How to keep enjoying programming in a world of LLMs

Not so long ago I read something on HN which resonated with me: we’re moving into the era that is comparable to car mechanics enthusiasts. You have a previous generation of cars where people just enjoy working on with hand tools, and there’s modern cars where people like to tune with software patches.

From the very start of llms I’ve had nothing but bad experiences with code that was generated for me. Either it’s buggy, it works but I end up losing an evening on some obscure bug, or it’s full of red flags.

My latest hobby project is just in a text editor with markup and that’s it. I’m also done with the augmented assistance in the IDE. I google things I forgot. I constantly read these amazing stories of people vibe-coding some firmware/driver that just works, and honestly I’m starting to question whether I’m reading the posts of some promotional bot.

One thing to keep in mind is that anytime you punt to the LLM (or anybody) for anything, that skill is going to atrophy.

I've seen this happen to myself where suddenly I had trouble planning out the architecture for a very small project. It should have been obvious to me, and I knew that. So it was disconcerting to not be able to suddenly have the answer appear in front of me like it normally would. I thought maybe I would go to Claude and help get some ideas.

But then I stopped myself. I knew I should be able to do this! So I got out a piece of paper and I scribbled ideas until the dam burst and suddenly the entire design was obvious, like it should have been in the first place. It took about 5 minutes.

But those were an alarming 5 minutes. It was like I'd gone blind to the solution.

And I realized that when I asked Claude for a bunch of ideas and then I selected the best one based on my experience, I was exercising that exact skill. I wasn't exercising the skill of coming up with the solution from scratch.

Lots of times we're happy letting particular skills atrophy. Maybe we don't like exercising them and we just don't want to do that anymore. And I think that's valid.

Just be careful how you use it.

All pros and cons of LLM coding aside, something has really shifted for me with the latest agentic coding. I’ve found my motivation to work slowly slipping away. No matter what role I had I always found something to keep me engaged with the job. Now though there’s no motivation. Every week it feels like my skills, talents, even ideas themselves are less and less relevant. I’m just meat shuffling data and permissions between bots

My jobs made me hate programming long before LLMs. If anything I enjoy programming more now that I can tell the LLM to do the bullshit I don’t want to do, saving my energy for interesting problems…usually ones found outside of my 9-5.

I recently (2 days ago) noticed i enjoy it a lot more if i use a super fast model with low reasoning (gpt 6 luna low effort + fast mode). That way, i can still have hands on the entire time and dont have to wait around for 20minutes for it to finish up and have made a bunch of decisions without me.

Also, LLMs are first and foremost excellent at reading ultra fast. Makes it excellent for summarizing and re-representing modules of your code

I've avoided using LLMs. You might not have the option of doing this in paid employment, but you certainly can in your spare time, and if you don't you'll gradually lose the ability to think in a programming language. This applies similarly to any other cognitive skill too: writing music or playing a musical instrument, speaking and reading a foreign language, doing cryptic crosswords, playing chess or go, etc. You wouldn't stop playing chess just because computers are now much better at it. The point is learn, understand, and do those things yourself.

Here's my advice, based on what I have done: implement a programming language yourself, from scratch, without using an LLM, and then program in that. Don't release your implementation, or any code you've written in it.

Most (almost all) of my programming at home has been done in a Lisp dialect I designed and wrote myself, which is superficially similar to Common Lisp, but with subtle differences, including some deficiencies that I have to work around. And in my Lisp dialect, I implemented a visual dataflow language. Code samples are on my web site, but they're PNG images, so are safe from LLMs (I think). The language was designed to run on MIMD hardware, which doesn't exist in the real world. I've also implemented a Prolog which doesn't use Edinburgh syntax, which I use for type checking, and for parsing a controlled English implementation. So the temptation, and also the option, of using an LLM was never there.

In the course of doing all this, I've learned a lot along the way, which I wouldn't have if I'd used an LLM.

I miss having a canvas. I miss having a place where I created something that is a reflection of my understanding.

The code used to be my canvas. But I suppose it never was an ideal canvas, because the code's primary purpose is to achieve a business objective, or make something work.

