[josephg]

Really? I'm more motivated than ever to make stuff at the moment. I have a long list of projects I've always wanted to make, but I never had time. The barrier is so low now.

For example, I want to make:

- A mini OS on top of SeL4

- A UI framework based on SolidJS, for native apps, in rust.

- My own photo manager (which can do backups & sync across all my devices). And a gallery to share photos with friends

- A local first data store, built on top of CRDTs

- My own programming language

And lots more.

Each of these projects on their own would take months of time. If LLMs can speed up development, that's great! I don't care if nobody else uses what I make. I want a personal computer full of my own software.

[throwaway13337]

I feel the same way as you. But was unfortunately not surprised to see the replies you are getting here.

There are a ton of opportunities available right now to make new things. And make them better, more customizable, and more sovereign.

To the replies: be the change you want to see in the world, guys. That may be trite but focusing only on the negative will just make your own life shitty.

[cryo32]

Leisure projects for me at least are about the personal challenge and achievement. If the LLM does it, you achieved nothing.

[r2_pilot]

I'm glad that you find achievement in the personal challenge. At home, I'm just getting things done. Small things, bigger things, and best of all I get to pet the dog more while it works in the background.

[cryo32]

Yeah so don't bother. I don't write code at home. What's the point? I go on holiday once a month!

[josephg]

So, you don't even work on personal projects? But you want to lecture everyone else about how to do them correctly (according to you)? What a waste of time.

[cryo32]

I spent years working on personal projects.

Back to 1988.

Think I have a fair bit of experience.

[whstl]

Are you assuming that "using a LLM" automatically means "vibe coding"?

Is it not engineering anymore even if you micromanage and relegate the machine to a better typist, following patterns and doing research around?

[josephg]

> If the LLM does it, you achieved nothing.

Oh get off your high horse.

You may as well say "If the compiler compiles your code, you achieved nothing". Its the same argument.

I love meaty algorithmic challenges. And I enjoy the design challenge of making a piece of software. But I don't write CSS for fun. Debugging styling issues on mobile? I hate it.

LLMs let me work on the parts that I find enjoyable and satisfying. Like UI design, or figuring out the data model. And then I can delegate the parts I don't like to Claude. It seems very happy to bang away at CSS.

That's a great deal. If you want to personally write every line of code, good for you. But don't police my leisure projects.

[sillyfluke]

I support this take especially since you added the "I don't care if nobody else uses what I make", but you should at least acknowledge what you're talking about is pretty unrelated to the article, as the author's entire context seems to be making something for other people to use and building it together with other people.

Since you said you want to make those things that you list, I assume none of these things have been built yet. If so, I would encourage you to consider how excited you will be to constantly maintain those things you build. But even if the maintainence cycle won't be as exciting, since you are the sole user you have the advantage of being able to proceed at a leisurely pace even while doing maintainence work.

In a professional setting, the dopamine hit of being able to build something quickly that works in an area that you have little to no knowledge in makes you more dependent on the AI in the maintaince cycle as you want to chase that dopamine high by maintaining the same development speed. This in turn leads to a bigger burnout crash after that peak dopamine hit. Maintainence is a phase of diminishing returns even without AI, but when your coding agents are introducing new bugs at record pace with their bugfixes with no new features to write home about you are in a special place in Hell.

I'm all for using AI to build ambitious projects. I have yet to see a person/company/organization continuously release huge software endeavours in a stable professional manner day in and day out with a coding agent harem in tow.

If something like the Ladybird browser, or any browser that is "built by scratch", achieved Chrome parity in six months and consistently maintained the same level of stability with continuous releases then I would see that as proof that this approach has become professionaly sustainable.

The reason people are getting away with so much using AI is because of the open secret in most enterprise engineering practices: the customer cares more about the response time for fixes they report than they do about overall or longterm product quality.

[josephg]

> I would encourage you to consider how excited you will be to constantly maintain those things you build.

Why should I consider that?

Its funny how the default with programming is that the piece of software exists forever. I've been learning to play the piano lately. The default with piano is that every piece is ephemeral. If I don't go out of my way to record something I play, after the notes have run out, the piece is gone forever. The same is true of cooking - except you can't record a meal at all. Once you eat it, its gone. Lots of art forms are like this - theatre. Dance. The circus. They're no less beautiful for being ephemeral.

Why do we assume software has to be maintained indefinitely? Why even think about that right now? Maybe I'll work on these projects for awhile, maintain them as long as I want, and then in a few years someone will make something way better and I'll use that instead? Would that make the effort I put in pointless? I don't think so. I think it would make programming more like playing the piano. How lovely.

> I'm all for using AI to build ambitious projects. I have yet to see a person/company/organization continuously release huge software endeavours in a stable professional manner day in and day out with a coding agent harem in tow.

