It's nice that you have all those wonderful experiences with LLMs. But for once in your life, could you show us the code? Because you look like yet another cheerleader that have nothing to show, and it's annoying.

Sure. I'll show something. I'm working on an app to help teach myself french. I work at a busy startup so I only have a few hours to spare here and there, but I've managed to make an app that works very well for me, mainly because of the help I receive from Claude Code. I can't make the github repo public because it contains some copyright material [^1]. but maybe I'll make a censored version public if there's interest. It's at https://yap.town .

[^1]: to be clear, nothing in the frontend is copyrighted. I use some copyrighted works to figure out how common various words are, which I need because I wanted the app to teach the most common words first.

Edit: the site uses the FileSystemWritableFileStream API, so Safari/iOS users will need Safari 26.

You touch upon an interesting phenomenon that is quite pervasive throughout the world of software development, and possibly many other fields as well.

To avoid heated discussions, allow me to illustrate the concept with why enterprise software is mainly built with Java, whereas most blog posts are about writing backends with TypeScript, Python, or Rust. The reason for this is at least twofold:

1. Professional programmers don't get paid to write blog posts, and typically want to spend their free time doing other things. Hobbyists do have the time, but they typically do not see the added value of a boring language such as Java, because they don't work in teams.

2. When something is already known, it is boring for people to read about, and therefore less interesting to write about. When something is new, many people write about it, but it's hard to tell who is right and who is wrong.

Given that good writing, and the additional marketing to find the respective audience, take energy, it is not strange that we find weirdly biased opinions when reading blog posts and forums on the internet. I typically find it better to discuss matters with people I know and trust, or to experiment a bit by myself.

The same might happen now with reporting on AI assisted coding.

Edit: might as well just have said "visibility bias" and "novelty bias" if I had consulted an LLM before commenting.

Here's an example, from a session from yesterday and today, buyer beware naturally I'm still testing and refining it: https://github.com/rdaum/tature

I'll now go through this, remove the excessive comments and flowery language, add more tests, put it through its paces. But it did me a service by getting the pieces in place to start.

And I'm even above the 250 karma threshold!

This is the new "Source?" comment (which, funny enough, still works).

But I don't think the code matters as much as the intention. The comment is all about exploration and learning. If you treat your LLM like a Wikipedia dive, you will come out the other end with newfound knowledge. If you only want it to achieve a discrete goal, it may or may not do so, but you will have no way to know which.

I have had similar experiences to OP. All of these apps (mostly maths learning, but also the bus one) were coded using a mix of copilot and Gemini CLI: https://rupertlinacre.com/

I'm probably capable of building all of them by hand, but with a 6yo I'd have never had the time. He loves the games, his mental arithmetic has come on amazingly now he does it 'for fun'.

All code is here: https://github.com/rupertlinacre

Much of this built out of a frustration that most maths resources online are trying to sell you something, full of ads, or poor quality. Just a simple zoomable numberline is hard to find

No code to share yet, but results nonetheless.

Tabu search guided graph layout:

https://bsky.app/profile/micahscopes.bsky.social/post/3luh4s...

https://bsky.app/profile/micahscopes.bsky.social/post/3luh4d...

Fast Gaussian blue noise with wgpu:

https://bsky.app/profile/micahscopes.bsky.social/post/3ls3bz...

In both these examples, I leaned on Claude to set up the boilerplate, the GUI, etc, which gave me more mental budget for playing with the challenging aspects of the problem. For example, the tabu graph layout is inspired by several papers, but I was able to iterate really quickly with claude on new ideas from my own creative imagination with the problem. A few of them actually turned out really well.

Sometimes I'll admit that I do treat Claude like a slot machine, just shooting for luck. But in the end that's more trouble than it's worth.

The most fruitful approach is to maintain a solid understanding of what's happening and guide it the whole way. Ask it to prove that it's doing what it says it's doing by writing tests and using debug statements. Channel it toward double checking its own work. Challenge it.

Another thing that worked really well the other day was to use Claude to rewrite some old JavaScript libraries I hand wrote a few years ago in rust. Those kinds of things aren't slot machine problems. Claude code nails that kind of thing consistently.

Ah, one more huge success with code: https://github.com/micahscopes/radix_immutable

I took an existing MIT licensed prefix tree crate and had Claude+Gemini rewrite it to support immutable quickly comparable views. In about one day's work. I scoured the prefix tree libraries available in rust, as well as the various existing immutable collections libraries and found that nothing like this existed. This implementation has decently comprehensive tests and benchmarks.

One more I'll share, an embarrassing failure: https://github.com/micahscopes/splice-weaver-mcp

I used vibe kanban like a slot machine and ended up with a messy MCP server that doesn't really do anything useful that I can tell. Mostly because I didn't have a clear vision when I went into it.

they almost exclusively have under 250 karma too...