[ravenstine]

> 1. It is my belief that if you are proficient enough in the task at hand, it is actually a distraction to be checking "someone else code" over just writing it yourself. When I wrote the code, I know it by heart and I know what it does (or is supposed to do). At least for me, having to be creating prompts and then reviewing the code that generates is slower and takes me out of the flow. It is also more exhausting than just writing the thing myself.

I'm sure there were programmers who said the same thing in regards to high-level programming languages.

> 2. I am only able to check the correctness of the code, if am am proficient enough as a programmer (and possibly in the language as well). To become proficient I need to write a lot of code, but the more I use LLMs, the less repetitions I get in. So in a way it feels like LLMs are going to make you a "worse" programmer by doing the work for you.

Maybe that becomes irrelevant the more that the skill of the programmer shifts from handwriting "correct" code to supervising code generators while proofreading their work, and of course providing effective acceptance criteria. There's also a massive bias towards failed predictions of the past that serves to discredit predictions that may see a greater degree of manifestation. For every time someone says "but people predicted this before and it didn't pan out", I can point to technology that did fundamentally change how an industry works and even make jobs obsolete.

Seems to me a lot of programmers on HN are refusing to believe that their ability to be proficient with code may be either outdated or supplanted by the efficiency of a system that writes code that is not necessarily "elegant" in human terms.

> So in a way it feels like LLMs are going to make you a "worse" programmer by doing the work for you.

Most programmers aren't great at what they do to start with, whereas LLMs can only get better from here on.