[nicodjimenez]

I tend to agree with this. These days I usually use LLMs to learn about something new or to help me generate client code for common APIs (especially boto3 these days). I tried Windsurf to help me make basic changes to my docker compose files, but when it couldn't even do that correctly, I lost a little enthusiasm. I'm sure it can build a working prototype of a small web app but that's not enough for me.

For me LLMs are a game changer for devops (API knowledge is way less important now that it's even been) but I'm still doing copy pasting from ChatGPT, however primitive it may seem.

Fundamentally I don't think it's a good idea to outsource your thinking to a bot unless it's truly better than you at long term decision making. If you're still the decision maker, then you probably want to make the final call as to what the interfaces should look like. I've definitely had good experiences carefully defining object oriented interfaces (eg for interfacing with AWS) and having LLMs fill in the implementation details but I'm not sure that's "vibe coding" per se.

[pizzathyme]

I had a similar experience as the author. I've found found that cursor / copilot are FANTASTIC at "smart autocomplete", or "write a (small function that does this)" and quick viral prototypes.

But after I got a week into my LLM-led code base, it became clear it was all spaghetti code and progress ground to a halt.

This article is a perfect snapshot of the state of the art. It might improve in the future, but this is where it is in May 2025.