It's on me for procrastinating playing the game for so long, it was bound to happen.

In any case it's not practical to carry your dotfiles everywhere you go. Changes are also a hassle to propagate

Not terrible, but I'll just point my own llm to it instead of reading it myself like I would for an actual great documentation

https://en.wikipedia.org/wiki/Magic_(illusion)

One of the reasons why I use tmux rather than i.e. iterm2 tabs is that I don't have to change any of my habits or learn extra shortcuts when I'm working with ssh.

Although while I usually like tabs for most apps, I don't use tabs for terminal and rely either on window manager or tmux. I guess the difference is that I often want a mix of tabs and having multiple terminals side by side, whereas I don't really need that for a browser (or very seldom)

More concretely, you can have an installable (and updatable) skills that will teach the agents how to use your api and will come with slash commands.

What you cannot do with an mcp is pipe the output into standard tools (jq, head, etc...) or create scripts around it, etc.

A local mcp doesn't come in play because they just couldn't offer the same features in this case.

But what does ephemeral code even means? That we will throw everything out of the window at every release cycle and recreate from scratch with llms based on specs? That's not happening

The only thing I can think of is massively increased context windows (around 4k for gpt3), but a million context token with degraded performance when full is not what I'd qualify as resolved.

While it's a great tool in the hands of capable and well intentioned people, there's not a world out there where the average quality of software goes up.