Addressing the end of the article, I think that we are all very much still learning how to use AI responsibly. It's like we just discovered alcohol and we're going on a rager every night because we don't know any better yet.
It's too easy to buy €100 of Claude tokens and burn through them to make those dream projects appear as if by magic. There's a middle ground where, for example, instead of building a whole project it could produce a project template and provide guidance as you build. That should take the edge off the task paralysis and hopefully disrupt the addiction loop.
That's how I use LLMs for programming. I predominately use the chatbots instead of the CLI tools. Every so often, I'll ask for a one-shot of some MVP, but then I take that MVP and make all the changes myself. However, I must say that I rarely do the one-shot-and-edit style of development. I find that such a process can save time, but not always.
It's too easy to buy €100 of Claude tokens and burn through them to make those dream projects appear as if by magic. There's a middle ground where, for example, instead of building a whole project it could produce a project template and provide guidance as you build. That should take the edge off the task paralysis and hopefully disrupt the addiction loop.