Live data from Hacker News

Show HN: Transform your codebase into a single Markdown doc for feeding into AI

tesserato.web.app

161–170 of 172 posts

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#163

CodeWeavers is a software company that focuses on Wine development and sells a proprietary version of Wine called CrossOver for running Windows applications on macOS, ChromeOS and Linux. https://en.wikipedia.org/wiki/CodeWeavers Trademark is active. It's an Ⓡ not just a ™, registered not just trademarked. To keep it, they have to demonstrate they defend it. https://www.trademarkia.com/codeweavers-76546826 While this…

Yeah, I was thinking "what does the Wine guys have to do with this?" This project is definitely going to get C&D'd.

Do you think they would actually litigate? They seem like different products serving entirely different markets so I am not sure that the trademark infringement claim is very defensible. And how do they prove damages?

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#164

This kind of context is really useful for LLMs, but in any significant project, including all code in this manner will easily exceed context limitations. I've been wanting to do something like this for my php projects, but instead of dumping the entire files, would just create a map of its methods signatures, variables, etc. That should give good enough information of what each file is used for and can do, while bein…

> including all code in this manner will easily exceed context limitations The context window for Gemini 2.0 Flash can handle roughly 50000 lines of code, and 2.0 Pro can handle twice that.

that goes faster than you think. Also, diminishing attention/memory of facts in context also goes down together with its length. Which might hurt when you just want to dump everything at once.

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#165

Earlier quoted context omitted.

I guess this only works for very small codebase?

Correct, but it's the same as what OP shared. You should use Aider/Cursor for proper indexing/intelligent codebase referencing

Cramming thousands of tokens of potentially irrelevant context through unclear indexing paths isn't "proper".

The best results come from feeding precisely targeted context directly into the prompt, where you know exactly what the model sees and how it processes it. The prompt receives the most accurate use of attention—whereas god knows what the pipeline is for cursor or what extra layers and context restrictions they add on top of base Claude.

Giving the model a clean project hierarchy accomplishes a lot efficiently in terms of context tokens. The key is ensuring it only sees what's relevant, without diluting its attention.

Tools like reopmix and OP's version, feeding targeted context straight into models like Claude or Google's offerings, outperform Copilot and Cursor in my experience, even though they use the same base models. Use the highest-quality attention (the prompt context) directly, rather than layers of uncertainty and "proper indexing".

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#166

CodeWeavers is a software company that focuses on Wine development and sells a proprietary version of Wine called CrossOver for running Windows applications on macOS, ChromeOS and Linux. https://en.wikipedia.org/wiki/CodeWeavers Trademark is active. It's an Ⓡ not just a ™, registered not just trademarked. To keep it, they have to demonstrate they defend it. https://www.trademarkia.com/codeweavers-76546826 While this…

CodeLoom could work instead

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#167

Such a functionality would be useful for developing some scripts and then converting to a Quarto document [1]. [1] https://quarto.org/

I've never used Quarto, but I might give it a go someday. I currently have a convoluted workflow for generating math-heavy documents that involves generating equations using SymPy in a notebook, accumulating them in a string, and ultimately dumping the string into a Markdown. I would love to simplify this sooner rather than later. I'm also keeping an eye on https://typst.app/ and hoping for a sane alternative to LaTeX to emerge.

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#170
post #123

Earlier quoted context omitted.

I'm still puzzled how come people are convinced by Cursor, while my experience was meh at best. Can it index your stuff? okay it can. Can it refactor a simple function? No it cannot, it can't even rename a damn Java class. How can I trust it to generate then code based on my codebase? So, what is your use case then? Or can anybody point me to some blog/articles/videos showing some real use cases for Cursor? Real as i…

I think you know the correct answer:)

I hoped to be wrong but no comment so far even tried to bring a based argument... eh, maybe I'll try again in a year.
Post reply on HN