I have several personal tools I’ve built and maintained.

It’s always more work than it looks. You can get to mostly usable tools quickly if your request isn’t too difficult, but every time I use them I run into another thing that needs to be fixed, changed, clarified, or cleaned up.

It’s fun at first, but over time you realize you’re spending more time building the tools than using the tools to build the thing you originally wanted to work on.

I think personal software is best for highly specific tools or for things you need to use repeatedly for a very long time.

For something like a SketchUp competitor, I wouldn’t want to try to maintain my own. The number of edge cases and features is bigger than you imagine up front, and the vibecoded version that might appear a few hours after your prompt is going to be very far from the version you want to use.

▲

Gigachad 6 minutes ago | parent | next [-]

I’ve been using the vibecoded Lightroom clone and it’s 5000 commits and around 20 releases in yet still has countless issues and missing features. I feel like it will get there eventually but the idea that you should just vibe up your own Lightroom rather than using an existing one is absurd with today’s tech. It’s still a massive amount of work even if it is way faster than ever before.

The vibecoded apps all rely on an army of users exploring the program and reporting all the bugs and edge cases. You don’t want to be doing that on your own.

▲

altmanaltman an hour ago | parent | prev [-]

Isn't the whole argument that ai-driven code will reduce the time spent building because AI can do it now? And a SketchUp competitor by defintion will not be personal software just like SketchUp is not.

▲

vips7L an hour ago | parent | next [-]

AI can’t do it. You still have to hold its hand. You still have to sit there and ask it to do things. There is no fire and forget.

▲

altmanaltman an hour ago | parent [-]

For personal projects that don't matter? Sorry but that's your opinion at this point. I respect it but also fully disagree. Also even in that case, isn't it still reducing time and problems we have with pre-AI personal projects like maintainability and feature creep like you mentioned.

	▲	80fj0348i 36 minutes ago \| parent \| next [-]
		> For personal projects that don't matter? My personal projects matter a lot. For some of them I am trusting my private data in the code, so I need to hold it to a high security and privacy standard. For others, I have hundreds or thousands of users (game mods, helper tools for hobbies, etc.), and I don't want to ship low quality to them.
	▲	vips7L an hour ago \| parent \| prev [-]
		It’s just my opinion that you have to ask the LLM to do things? Seems like reality to me tbh.

▲

Aurornis an hour ago | parent | prev [-]

I was talking about AI developed tooling.

It’s amazing that you can get something usable quickly, but then every time you use the software you’re back in the AI working on your tool.

Using AI to build the tool becomes the project, replacing the project that led you to think about vibecoding a tool.