming something they do forget that it empowers them to do a million other things.

But, let me suggest that you stop thinking about planning and design as "prompts". I work with it to figure out what I want to do and have it write a spec.md. Then I work with it to figure out the implementation strategy and have it write implementation.md. Then I tell it I am going to give those docs to a new instance and ask it to write all the context it will need with instructions about the files and have it write handoff.md.

By giving up on the paradigm of prompts, I turned my focus to the application and that has been very productive for me.

Good luck.

I am retired and am nearly equaling my salary with side jobs and only working a few hours a day. I don't see any reason you can't do that so stop whining and start learning.

You can rest assured that not all of us have lost our flexibility and ability to find joy. I love AI tech and am doing great work with it.