Generative AI coding tools and agents do not work for me

No offense intended, but this is written by a guy who has the spare time to write the blog. I can only assume his problem space is pretty narrow. I'm not sure what his workflow is like, but personally I am interacting with so many different tools, in so many different environments, with so many unique problem sets, that being able to use AIs for error evaluation, and yes, for writing code, has indeed been a game changer. In my experience it doesn't replace people at all, but they sure are powerful tools. Can they write unsupervised code? No. Do you need to read the code they write? Yes, absolutely. Can the AIs produce bugs that take time to find? Yes.

But despite all that, the tools can find problems, get information, and propose solutions so much faster and across such a vast set of challenges that I simply cannot imagine going back to working without them.

This fellow should keep on working without AIs. All the more power to him. And he can ride that horse all the way into retirement, most likely. But it's like ignoring the rise of IDEs, or Google search, or AWS.

I do agree with these points in my situation. I don't actually care for speed or having generated snippets for unfamiliar domains. Coding for me has always be about learning. Whether I'm building out a new feature or solving a bug, programming is always a learning experience. The goal is to bring forth a solution that a computer can then perform, but in the process you learn about how and more importantly why you should solve a problem.

The concept of why can get nebulous in a corporate setting, but it's nevertheless fun to explore. At the end of the day, someone have a problem and you're the one getting the computer to solve it. The process of getting there is fun in a way that you learn about what irks someone else (or yourself).

Thinking about the problem and its solution can be augmented with computers (I'm not remembering Go Standard Library). But computers are simple machines with very complex abstractions built on top of them. The thrill is in thinking in terms of two worlds, the real one where the problem occurs and the computing one where the solution will come forth. The analogy may be more understandable to someone who've learned two or more languages and think about the nuances between using them to depict the same reality.

Same as the TFA, I'm spending most of my time manipulating a mental model of the solution. When I get to code is just a translation. But the mental model is difuse, so getting it written gives it a firmer existence. LLMs generation is mostly disrupting the process. The only way they help really is a more pliable form of Stack Overflow, but I've only used Stack Overflow as human-authored annotations of the official docs.

My experience is that the "fancy autocomplete" is a focus destroyer.

I know what function I want to write, start writing it, and then bam! The screen fills with ghost text that may partly be what I want but probably not quit.

Focus shifts from writing to code review. I wrest my attention back to the task at hand, type some more, and bam! New ghost text to distract me.

Ever had the misfortune of having a conversation with a sentence-finisher? Feels like that.

Perhaps I need to bind to a hot key instead of using the default always-on setting.

---

I suspect people using the agentic approaches skip this entirely and therefore have a more pleasant experience overall.

The conversations will climb the ladder and narrow.

Eventually: well, but, the AI coding agent isn't better than a top 10%/5%/1% software developer.

And it'll be that the coding agents can't do narrow X thing better than a top tier specialist at that thing.

The skeptics will forever move the goal posts.

To some degree, traditional coding and AI coding are not the same thing, so it's not surprising that some people are better at one than the other. The author is basically saying that he's much better at coding than AI coding.

But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher skill ceiling than many people realize. You might prefer manual coding, but you might just be bad at AI coding and you might prefer it if you improved at it.

With that said, I'm still very skeptical of letting the AI drive the majority of the software work, despite meeting people who swear it works. I personally am currently preferring "let the AI do most of the grunt work but get good at managing it and shepherding the high level software design".

It's a tiny bit like drawing vs photography and if you look through that lens it's obvious that many drawers might not like photography.