[djaychela]

Can someone offer me some help? I've just been messing about "vibe coding" little python apps with local llm, continue and vscode. And I got so far with it.

Then I found the free tier of claude so I fed in the "works so far" version with the changes that the local llm made, and it fixed and updated all the issues (with clear explanation) in one go. Success!

So my next level attempt was to get all the spec and prompts for a new project (a simple manic miner style 2d game using pygame). 8 used chat gpt to craft all this and it looked sensible to me with appropriate constraints for different parts of the projrct.

Which claude created. But it keeps referring to a method which it says is not present in the code and that I'm running the wrong version. (I'm definitely not). I've tried indicating it by reference to the line number and the surrounding code but it's just gas lighting me.

Any ideas how to progress from this? I'm not expecting perfection, but it seems it's just taken me to a higher level before it runs into essentially the same issue as the local llm.

All advice appreciated, I'm just dabbling with this four a bit of fun when I can (I'm pretty unwell so do things as and when I feel up to it)

Thanks in advance.

[postalcoder]

It's likely you're running into "too deep into mediocre code with unclear interfaces and a lot of hidden assumptions hell" that LLMs are generally poor at handling. If you're running into an inextricable wall then it's better to do a controlled demolition.

ie, take everything written by chatgpt and have the highest-quality model you have summarize what the game does, and break down all the features in depth.

Then, take that document and feed it into claude. It may take a few iterations but the code you get will be much better than your attempt on iterating on the existing code.

Claude will likely zero-shot a better application or, at least, one that it can improve on itself.

If claude still insists on making up new features then install the context7 MCP server and ask it to use context7 when working on your request.

[djaychela]

Thanks.

I think I should have made it more clear in my post, the code is claude's and was done from scratch (the first app was a mandelbrot viewer which it added features to, this is a platfrom game).

It's a single file at the moment (I did give a suggested project structure with files for each area of responsibility) and it kind-of-works.

I think I could create the missing method in the class but wanted to see if it was possible by getting the tools to do it - it's as much of an experiment in the process and the end result.

Thanks for replying, I shall investigate what you've suggested and see what happens.

[otabdeveloper4]

> Any ideas how to progress from this?

You can't. This is a limitation of LLM technology. They can output the most likely token sequence, but if "likely" doesn't match "correct" for your problem then there's nothing you can do.

Also, each LLM has its own definition of what "likely" is - it comes from the training and finetuning secret sauce of that particular LLM.