• 3 Posts
  • 122 Comments
Joined 3 years ago
cake
Cake day: March 15th, 2023

help-circle





  • If I am the tankie you must be the lgbtq femboy. There’s nothing wrong with it. We are here for different reasons :D.

    Stereotypes aside, aren’t you using one?

    • Image processing, (e.g.: Camera enhancement, gimp, rawtherapee are full with AIs)
    • sound processing, (noise reduction, etc…)
    • text processing
      • reasoning models for programming, math
      • LLMs for grammar checking / searching when I don’t know the keyword / researching when I’m not interested that much about the topic, but I want multiple sources / getting common knowledge I don’t know yet.
    • Recently I tried 3D asset generation. Damn it gave me a perfect character model. But it’s not for work so I’m not gonna pay for it.
    • etc…

    They are useful.



  • I had heavy problems to solve. Claude Opus could solve some. I could solve them too, but with claude it’s faster. One recent problem would take around two days if I would do it, but claude did it in half an hour.

    I’m not advertising claude, if it gives bullshit response I turn it off instantly. Like with every tool, you need to learn to use it.

    Another example: In the app I work on, there’s a huge list of city integration files. I had a loose set of specifications for a new city, and with claude I could roll out a new prototype in no time. It saved me about a month of work.

    It’s expensive and energy hungry for sure.



  • I use prisma ORM with kysely Query Builder. Prisma has its own schema language that we write with great IDE support and provides a parser to generate type-safe clients. It gives you the ts client generator by default. But for example, kysely also needs types and somebody wrote a prisma-kysely generator, which generates types for kysely based on the prisma schema. Prisma since then also have Typed SQL (type-safe raw sql). (Although, I haven’t tried that yet.) So prisma can cover that missing 9% of cases, and there maybe 1% left for untyped raw sql.

    Do you think Lutra can replace that 9+1% of cases? Or would it be also useful to write migrations in Lutra?









  • I used claude code to migrate a small rust project from raw sql to an ORM. It was next level. In a timespan of a small bug fix I could rewrite the data model. It tested the code, it fixed the errors, I was amazed. I reviewed every change, so I could spot problems like migration would fail with prod data. I wrote a new prompt to fix that and it fixed.

    For anybody new to claude code: It’s a tui app where you can log in and write prompts for the project in the current directory. The way it works, it searches files in the project based on the prompt, and it locates the related code sections. So it gathers the context pretty well. It can suggest changes, it can suggest running CLI commands, it can read its output. It reacts to itself. You can accept or intercept and correct it anytime.

    I ran it in docker just in case.

    In summary, this is a real deal, but of course the code needs to be reviewed. Sometimes, it produces, simply put, unmaintainable code, that shouldn’t be used. Works or not, it should move.