• 0 Posts
  • 27 Comments
Joined 8 days ago
cake
Cake day: July 20th, 2025

help-circle













  • Totally disagree. Your position is way too overly simplistic and naive.

    An engineer only builds a bridge as strong as it needs to be, and likewise I “vibe code” things based on how few fucks I need to give.

    I’m experienced and can review the output for sanity and completion. I can test it, I can rewrite it, etc.

    Stop looking at vibe coding as doing the whole thing, it’s more valuable as the glue between things, or to create scripts tools that make you more efficient.

    And you can vibe code entire apps that basically just work these days. You probably don’t want to maintain those apps but thats a question of lifecycle planning.

    It is so much faster to vibe code an API integration and a suite of tests than I can write. It’s faster to write a functional jq or bash script.

    But it’s also much much much worse at doing data viz or writing pandas code because it’s trained on 10,000 shitty medium blogs.

    You really have to know what you’re doing and what the model is doing, but it is not universally trash.

    And if you don’t believe me, put $20 into the Claude API and install Claude Code and ask it to build something.



  • I don’t know rust, but for example in Swift the type system can make things way more difficult.

    Before they added macros if you wanted to write ORM code on a SQL database it was brutal, and if you need to go into raw buffers it’s generally easier to just write C/objc code and a bridging header. The type system can make it harder to reason about performance too because you lose some visibility in what actually gets compiled.

    The Swift type system has improved, but I’ve spent a lot of time fighting with it. I just try to avoid generics and type erasure now.

    I’ve had similar experiences with Java and Scala.

    That’s what I mean about it being nice to drop out of setting up some type hierarchy and interfaces and just working with a raw buffers or function pointers.


  • I actually do like that C/C++ let you do this stuff.

    Sometimes it’s nice to acknowledge that I’m writing software for a computer and it’s all just bytes. Sometimes I don’t really want to wrestle with the ivory tower of abstract type theory mixed with vague compiler errors, I just want to allocate a block of memory and apply a minimal set rules on top.




  • Batch process turning unstructured free form text data into structured outputs.

    As a crappy example imagine if you wanted to download metadata about your albums but they’re all labelled “Various Artists”. You can use an LLM call to read the album description and fix the track artists for the tracks, now you can properly organize your collection.

    I’m using the same idea, different domain and a complex set of inputs.

    It can be much more cost effective than manually spending days tagging data and writing custom importers.

    You can definitely go lighter than LLMs. You can use gensim to do category matching, you can use sentence transformers and nearest neighbours (this is basically what Semantle does), but LLM performed the best on more complex document input.