I want a really polished literate programming environment where I can slice up the code and add drawings and annotations, and it is all automatically kept in sync with the actual code. I could use this to record my own understanding. Teams could use this to collaborate and create documentation.

The code still matters, but the time for human hand crafted code seems to have ended. Humans still want and need to craft something though. We need to create something to solidify and record our understanding.

Humans need a place to write as a tool for thought, and if the code is no longer that place, we need something else--and if done well it can be better than the actual code.

And it has to not fucking suck--I'm not talking about Jira and Confluence here--good Lord, I know if I present this idea to a project manager they're just going to tell me to use Confluence.

And, again, I'm not talking about just a really great note taking app here. It needs to be interleaved with the code and kept in sync with the code.

I don't mind using an LLM while programming. At least the way I use it, I still feel like my experience, knowledge and taste is being utilized to make it better than if I were to vibe it.

What has made me enjoy it less, is having to deal with colleagues' use of it. Sorry to say, but I don't enjoy talking to meat proxies, or getting huge PRs that solve the wrong problem. It's like half the people have turned off their brain. We produce faster, but we don't produce the right stuff.

While reading "The Nemesis of Creativity"

It uses a Chinese sage to illustrate the fight against using machines:

"I have heard my teacher say that whoever uses machines does all his work like a machine. He who does his work like a machine grows a heart like a machine, and he who carries the heart of a machine in his breast loses his simplicity. He who has lost his simplicity becomes unsure in the strivings of his soul. Uncertainty in the strivings of the soul is something which does not agree with honest sense. It is not that I do not know of such things; I am ashamed to use them."

It resonates with me similarly as the post.

I’ve been experimenting with this idea that I can implement features faster and more accurately than the big model + agent swarm paradigm. I also have been trying this because of what the post brings up when it comes to AI burnout.

For me, writing the code (literally typing), shifting files around, renaming things is slow. So I’ve been using small models + much stronger grasp on the reins. Similar to what this post mentions. It’s been great, the decisions come from me. I tell it to make a domain class with these fields and these invariants. It does it in a split second, I look it over, tweak it and move to the next part of implementation.

When I experimented with swarms it would spend an hour just having agents adversarially review to decide some pretty trivial details. This way, when someone asks me a question during review, I can answer it. When I need to dive back in, I know what to look for and where to look for it. I have way more connection to my work, than a few months prior.

This is great for personal projects, but at work chances are someone will have completely rewritten/refactored/rearchitected everything I'd built up a good mental model of next time I blinked.

I don't understand what's difficult about enjoying programming now that LLMs are everywhere. It's akin to musicians who still play their instruments despite having the ability to stream any music they'd like. Nothing's stopping them from playing their instrument. Why is programming any different?

I remember enjoying myself more as an intern in a fullstack capacity than I did when I was given the job full time about three months later. But that was 7 years ago.

I also remembered the sheer joy of forking enterprise codebases like that of cal.com and highlight.io - just to study and try to understand how large teams worked. I followed issues, I read through PRs and related comments, looked at how some of the comments were resolved. I studied the various moving parts of the app - highlight especially being effectively a log ingestion and aggregation platform, had some rather large infrastructure requirements - kafka, redis, postgresql, clickhouse. It was hard to run with infrastructure directly on your computer. You had to use their docker containers.

I also remembered reading through a tutorial for an sqlite clone in C. It was interesting. I particularly enjoyed typing out the C code and even trying alternate implementation of b-tree operations.

I remember back in 2022 - after I was unemployed for a while - I discovered open source bounties on algora.io (LLMs have since made this platform go bust). I was able to earn roughly $300 per month for a while working on open source issues ranging from $50 to $350. Now most $50 bounties can be one-shot with frontier models. So of course, no one posts open source bounties anymore. If you do, you may just end up with 50 slopped PRs.

Just random thoughts.

People just like to spill out their justifications on how they interact with ai and generally try to be agreeable in their comfort zones until they get bamboozled by actual market demands. No competitive structure is willing to pay more (to you) that could be replaced by lower cost means to maximize profits. This is basic economy 101. This article seems a huge cope to me IMHO regarding the advice it gives. Programming is mostly solved, although in a very anti-humane way IMHO. Hobbyist means could justify it in the remaining time...

