3 comments

  • skeptrune 7 hours ago ago

    They don't work well at all for us.

    We have a relatively large Rust codebase and I would describe the LLM's as actively harmful at making agentic-style, self-piloted changes.

    Very pointed context management with split screens and explicit inclusion of relevant files in the context is sometimes useful though.

    My biggest gripe is that AI can't just generate a new SQL migration and CRUD routes for an additional resource we want to add without issue. I always have to punt and end up doing it myself.

    • prasoonds 6 hours ago ago

      I've heard Rust is especially hard for LLMs, what with the need to thinking deeply about variable ownership and lifetimes. I wonder if it will work better if you try o1-mini (as long as you're still providing the right context!)

      And I would've thought that AI would be good at creating new routes (wrap this function in a POST route) - certainly I've done this with Python and TS and it's been fine. Maybe it's a Rust specific issue? Likewise, SQL migrations I would've expected to also just work, especially if your schema change is small! Interesting that it doesn't!

      Which tool do you use? Cursor or something else?

  • prasoonds 7 hours ago ago

    Also to add some more context:

    - I've found LLM codegen working very well with standard React + TS code

    - It sucks when using less knows languages or less popular frameworks (I tried reverse engineering github copilot lua code from the neovim extension in one instance and it really didn't work well)

    I'd be curious to hear people's experience here.