The Emacsification of Software

I know the article is mostly about making stand-alone software, but this type of thing is why one of the things I value most when looking workflow tools I will be using heavily is extensibility. I can try put someone's neovim plugin for a second, figure out if it's something I actually need, and if so make my own personal version that matches my mental model perfectly, adds all the dumb little bells I want, and removes all the useful features I don't personally care about. Plus I no longer need to worry nearly as much about supply chain issues.

Over the years I've replaced 90% of the plugins I used when I started. Plus I get a nice outlet from any pesky NIH symptoms.

I feel as though the author really missed an opportunity here: "The Emacsulation of Software"

I've absolutely engaged in making personal software [0] thanks to the age of LLMs.

But to be honest, my time using Emacs didn't teach me to "build personal software". My Emacs set up was extremely brittle, and it was a nightmare when I tried to use it across Windows & macOS. My university project was written using an unholy combination of org-mode & some workflow to create a beautiful LaTeX file, and I couldn't tell you how to recompile it (if I were to try, I'd probably get an LLM to literally translate it to LaTeX).

I want my life to have as little maintenance as possible, and making my own software for everything isn't always compatible with that.

[0]: A rewrite of a NETFX application in Rust, simply because the 20 minute installation time irked me: https://github.com/bevan-philip/wlan-optimizer

Setting aside the fact that good content is more enjoyable than bad content, experiences are meant to be shared. Humans are a social species, and a very large part of media consumption goes beyond the actual consumption and into sharing that experience with other people. People build communities around the media they like, and even integrate their favorites as part of their identity, wearing branded clothes or cosplay, decorating their rooms with merch, setting wallpapers, and so many other ways to signal what they enjoy to others. "Content creation for one" rather misses how humans work. Heck, not only media but even tools are subject to this -- people legitimately make emacs or vi part of their personality.

> The entire economic model of content creation and distribution is going to explode in the next 3 or 4 years

I think this is also inherently self-contradictory. What's the point of distributing content made for one? This gets into the same fallacy that people engage in w.r.t. "applications for one" displacing software developers. Yes, LLMs can pump out buggy software that suits one person's needs, and it doesn't need to be reliable enough to deploy at scale. It serves real utility here, because there was a gap between "the value of such software" and "what software developers are willing to work for", which meant that this software wasn't being created because there wasn't economic value in it. But then, how does one suppose software that has no economic value is going to replace all the professional software developers who were being paid to produce software that has economic value? LLMs filled a gap software developers weren't being paid to do, but given that they were not paid to do it, their jobs are not contingent on the existence of this niche. It simply doesn't follow that being able to produce content with zero economic value, whether that's applications or content for one, will cause an 'explosion' in the existing economic models.

No, I don't. I don't want anything that has to do with John Gruber, ever.