I find it absolutely is much of the time - I'll determine the architecture/overall solution, know exactly what needs to go in a multitude of files, and now actualizing all that isn't really thinking anymore, just donkey work. Getting AI to do this has been incredible now that it's finally good enough. I've had Copilot make flawless 500+LOC C++ classes in the first pass, and when I introduced bugs by changing it by hand, it found them instantly from stack traces without even having symbols, saving me hours. I see a future where writing a large codebase all by hand is seen like raising a barn the Amish way with no powertools - impressive and maybe there's something to be said for it philosophically, but just not practical otherwise.
I find however, that while typing it all out, my mind often continues analyzing and thinking, and that I often find a new idea, or new structure, that might be even better. Typing it out and seeing it appear in front of me. It also gives me a feeling for how tedious, brittle, or annoying the solution is.
Granted, sometimes it's really not that interesting to type the stuff. It depends what one is working on.
Each time I write a routine it's different. Its better. I've learned something from last time. In fact, this is one of the things that got me hooked on computing. That there's so much complexity, often hidden, that there's always more to learn and improve upon.
And truth be told, if I'm writing the same thing many times it's time to create a library. Maybe just for myself or for the company I work for. But the same thing happens. I always learn more while doing it and it always gets better.
I fear the programmer whose bottleneck is typing. They already know the answer. But the problem is that there is none
If you use that much time for donkey work, you are using the wrong tools. If it is so simple so that can delegate it to a LLM, you need to use a language with more expressive power.
There's no such language, sans Lisp with extreme use of macros.
Here's an alternative take: if typing isn't a bottleneck for you, and you don't experience coding as being donkey work, you are thinking too slow, and/or in too small increments.
How often are you actually doing this though?
I think I probably work in something greenfield about once a decade. The hard part is always going down a rabbit hole in established code bases. I can do the boilerplate in a few days. It saves time, but not really even one hairy issue a year.
> The hard part is always going down a rabbit hole in established code bases.
Actually, I found that this is exactly where they shine (I wouldn't trust them with greenfield implementation myself). Exploring existing code is so much easier when you can ask them how something works. You can even ask them to find problems - you can't trust them to be correct, of course, but at least you get some good brainstorming going. And, incredibly, they often do find actual problems in the code. Pretty impressive for language models.
Nowadays? 4+ times a week. I want to learn as much as I can now that I essentially have 24/7 mentors that can remember everything I've told them.
Sure, I could write it all by hand; but even as a decent typer, I'll never match a tenth speed of claude code or opencode just GOING. Maybe there's a better way to learn, but whatever it is, it's not obvious to me.
I actually felt like I learned the most when I stopped going to Google and StackOverflow for solutions and instead moved to docs. It's far less direct but the information is much more rich. All that auxiliary information compounds. I want to skip it, feeling rushed to get an answer, but I've always been the better for taking the "scenic route". I'd then play around and learn how to push functions and abuse them. Boy there's no learning like learning how to abuse code.
Fwiw, I do use LLMs, but they don't write code for me. They are fantastic rubber ducky machines. Far better than my cat, which is better than an actual rubber duck. They aid in docs too, helping fill in that space when you don't exactly understand them. But don't let them do the hard work nor the boring work. The boring work is where you usually learn the most. It's also the time you don't recognize that's happening
Close to 5 years. I read docs too and love the immersion and the fully grasping of concepts when going with your route, but most days there's just not enough hours for this.
> The boring work is where you usually learn the most. It's also the time you don't recognize that's happening
That was always how I did it before mid-2025. And I do still do boring work when I truly want to master something, but doing that too much just means (for me) not finishing anything.
5 years isn't that long. I've been doing 3X that and I'm constantly learning new things. Not even about new language features but even languages I've been using that whole time. New ways to problem solve. New algorithms. New tools.
Not finishing things can be okay but also not. An important skill to learn is what's good enough. And to write good enough to be easily upgradable. It's important to write code to be flexible for this reason. It's also important to realize it's okay to completely throw away code. But also this is the reason comments are so important. Don't just write what functions do but also write how you envision the design. Even if you can't get to it now. Then when you or anyone else comes back (after lunch, next week, next year, whenever) there's good hints about all that. Knowing how to get up to speed and be effective fast. If anything this helps agents even more. Commenting is a vastly under appreciated skill and only becoming more valuable
I find it absolutely is much of the time - I'll determine the architecture/overall solution, know exactly what needs to go in a multitude of files, and now actualizing all that isn't really thinking anymore, just donkey work. Getting AI to do this has been incredible now that it's finally good enough. I've had Copilot make flawless 500+LOC C++ classes in the first pass, and when I introduced bugs by changing it by hand, it found them instantly from stack traces without even having symbols, saving me hours. I see a future where writing a large codebase all by hand is seen like raising a barn the Amish way with no powertools - impressive and maybe there's something to be said for it philosophically, but just not practical otherwise.