I'm happy to have a discussion with you if you bring any argument.
Before GPT what would have been your choise of architecture, setup, alogorithm if someone comes to you and says "write a tool/system which can generate code" "what do you mean generate code? How do i control it?" "by writing what you want in natural language" "puh 50 years of development, 100 billion, top tier team of linguists and software engineers perhaps?"
Ask StackOverflow if they think it didn't change anything for them.
Programming is the reification of decision-making processes. If you don't understand the decision-making process that you want, you get a different one, which at best approximates the one you want but couldn't articulate.
If you do this with COBOL or Python, at least you get consistent operation and errors when you're wrong. If you do this with any LLM, consistency is dropped in favor of obsequiousness.
The base problem is that people aren't equipped naturally to think about all the details of their problems.
It’s mind-boggling that anyone could deny this in mid-2026. Virtually every software engineer I know is no longer writing the majority of their code. Many are not writing any code, myself included. And I’m a staff engineer with 20 yoe, formerly at big tech, and now building a (profitable) SaaS of my own. The way I work is wildly different from a year ago.
My experience is different. I hear a lot of developers, old and young, scaling back their LLM use now that the bills are coming in. And I don't just mean the financial bills, mostly it's about them realising that there's a lot lf shit they need to fix that the model can't handle, and they no longer understand it enough to either do it or properly prompt a model to.
The most prevalent trend I see around me today is that people are going back to using the LLMs as research, review, and sketching tools, but writing most actual code themselves again. And it's not just AI skeptics doing that, it's those who went all-in and are finally seeing the downsides and limitations of this technology, now that the hype is waning.
Before GPT what would have been your choise of architecture, setup, alogorithm if someone comes to you and says "write a tool/system which can generate code" "what do you mean generate code? How do i control it?" "by writing what you want in natural language" "puh 50 years of development, 100 billion, top tier team of linguists and software engineers perhaps?"
Ask StackOverflow if they think it didn't change anything for them.