• 1 Post
  • 18 Comments
Joined 1 year ago
cake
Cake day: June 25th, 2023

help-circle

  • The first pass of elm ecosystem solved it. Before elm, it was also solved by other frameworks. But people wanted to be able to reuse their components and not rebuild new ones. React provided the ability to reuse css, and dirty js code in the middle of your application. You already had an way bigger ecosystem because you didn’t have to learn and built a complete new system again.

    Personally if I had the choice I believe a new start should start at the browser level. Stop supporting HTML/CSS/JS. Create a new app-centric DSL and not a document centric one like html/css/js.

    Ideally something inspired from cocoa layout. And I am dreaming but not accept generic code on the client side and only support a small controlled API. It would solve so many security issues. Sure, the creativity in such an ecosystem will be severely reduced. But we will have a so much improved UX.











  • I don’t see how this could be positive for any Software developer in the long run. I totally see how this could be positive for CEO/CTO, Project Managers, in the long run, and I see a few short term advantages for Software developers.

    Let’s be clear, I saw that coming since Microsoft bought Github, and I am scared by the direction this is taking. The end goal is to move more and more control and power to non-software people about Software development.

    By forcing every developer to not use their own tools this will have a lot of advantage for CEO/CTOs but this is terrible for software developers:

    1. telemetry: they will try to find a formula to assess who are the best performer in a team. And as with SEO, any formula could be gamed, the best at this game, will not be the best software developers, but the one that will learn how to cheat.
    2. global team tooling enforcement: vim vs emacs etc… ? Forget about it, the only way to work on a project will be via this unique allowed editor.
    3. assets protection: impossible to download the code on your local computer to use external tools on it. The only way to have analysis tools will be via these “allowed” analysis tools. This will make code analysis and experimentation a lot more difficult.
    4. Locked by promoting vendor-specific applications. As you will focus to make your code/app/product work only for Google Cloud for example, you will naturally use Google-Cloud-only features that will make your code difficult (or impossible) to move to another Cloud provider, or god-forbid, host your product on a non-cloud or private made cloud.

    And I can think of other possible drawbacks but my comment is already long enough.



  • I don’t see how this could be prevented.

    There are already many “small web” movements. With different proposals. Like gemini, sub-set of currently supported web standards (typically no-js, no-css, no POST, etc…)

    But the monetized web is doomed to reach a point were it will be controlled in such a way that you will not be able to block ads, not be able to hide your pseudonymous identity.

    I remember reading an article many years ago about the cat and mouse game between ads publishers and ad-blockers. The conclusion were that in the end, ads blocker will lose the final war. And with these kind of system we are closer and closer to reach it.

    I think we need to collectively find a way to have sub-nets. For example declare that our website conform to certain sub-net properties.

    • no-ads
    • privacy (no cookie/no js/no user-agent header/no canvas, no css)
    • etc…

    The small webs are different for everyone. It would be very nice if we could put an HTML header that would list which small webs pattern this page is compatible with. And have a browser that would adapt to your preferences and also a way to filter your small-web preferences in search engine.

    The closest to this we have today is probably gemini. But this a very small but friendly web. I am sure we could find other solutions to create an alternative “respecting his users” web.


  • As you only mention git and not any git hosting. I would say you could easily use git hooks. Fir you and probably ask everyone in your team to install the same git hooks to have a chance to review changes before they are commited.

    For my team there is an init-git-repo.sh shell script in our repository. When you execute it, it will install all the git-hooks fir your local repository.

    You can use them to add checks during commit, merge, etc…

    Edit: I read a bit too fast. As you are using bitbucket there id probably the equivalent of github’s CODEOWNER file as already proposed in another comment.



  • nix does not need nixOS to run but is a complex package manager. At least for me, it doesn’t seem more complex than docker ecosystem.

    I personally use nix to take care of downloading compatible dependencies in isolation for me. And the rest of the code is really, just basic script shell or Makefile too.

    I also could add a fancy mergeShells function I have written in nix to support a docker-compose-like composition of nix-shell files. But you could go a very long way with nix before you even want to do something like this.