I just pray open weight wins at the end and people actually utilize their ai and own their ai.

One thing I've been doing is to use it for:

1. Compare the code against production data with MCP. We use a read only platform called Metabase which reads one of the MySQL replicas. I tell the agent to fetch production data and make a static pass (it doesn't run the code) in which it compares shapes and inputs, and oh boy it has caught a few misnomers.

2. To debug production data and create graphs. It connects to datadog (where we store the logs), checks the history of the commits, and many times suggest fixes. These are for low-medium impact like validations that didn't need to go through, or a step check that it was missing

3. Creating tickets on the board (we use linear). Now PRs are more detailed and can be understood.

And for coding? I've been spending the last 4 weeks scrutinizing EVERY output and decision from frontier models, and pushed back in many decisions.

For tasks you don't want to do (such as work-related ones), use an LLM.

For tasks you enjoy, write them yourself.

I just realized that the last time I wrote a for loop was in November 2025, so it’s been ten months.

The previous time I had this kind of break from hands-on imperative programming was in… 1987.

I was seven years old when I started doing BASIC, and though interests came and went (at one point I went to film school), I never stopped coding entirely. Until now.

The amount of code I’m producing today is higher than before. I’m now also middle-managing a team and doing what’s effectively customer-facing product management, a combination that has become bearable thanks to AI. But it’s hard to shake the feeling that something is permanently gone from my life.

I don't understand these posts. I've never been more excited to program. Everything that I disliked about it disappeared overnight.

Who likes typing code, writing boilerplate, reading bad documentation for nights looking for that small thing, asking around in forums, reading dependency source code, writing trivial unit/ui tests.

And who likes planning, architecting, directing a team, steering and giving advice, reviewing code, designing interfaces and APIs. Coding became more mentally exciting.

LLMs truly took the worst of this trade, and left all the enjoyable things (which they will be unable to do until AGI = for a long time if ever).

It's over. LLMs can produce any algorithm, any tech stack, any concept in seconds, minutes, or hours.

Writing code is like trying to build a house without powertools. Could you do it? Sure. But no one ever will, for most values of no one.

This sums up well the current zeitgeist, wow

  Afraid of loosing your job to someone with little programming skills, no aspirations to quality, and a huge Claude account?

I've lately been using LLMs to do a lot of testing and verification.

An LLM can go and pull files off NFS, and write and run verification scripts in less time than I can even think of a testing strategy or locate the files.

Sometimes they'll do it unprompted

For writing unit tests, which are often repetative and verbose, they are another godsend.

Overall they're freeing up a lot more time for nice things like thoughtful API design, refactoring, system architecture and design work etc.

For exploring massive codebases they are another godsend

People are comparing this to tech automating wood work, knitting, baking etc. That comparison is fundamentally flawed.

You still needed to know how to operate those machines. Where to begin, when to do what. Know what’s right and what’s wrong. They are just tools.

Something like claude desktop can help regular people build, a fully functioning, scalable and maintainable program on any platform contrary to popular opinion. These harnesses are getting that good.

Only reason people don’t do that is because they are intimidated. Regular people don’t even understand file systems. As soon as an Apple-like version of claude code exists that intimidation will be gone.

I have been writing code for 14 years now and everything I learned from my failures and successes someone else can get for free. Even newer paradigms these LLM’s can dream up.

Its the democratisation, of that foundation people put so much effort building is what pissed off everyone here. Including myself I’ll admit.

Results of all these years of hard earned knowledge are accessible to any random person off the street without any effort.

I use claude code at work, even for architectural decisions it can iterate small prototypes to validate. I still read code because I am old school but it can replace most people.

You keep doing it regardless of LLMs, use them to your advantage

It’s very clear AI writes great code and will even review it for bugs much better and faster than a human can. With cloud agents like Devin, you can spawn an army of these agents at a moments notice. Teams who figure out how to do this will simply out compete any teams who don’t.

Now humans operate at a higher level of abstraction. Our focus area is now ensuring the high-level architecture will accommodate future needs well, ensuring the final product meets requirements, and most importantly, ensuring the final product has been validated. It’s important to use every strategy in the book to test the output via unit tests, smoke tests, integration tests, and end to end tests. On our team, we’ve been investing a lot in setting up full test environments that include the entire stack at a level simply unachievable before AI. Now we can merge code changes at an unprecedented velocity without losing confidence in the system.

