Is this an effective CTA?

What types of negative side-effects would there be from an “open source” application that was free, open, and restricted entirely by license? Rather than “we make no warranty” the license says “you may not use”.

I’ve also had a few products I’ve released on GitHub as public but never assigned a license, which probably means they are proprietary, unless GitHub TOS says otherwise.

I realize each of these is a unique situation.

I use my own text editor too. Nobody else seems to get value from it. I’m still surprised by the value we get from home grown solutions.

I use my own text editor too, written using my own programming language. Fortunately Operating Systems suit my needs and I won't have to write my own OS ;-)

I use my own editor too. I modified an existing editor to my own needs. But I do use VSC as well for multi file projects. My editor can load images as well and has a scripting language to manipulate images. I primarily use it to edit my website, which is a static website in bare HTML. It also has some 'browser' functions in the sense that F5 opens a link including jumping to an anker if there is one in the link. It does have colour coding for HTML that also checks for matching tags.

Didn't even link it. :(

I guess the "link" is the implicit suggestion to write your own :-)

I use my own text editor too.

Sometimes I get surprise questions from my friends whenever they see my screen. “What’s that?” “That’s my own text editor!”

I’m currently writing my own text editor (it’s basically a markdown equivalent of Jupyter notebooks).

I’ve also written my own terminal emulator and my own shell. The shell does actually see other contributors and users these days too.

You can perform a legitimate muscle-flex when saying that too.

Me too. Maybe we could mastermind? Reach out, my email is in my profile.

Balance Buckets helps you set aside money for the things you care about.

It’s two-minute envelope accounting for your bank balance.

https://buckets.joelryan.com

His book (maybe he has several) is fantastic.

Cool project.

I keep wanting to build a large "lite brite" style display for my window. I keep getting stopped even though I have a lot of the tools necessary, like this laser engraver.

You just gave me an idea about an extremely simple way to build this using a Raspberry Pi Zero and my cheap laser engraver.

> What really matters is how well does the code performs 1 month after it goes live, 6 months, 5 years.

After 40 years in this industry—I started at 10 and hit 50 this year—I’ve developed a low tolerance for architectural decay.

Last night, I used Claude to spin up a website editor. My baseline for this project was a minimal JavaScript UI I’ve been running that clocks in at a lean 2.7KB (https://ponder.joeldare.com). It’s fast, it’s stable, and I understand every line. But for this session, I opted for Node and neglected to include my usual "zero-framework" constraint in the prompt.

The result is a functional, working piece of software that is also a total disaster. It’s a 48KB bundle with 5 direct dependencies—which exploded into 89 total dependencies. In a world where we prioritize "velocity" over maintenance, this is the status quo. For me, it’s unacceptable.

If a simple editor requires 89 third-party packages to exist, it won't survive the 5-year test. I'm going back to basics.

I'll try again but we NEED to expertly drive these tools, at least right now.

I don't understand. You specifically:

> neglected to include my usual "zero-framework" constraint in the prompt

And then your complaint is that it included a bunch of dependencies?

AI's do what you tell them. I don't understand how you conclude:

> If a simple editor requires 89 third-party packages to exist

It obviously doesn't. Why even bother complaining about an AI's default choices when it's so trivial to change them just by asking?

My main point is that we need to expertly drive these tools. I forgot the trivial instruction and ended up with something that more closely resembles modern software instead of what I personally value. AI still requires our expertise to guide it. I'm not sure if that will be the case in a year, but it is today.

You seem intelligent so it is probably confusing to many why you are posting this.

You call it a trivial instruction, but it is not trivial. It was a core requirement for your own design that you neglected to specify. This is not different than leaving out any other core requirement for a engineering specification.

Most people would NOT want this requirement. Meaning most people wouldn't care if there are package dependencies are not, so the agent 100% did the right thing.

I always tell Claude, choose your own stack but no node_modules.

What's missing is another LLM dialog between you and Claude. One that figures out your priorities, your non-functional requirements, and instructs Claude appropriately.

We'll get there.

This perhaps reflects the general divide in viewpoints on “vibe-coding”. Do you let go of everything (including understanding) and let it rip, or require control and standards to some degree. Current coding agents seem to promote the former. The only way with their approach, is to provide them with constraints?

> What's missing is another LLM dialog between you and Claude. One that figures out your priorities, your non-functional requirements, and instructs Claude appropriately.

There are already spec frameworks that do precisely this. I've been using BMAD for planning and speccing out something fairly elaborate, and it's been a blast.

Can you share the prompts?

I used this prompt and it suggested a model I already have installed and one other. I'm not sure if it's the "newest" answer.

> What is the best local LLM that I could run on this computer? I have Ollama (and prefer it) and I have LM Studio. I'm willing to install others, if it gives me better bang for my buck. Use bash commands to inspect the RAM and such. I prefer a model with tool calling.

That is a really interesting game. It's making me think twice about real estate investment. :P