Your last sentence describes my thoughts exactly. I try to incorporate Claude into my workflow, just to see what it can do, and the best I’ve ended up with is - if I had written it completely by myself from the start, I would have finished the project in the same amount of time but I’d understand the details far better.

Even just some AI-assisted development in the trickier parts of my code bases completely robs me of understanding. And those are the parts that need my understanding the most!

> It's strange to me when articles like this describe the 'pain of writing code'.

I find it strange to compare the comment sections for AI articles with those about vim/emacs etc.

In the vim/emacs comments, people always state that typing in code hardly takes any time, and thinking hard is where they spend their time, so it's not worth learning to type fast. Then in the AI comments, they say that with AI writing the code, they are free'd up to spend more time thinking and less time coding. If writing the code was the easy part in the first place, and wasn't even worth learning to type faster, then how much value can AI be adding?

Now, these might be disjoint sets of people, but I suspect (with no evidence of course) there's a fairly large overlap between them.

Have you really never found writing code painful?

CI is failing. It passed yesterday. Is there a flaky API being called somewhere? Did a recent commit introduce a breaking change? Maybe one of my third-party dependencies shipped a breaking change?

I was going to work on new code, but now I have to spend between 5 minutes and an hour+ - impossible to predict - solving this new frustration that just cropped up.

I love building things and solving new problems. I'd rather not have that time stolen from me by tedious issues like this... especially now I can outsource the CI debugging to an agent.

These days if something flakes out in CI I point Claude Code at it and 90% of the time I have the solution a couple of minutes later.

Your comment is spot on, but the nuance people who are still new to these LLMs don't yet see is the real reason "he'd be better off just writing the damned book instead."

1. That prompt is always a slot machine. It's never 100% deterministic and that's why we haven't seen an explosion of claude skills. When it works for you, and it's magical, everyone is wowed. However, there is a set of users who then bang their head, wondering why their identical attempt is garbage compared to their coworker. "It must be a skills issue." No, it's just the LLM being an LLM.

2. Coding agents are hyper localized and refuse to consider the larger project when it solves something. So you end up with these "paper cuts" of duplicated functions or classes that do one thing different. Now the LLM in future runs has to decide which of these classes or functions to use and you end up with two competing implementations. Future you will bang your head trying to figure out how to combine them.

3. The "voice" of the code it outputs is trained on public repositories so if your internal codebase is doing something unique, the LLM will consistently pick the voice it's trained on, forcing you to rewrite behind it to match your internal code.

4. It has no chill. If I set any "important" rules in the prompt then it sometimes adheres to it at the expense of doing the "right" thing in its changes. Or it completely ignores it and does its own thing, when it would have been the perfect time to follow the rule. This is to your point that, if I had just written the code myself, it would have been less words than any "perfect" prompt it would have taken to get the same code change.

I was talking to a coworker that really likes AI tooling and it came up that they feel stronger reading unfamiliar code than writing code.

I wonder how much it comes down to that divide. I also wonder how true that is, or if they’re just more trusting that the function does what its name implies the way they think it should.

I suspect you, like me, feel more comfortable with code we’ve written than having to review totally foreign code. The rate limit is in the high level design, not in how fast I can throw code at a file.

It might be a difference in cognition, or maybe we just have a greater need to know precisely how something works instead of accepting a hand wavey “it appears to work, which is good enough”.

People are different. Some are painters and some are sculptors. Andy Warhol was a master draftsman but he didn't get famous off of his drawings. He got famous off of screen printing other people's art that he often didn't own. He just pioneered the technique and because it was new, people got excited, and today he's widely considered to be a generational artistic genius.

I tend to believe that, in all things, the quality of the output and how it is received is what matters and not the process that leads to producing the output.

If you use an LLM assisted workflow to write something that a lot of people love, then you have created art and you are a great artist. It's probable that if Tolkien was born in our time instead of his, he'd be using modern tools while still creating great art, because his creative mind and his work ethic are the most important factors in the creative process.

I'm not of the opinion that any LLM will ever provide quality that comes close to a master work by itself, but I do think they will be valuable tools for a lot of creative people in the grueling and unrewarding "just make it exist first" stage of the creative process, while genius will still shine as it always has in the "you can make it good later" stage.

Current models won't write anything new, they are "just" great at matching, qualifying, and copying patterns. They bring a lot of value right now, but there is no creativity.

Tolkien's book is an art, programs are supposed to do something.

