← Back to context

Comment by shuraman7

8 hours ago

It's really hard to believe this isn't AI generated, but today I was trying to use the HTTP server from std after the 0.15 changes, couldn't figure out how it's supposed to work until I've searched repos in Github. LLM's couldn't figure it out as well, they were stuck in a loop of changing/breaking things even further until they arrived at the solution of using the deprecated way. so I guess this is actually handwritten which is amazing because it looks like the best resource I've seen up until now for Zig

14 comments

shuraman7

Reply
blks  7 hours ago

> It's really hard to believe this isn't AI generated

Case of a person who is relying on LLMs so much he cannot imagine doing something big by themselves.

  • shuraman7  7 hours ago

    it's not only the size - it was pushed all at once, anonymously, using text that highly resembles that of an AI. I still think that some of the text is AI generated. perhaps not the code, but the wording of the text just reeks of AI

    • trenchpilgrim  3 hours ago

      > it was pushed all at once

      For some of my projects I develop against my own private git server, then when I'm ready to go public, create a new git repo with a fully squashed history. My early commits are basically all `git commit -m "added stuff"`

tredre3  8 hours ago

I've had the same experience as you with Zig. I quite love the idea of it Zig but the undocumented churn is a bit much. I wish they had auto generated docs that reflect the current state of the stdlib, at least. Even if it just listed the signatures with no commentary.

I was trying to solve a simple problem but Google, the official docs, and LLMs were all out of date. I eventually found what I needed in Zig's commit history, where they casually renamed something without updating the docs. It's been renamed once more apparently, still not reflected in the docs :shrugs:.

  • Aeolun  36 minutes ago

    But you can tell your LLM to just go look at the source code (after checking it out so it doesn’t try 20s github requests). Always works like a charm for me.