Yes, I've burned through enough claude tokens now that I find myself agreeing with you. I wouldn't use an LLM to make and maintain google chrome. But I wasn't planning on doing that anyway. There are also a lot more options than (1) write everything yourself and (2) vibe code the whole thing.

LLMs are good at small-to-medium scope tasks right now. Fine. I'll use them - or not use them - with their limitations in mind.

[sillyfluke]

>Why would I consider [maintainence]...Its funny how the default with programming is that the piece of software exists forever.

By all means don't consider it if you don't plan on using them for a considerable amount of time, but there's a lot of of distance between a decent amount of time and "forever". You listed a mini OS and a UI toolkit among your projects, I hope you can forgive me for assuming you were planning to use those things to build more things, which would in turn often entail improving and maintaining these building blocks while they are actively used.

[josephg]

Ah fair. When you say “maintenance”, my mind goes to handling pull requests and keeping on top of filed issues on GitHub. If the software has an audience of 1, a lot of that work goes away.

Adding the features I have a need for over time is the fun part as far as I’m concerned.

[slopinthebag]

The issue is maintenance. If you want to use these projects for important things, you need to maintain them. If you don't want to maintain them, I can't see myself using them for anything important.

I actually want less software for myself. Less things to maintain. I've become a "digital minimalist" in that I use very few software, only ones maintained by others who can afford and are willing to keep them working.

[josephg]

Some people find freedom in building their own house. Some people find freedom in living in a serviced apartment.

Some people find joy in home cooked meals. To others, wealth is never needing to cook again.

To each their own.

As for maintenance, I think LLMs are actually very well suited for small maintenance tasks. The expensive part of programming is loading and unloading context into my head. "Oh dear, what is all this code doing? Oh no, coffeescript? And some ancient version of express JS? How does any of this work?". LLMs can bomb in, fix a compilation error and bomb out. "This program isn't compiling any more on macos X.Y.Z. Read the patch notes. Figure out why and fix the problem." Perfect.

[lacedeconstruct]

*Make anything "new"

[josephg]

Everything I want to make is new. I don't understand the objection.

For example, the photo backup system I want to make will let me manage my ~400gb photo library. I want my library backed up on a couple devices, running linux and freebsd. I want my mac and iphone to have a local mirror of all the favorited photos, and when I'm at home, I want to be able to browse all photos from those devices by streaming them over the local network. I want native macos & ios app interfaces to view and manage all that.

I don't know any existing software that meets my requirements. I don't think any such software exists. Apple, Dropbox and Google will solve this problem for me if I store all my photos in their cloud and pay them an ongoing subscription for the privilege. I'd much rather make something myself, and back up my photos on my own hard drives.

Making something like this is simple enough, but very time consuming. If claude can take the drudgery out of it, well, I think that's just delightful.

[righthand]

Ente photos is one thing and there are others.

You can accomplish most of that by installing Syncthing.

But the objection is that you’re not really building anything new even if you think it’s a new idea. By your definition you’re building for yourself and not sharing…so what good are your little projects. Reading your original list it just seems like you want to build and run software without having to do any research, even if a solution already exists.

[josephg]

> But the objection is that you’re not really building anything new even if you think it’s a new idea. By your definition you’re building for yourself and not sharing…so what good are your little projects.

What an incredibly blinkered view. You think there's no value at all in making software unless your program solves a truly novel problem, and does so for millions of users?

There's so much joy that can be found in simple, disposable acts of creativity. I don't need the world to applaud when I cook an omelette, make a table out of wood or play a piece on the piano. Why would I need that from the software I make? Just because you can buy a table from IKEA doesn't mean its not fun to make one yourself. Just because someone on spotify played it better doesn't mean there's no joy in playing music.

Why would I hesitate to make my ideal photo library program, just because other programs exist? What a sad, self-limiting rule.

[righthand]

No you would hesitate because you yourself said you dont have the time. So why would you still develop it if you dont have the time to maintain or develop a project like that. You’re the one being sad and limiting unless you find a reason not to be. Sorry you had to rely on Llms to get a decent photo setup running but you also DIDNT have to reinvent the wheel to accomplish that. Waste all the time in the world that you want building single use stuff with LLMs but dont walk around like it wasn’t possible before because it required dev time then turn around and tell us you have plenty of time to screw around with an LLM which is proven to not give time savings. Im glad you found out about code generators to start projects though.

[josephg]

You seem mad at me for making fun projects with LLMs. Of course it was possible to do fun stuff before LLMs. Been there, done that! It’s just even easier now that I can rent an llm to do all the boring bits. How sick is that!

Does that make you mad? Why does other people enjoying themselves with LLMs make you mad?

[argee]

I have everything this guy is talking about just from running Filerun (with the Nextcloud client for mirrors) and backing up to Backblaze R2. At some point developers seem to forget that other developers exist.

[josephg]

> At some point developers seem to forget that other developers exist.

