nate-gehringer

This whole LLM coding mania has highlighted something that I was previously less appreciative of: some people (self included) like writing code because it is an enjoyable, enriching experience to them. Solving puzzles in code has lit up the reward pathways of my brain since the first time I tried it, and I don’t see why that would ever change.

Prodding an LLM into solving a problem is just not the same thing. I understand that the results of prompting could be more exciting than programming to some, but the idea that manual coding is “over” feels dismissive of hobbyists at the very least. Perhaps the author is suggesting that manual programming in the industry is over, but I don’t buy that either. Thesis being, there will eventually be a cost to employing “experts” that lack understanding.

> If agents can handle the code, could we finally work directly with the logic, interfaces, and data models we want?

Aren’t high-level programming languages very refined encodings of “logic, interfaces, and data models?” Why would using natural language be more efficient at such things than special-purpose languages developed over decades?

If you have to preface an idea about its potential confusing nature, that should be a warning that it might not best serve your users.

In my opinion, the existing UI widget that solves this problem best is a plain old group of radio buttons (auto, light, dark). Two checkboxes that interact with each other and also a sometimes-hidden label is something new for users to learn and also more complex to implement and maintain.

In my haste to initially get a blog started and published, I created it as a single HTML file with fragment identifiers / links for each post. Earlier today, sethops1’s valid feedback prompted me to restructure it as an index page with separate pages for each post.

Links to posts no longer contain URL fragments, but I kept the fragment-style links working with JavaScript.

I recently blogged about some Cloudflare Workers I developed to combat this type of traffic: https://code.backwater.systems/blog/#2026-06-29T23:40:00.000...

Ahh—thanks for the update. I’ll look into changing that notation to make it less confusing regarding slash chords.

I appreciate the feedback and sanity checking!

I’m definitely planning on add a wider array of chords types now that the app is basically working. As far as the 7th inversions, I essentially “ignored” inversions by flattening the notes into a single octave … there may be an issue with this logic.

I came across <https://chord-display.rednet.io> myself yesterday and took a cursory look. Nice app. They use a library called `tonal` <https://github.com/tonaljs/tonal> for their music theory logic, which ought to be a good resource to validate against.