After programming for 40 years, my brain has many language parsers. But languages and interfaces and classes evolve and it been a huge productivity boost the use LLMs for coding.

I use AI like StackOverflow on steroids. And like using stackoverflow, I do it in a browser and I don't let the LLM touch my code.

I, personally, love programming more than ever!

Appreciate the read, even if the workflow's not for me personally. I've found that I'm just not that interested in writing the code by hand now that the option to not do so is available - but I totally understand people who still want to!

> Since people have mistaken my texts for LLM-generated before, I’ll tell you that it is 100% human written without any AI-assistance.

> This is the game changer.

> This is not communication. It’s a tool output.

Not saying I'm 100% sure, but those seemed slightly sus to me

I think since LLMs make code generation cheaper, we are left with more complicated, often more socially demanding tasks. Programming is becoming even less "leave me alone and let me write code" (on average). This can lead to burnout for many people, but this exploitative capitalism doesn't care.

Look, I love code. I have laser cut code snippets framed on my walls. I functions that I have shared online proudly multiple times. I have projects I have lovingly tended to for years just for the joy of making a computer do something strange.

But what’s far far more important is making people happy by producing good software. Ever since my very first SWE internship I’ve cared most about the user. I’m extremely bummed if the user isn’t happy with my work. I’m ecstatic if my work can improve their day. LLMs change how my work gets done and what it is that my effort goes towards. But the core reason to be here instructing computers hasn’t changed.

Agreeing with the means/end framing, and the bit that's missing is that most of us are both depending on the day. I'll happily let it generate the CSV parser and still want to hand-write the tricky state machine.

Pick something you always wanted to learn more about and use LLMs to help you

I find it quite entertaining that programmers seem to find themselves in the same position as every other person that has hobbies that were once serious jobs but got automated away, and can't seem to connect the dots. How to keep enjoying programming? The same way as people that still make their own clothes, their own furniture, their own shoes, their own bread, and so on. They do it for themselves, for their own satisfaction and for the transformative potential doing things on your own has.

It doesn't matter how fast you're going if you're going in the wrong direction. Programming can still be a challenge with LLM's, but everyone is panicking and skipping the research portion.

Still, isn't programming fine as a hobby? Honestly, when I program, I hand off the parts I don't want to do to AI, and these days I just do what I want to do. It seems like something worth doing as a hobby. At work, you're forced to use AI to meet deadlines, but as a hobby it seems perfectly good too.

Thanks for sharing. It might also come down to whether we see programming as an end in itself or as a tool.

You could just not use LLMs?

I have been programming for 25+ years and the last year has been the most fun because every single useless-for-everyone-but-me idea ... I could spend a few hours on and get it working. Did 30-40 different small projects this year.[1] Mostly used by me (and some by a couple of friends).

I write software because I am interested in the final outcomes, not because I enjoy the journey, which is often infuriating because of the mistakes you make, or the crap you depend on to get your work done.

Whether people will still have jobs in three years, or thirty, only time will tell, but I feel people are kidding themselves if they think LLMs won't have an impact. We were fine with using machines to automate physical labor as we now balk at the same thing happening to the intellectual side of things.

I, personally, have done a complete volte-face as far as my views on the subject are concerned over the past year or so as I use LLMs more and more for coding and other tasks.

---

[1] There is this idea I have had of an Excel replacement: simple, purely functional, TSV-based spreadsheet with zero backward compatibility with styles as purely optional sidecar material that I have always wanted to do but lacked the time. Brainstormed a spec with Claude today. Might work on it in the near future.

But there might be reasons you don’t want to be, e.g. you actually need to bring some real productiveness gain to the table, or you don’t want to be left behind while the rest of your team, your company, your industry, is moving towards heavy LLM adoption.

Oh sure, you are not an LLM bro! Honest!

The amount of new LLM articles that try to feed them like vegetables to a child is amusing and tragic at the same time.

[flagged]

[flagged]

[flagged]