Hacker News Reader

Comment by 999900000999 | Hacker News Reader

I really would prefer them to start creating customized models.

I've vibe coded Godot games extensively.

Just about every model I've tried likes to invent imaginary functions.

I was really prefer for there to be a way for me to pick model trained in whatever framework I need.

Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then ask the AI to fix its book, and it will just add more AI generated words.

On one hand I want this to be a reality check to everyone who's trying to lay off real software engineers to replace us with AI.

On the other hand half of the stock market is held up by overhyped AI valuations. If the tide goes out too fast, and there is a mass realization that this stuff just isn't as good as it's hyped to be, it's not going to be fun for anyone.

View on HN

I had this problem 2 years ago. All the models were telling me use libraries that hadn't been invented yet.

That was annoying back then, but these days that's not so much of a problem.

You can write your program and then simply have it invent the library as well, while it's at it! ;)

These days not so much of a problem because the libraries now exist? Haha

mostly because of slop-squatting i’d imagine…

It's still very much a problem.

For one hilarious example, Gemini (2.5; I haven't tried it with 3 yet) only knows about the old Google API for Gemini, not about the new one. So if you give it code written against the new stuff, it will often do things like, "this is definitely wrong, I know this API doesn't have this method, let me fix that".

I find Gemini 3 (and Claude 4.5) also only seem to know about the 2024 era of LLMs and will often just randomly rewrite calls to GPT5 to GPT4o, or Claude 4.5 to Claude 3.5 if it happens to find them in a file, regardless of whether I told it to do anything about that or not.

How well has your vibecoding with Godot worked? I thought about it but wouldn't the LLM be unable to add files by itself due to stuff only the Godot editor knows how to do like generating uid files and so on? I would have expected that the LLM needs a MCP or some tool calling to properly interact with a Godot project. How are you doing it?

For Unity, claude is capable of creating .meta files and editing .unity scenes, at least until they get really large

It works really really well!

I can have it do changes via a Copilot Pull Request on GitHub and deploy it straight to itch without me touching the code.

I’m using Web builds.

The only thing that’s weird is I literally got screenshots from to work on the PRs once or twice and then it stopped working.

Add the documentation to the context window in that case, a bit of context engineering.

I’ve found writing a MCP server with access to the docs cloned locally does wonders.

I don't know context is still an issue if you have lots of docs in my experience.

If you use cursor you can just attach the documentation. Same thing, different method.

Just add godot example games nearby and it will learn functions / usecase from them. Just say in instructions BTW you have example games in "examples" directory to check

You can also use "repomix" tool to bundle whole source of godot into single file and tell it to search it when uncertain

Why use an extra tool, when you can tell the LLM where the Godot source is to be found in case it wants to investigate some details? What is the benefit of using repomix?

Context7 might be good for you

Definetly! I put in the instructions.md file to check if the code is well conform to the latest doc using Context7, works quite well!

Just curious, wouldn't it be easier to download the docs in a format that is searchable for the LLM? A MCP for this seems overkill to me.

It's just convenience really. Context7 takes care of keeping _all_ the documentation available and provides a search function.

You can definitely have it locally or even build a RAG/MCP -thing just for the specific docs you want.

Reply on news.ycombinator.com