Hacker News new | past | comments | ask | show | jobs | submit
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.
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.
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.
For my personal projects I think it does matter even more. I've got some perculiar and weird quirks that may even go against best practices (that's what makes them personal projects).

AI can get the implementation done just fine but in my experience it needs guidance because it can't guess what features and details I want / don't want.

The difference to "before" is that it's now possible at all for me to get personal projects to a working state but in sum they still require a few hours every now and then supervising.

> 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.

It’s just my opinion that you have to ask the LLM to do things? Seems like reality to me tbh.
> For personal projects that don't matter?

If it doesn’t matter then do what you want. By definition, it doesn’t matter.

Some of us actually use these tools, so it does matter. You do have to consider things when it matters.

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.

I'm coming to think that a hybrid of vibe-coding but with an existing substrate is the right way to go.

For instance in the context of this SketchUp clone that might mean using AI to generate an addon for Blender.

For some of my recent projects I'm using the community edition of Odoo to serve as that substrate because it already has an established community of modules to draw from, ten years or so of real world use, and I don't have to burn tokens generating a user account system with permissions or the data models / ORM to interface with them.

This seems to be serving me well, but we'll see. It could be that I end up in the same the tool becoming the project scenario that you describe, just a little bit later than if I had started from a blank slate.