• 1 Post
  • 33 Comments
Joined 2 years ago
cake
Cake day: June 25th, 2023

help-circle
  • I didn’t see Claude 4 Sonnet in the tests and this is the one I use. And it looks like about the same category as o4 mini from my experience.

    It is a nice tool to have in my belt. But these LLM based agents are still very far from being able to do advanced and hard tasks. But to me it is probably more important to communicate and learn about the limitations about these tools to not lose tile instead of gaining it.

    In fact, I am not even sure they are good enough to be used to really generate production-ready code. But they are nice for pre-reviewing, building simple scripts that don’t need to be highly reliable, analyse a project, ask specific questions etc… The game changer for me was to use Clojure-MCP. Having a REPL at disposal really enhance the quality of most answers.


  • He looks from company money perspective. And I think AI is difficult to monetize. A google paper explained a long time ago that big company cannot easily have a huge competitive advantage because new techniques exists in the open source world to learn incrementally on top of costly models. Mainly you don’t need millions to make another good quality LLM.

    That being said. LLM add some value, but as everything hyped to no end the real value is negligible comparatively to the « market expected value ».




  • Moreover, codebase in pure funcional languages is hard to understand and maintain, that’s why they are rarely used in production.

    hahahah how to trigger a lot of people working with these pure functional languages (like me).

    I’ve worked with both “normal languages” like C++, java, Perl, javascript (node + UI), etc… and then I switched to Haskell and Clojure. And our current production code is a LOT better than in traditional languages. In particular, maintenance is a lot cheaper that what I was used to when working with more traditional languages.

    Regarding the community impact I would advise to use Clojure instead of Haskell (or Purescript, or Elm). Clojure is a nice middleground that has a huge advantage of being very stable (by that I mean, the code you write today will probably be very easy to deploy in 10, or 20 years from now).

    Note however, the language alone is not sufficient to write good code, but it helps you choose better abstractions that will be easier to maintain. If you dive into the spirit of the language, you will have a better intuition and understanding about state management of big applications and will probably make more visible some design issues.







    • can AI replace the job of a real programmer, or a team of software engineers? Probably not for a long time.
    • can manager abuse the fantasy that they could get rid of those pesky engineers that dare telling them something is impossible? Yes totally. If they believe adding an AI tool to a team justifies a 200% increase in productivity. Some managers will fire people against all metrics and evidence. Calling that move a success. Same occurred when they try to outsource code to cheaper teams.

  • 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.