At some point developers seem to forget that making stuff is fun. The fact SQLite and GCC exist doesn't mean you're banned from making a database or a C compiler.

You're allowed to make stuff just because.

[cryo32]

What's your time and life worth? You pay Apple to deal with it (which I do) and get to live a peaceful life and go out and take photos and have experiences. Or do you spend weeks implementing your own solution with Claude. The latter is considerably higher cost in time and money.

AI is seen as a way out of drudgery but you're just trading one problem for another.

[satvikpendem]

The implementation is part of the fun.

[ori_b]

So why would you buy it off of Anthropic?

[duckmysick]

In any activity you can take shortcuts that makes it easier. It's up to you how many (if any) you want.

Take woodworking for example. When I build a kitchen cabinet, I can get lumber that's already smooth and treated, I can buy drawer tracks, I can use power tools instead of a handsaw and a screwdriver, I can use a pocket hole jig to make joints easier. I still have to do more planning and assembling than with the Ikea cabinet, which also takes more work than having a contractor do everything for me.

I'm doing it my way because it's fun for me. Other people might enjoy other parts of the process - or different things altogether.

There's a whole spectrum between doing everything from scratch and paying someone to have it done for you.

[satvikpendem]

I don't understand the question. For one thing I use local models mainly, but even if I didn't, I'd be buying the tokens from cloud model providers, not the prepackaged, fully complete software itself. I buy the tokens to make what I want.

It's actually quite similar to buying the services of a programmer off Upwork to build something for me, only with LLMs it's way cheaper and faster, with a shorter feedback loop.

[unknownfuture]

Interesting that you think building is just coding.

What do you think architects do? Or interior designers? Or civil engineers?

[uncognic]

Take a look at https://immich.app/

[josephg]

Oh that looks lovely. I enjoy the UI and all the work on tagging and classification. But its still missing some features I want:

- I want native desktop apps

- I want P2P device sync. My laptop and my home server should be peers. Just with different rules for which photos are stored locally on each device.

- I want per-device storage rules. (Eg, "I want all my favorited photos, and recent photos up to 50gb on my laptop").

- Backups. I want to be able to plug in an external hard drive and backup my photos (with some rules). Then disconnect the drive and see in the metadata for those photos that I have a copy of the full res RAW on that drive.

But even if other programs exist, its still fun to make something myself. Authoring your own software gives you a different relationship with the computer. You're less of a consumer. You can change or tweak features on a whim. Psychologically, its kind of like being in your own home vs being in a hotel room. If you hate the furniture at home, you can move it or change it. You can decorate however you like. In a hotel, you're affected by your environment but you have no agency over it. I think its much more healthy to create.

[rrvsh]

You're not wrong, but a fork of Immich would achieve much of the same, no? I understand this is probably a detour from the conversation, but I've been thinking of doing the same to add some niceties

[josephg]

If my goal was to make something that fits in with the existing ecosystem and has the most users possible, I could do that. Try to make some changes which could possibly be upstreamed. Spend my time going back and forth on minutia in github pull requests. Learn Dart. Figure out how to wrap a typescript & dart app in a macOS native window. Or turn to electron. (Yuck.)

But I’m optimising for the feeling of joy and agency over my tools. I also want to experiment with p2p / local first data structures in a real app. I could fork immich and rewrite the data model. But that all seems much less fun.

At the end of the day, I’m not doing this for other people. I’m doing this for me. Learning dart so I can hack on someone else’s code sounds like a pain in the butt. Not like something I’d want to do for fun on the weekend.

Working on someone else’s code seems like a strange default. You and others have jumped on me for wanting to make my own thing instead of using - or forking - someone else’s software. Can you help me understand why? Why would that be the default for a fun hobby project? I’m confused.

[ori_b]

And you're actually excited by the prospect of buying them from Anthropic instead of making them?

[josephg]

Suppose you're the senior engineer on a project. You design the UI of the software. Then design how you want the software to work internally. Then write the core data structures. And then guide a bunch of junior engineers to write the code, review their work.

Is that the same as buying a computer program from anthropic?

I have a friend who's an architect. Sometimes we're in the city and he says "Oh see that building? Its one of mine." He didn't lay the concrete, or do the wiring or anything. Should he not be proud, because a construction company built each floor? Does it not count? Does his contribution not matter?

[satvikpendem]

Open weight models exist and are good enough to make the projects above.

[ori_b]

And you're actually excited about these table scraps that companies couldn't even monetize, rather than making something?

[rrvsh]

You are being needlessly combative. Please take a step back and look at what you are doing - I don't think this is positive for you or anybody

[satvikpendem]

Couldn't even monetize? DeepSeek and Alibaba with Qwen are doing quite well, no table scraps required. I am making things, I don't have to physically type letters on a keyboard to make things as long as the output of what I want exists.