Now, some program may be considered art (e.g. codegolf) or considered art by their creator. I consider my programs and code are only the means to get the computer to do what it wants, and there are also easy way to ensure that they do what we want.

> Frodo and Sam having an argument over the trustworthiness of Gollum. Frodo should be defending Gollum and Sam should be on his side.'

Is exactly what programs are. Not the minutiae of the language within.

Writing he code should be the easy part and one of the smaller time sinks actually. The fruits of the labour is in the planning, the design, the architecture and the requirements that you want to achieve now and potentially in the future.. these all require a serious amount of effort and foresight to plan out.

When you're ready, maybe you've done some POC in areas you were unsure, maybe some good skeletons work to see a happy path draw a shadow of s solution, iterate over your plans and then put some real "code"/foundation in place.

It's a beautiful process. Starting out I used to just jump into s project deep with the code first and hit that workaround button one too many times and it's far more expensive, we all know that.

I don't find writing code painful, but I do find it tedious. The amount of time wasted on boilerplate keeps me from getting to the good stuff. LLMs let me speed run through all of that.

To take it back to your example, let's imagine Tolkien is spending a ton of time on setting up his typewriter, making sure he had his correction tape handy, verifying his spelling and correcting mistakes, ensuring his tab stops were setup to his writing standard, checking for punctuation marks, etc. Now imagine eliminating all that crap so he can focus on the artistic nature of the dialogue.

I agree with your point. My concern is more about the tedious aspects. You could argue that tedium is part of what makes the craft valuable, and there's truth to that. But it comes down to trade-offs, what could I accomplish with that saved time, and would I get more value from those other pursuits?

Isn't that what Tolkien did in his head? Write something, learn what he liked/didn't like then revise the words? Rinse/repeat. Same process here.

“ What’s gone is the tearing, exhausting manual labour of typing every single line of code.”

Yeah, this was always the easy part.

I didn't fully realize how much pain there was until I started delegating the coding to AI. It's very freeing. Unfortunately I think this will soon lead to mass layoffs.

Pain can mean tedium rather than intellectual challenge.

Sometimes you are not writing Lord of the Rings.

Sometimes you are writing a marketing copy for a new Nissan that's basically the same as last year Nissan, yet you need to sell it somehow. Nobody will REALLY read it more than 2 seconds and your words will be immediately forgotten. Maybe some AI is good then.

Claude Opus 4.6:

“He’s a liar and a sneak, Mr. Frodo, and I’ll say it plain — he’d slit our throats in our sleep if he thought he could get away with it,” Sam spat, glaring at the hunched figure scrabbling over the stones ahead. “Every word out of that foul mouth is poison dressed up as helpfulness, and I’m sick of pretending otherwise.” Frodo stopped walking and turned sharply, his eyes flashing with an intensity that made Sam take half a step back. “Enough, Sam. I won’t hear it again. I have decided. Sméagol is our guide and he is under my protection — that is the end of it.” Sam’s face reddened. “Protection! You’re protecting the very thing that wants to destroy you! He doesn’t care about you, Mr. Frodo. You’re nothing to him but the hand that carries what he wants!” But Frodo’s expression had hardened into something almost unrecognizable, a cold certainty that brooked no argument. “You don’t understand what this Ring does to a soul, Sam. You can’t understand it. I feel it every moment of every day, and if I say there is still something worth saving in that creature, then you will trust my judgment or you will walk behind me in silence. Those are your choices.” Sam opened his mouth, then closed it, stung as if he’d been struck. He fell back a pace, blinking hard, and said nothing more — though the look he fixed on Gollum’s retreating back was one of pure, undisguised loathing.

Please forgive me for being blunt, I want to emphasize how much this strikes me.

Your post feels like the last generation lamenting the new generation. Why can't we just use radios and slide rules?

If you've ever enjoyed the sci-fi genre, do you think the people in those stories are writing C and JavaScript?

There's so much plumbing and refactoring bullshit in writing code. I've written years of five nines high SLA code that moves billions of dollars daily. I've had my excitement setting up dev tools and configuring vim a million ways. I want starships now.

I want to see the future unfold during my career, not just have it be incrementalism until I retire.

I want robots walking around in my house, doing my chores. I want a holodeck. I want to be able to make art and music and movies and games. I will not be content with twenty more years of cellphone upgrades.

God, just the thought of another ten years of the same is killing me. It's so fucking mundane.

The future is exciting.

Bring it.