Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why Cline doesn't index your codebase

cline.bot

Post reply on HN
Print view View original

121–130 of 131 posts

Re: Why Cline doesn't index your codebase

#121

Post by atonse »

nlh wrote: post #110
atonse wrote: post #97

Earlier quoted context omitted.

What's the benefit? If you're paying $20/month for cursor you already get all the agentic coding as part of it.

Cursor changed their pricing recently and now charge a 20% markup on LLM API calls to use their "Max" models (which from what I gather are the full extent of the LLM context windows you get in the API anyway). I also don't love that Cursor generally plays "context compression" games since they have an incentive to keep their costs minimal. I just don't love any of these tools that try to be a bit too smart as a middl…

Everything you’re saying is valid for agentic coding.

But I’m also missing the regular Cursor Tab inline autocomplete when I’m coding, cuz I still often write code line by line like a caveman.

So what’s the cline alternative to it? Or am I thinking of this wrong?

Re: Why Cline doesn't index your codebase

#122

Post by atonse »

bradfox2 wrote: post #108
atonse wrote: post #49

Earlier quoted context omitted.

I've always wondered... Making agents edits (like vibe coding), all the tools I've tried (Cursor, Zed, VSCode) are pretty equal since most of the brains are in the underlying models themselves. But the killer app that keeps me using Cursor is Cursor Tab, which helps you WHILE you code. Whatever model they have for that works beautifully for me, whereas Zed's autocomplete model is the last thing that keeps me away fro…

Copilot

Has it improved lately? I used it for a year and until I switched to cursor, I felt the AI coding stuff was a complete sham, because copilot was essentially useless.

I’ll try it out.

Re: Why Cline doesn't index your codebase

#123

Post by nlh »

atonse wrote: post #121
nlh wrote: post #110

Earlier quoted context omitted.

Cursor changed their pricing recently and now charge a 20% markup on LLM API calls to use their "Max" models (which from what I gather are the full extent of the LLM context windows you get in the API anyway). I also don't love that Cursor generally plays "context compression" games since they have an incentive to keep their costs minimal. I just don't love any of these tools that try to be a bit too smart as a middl…

Everything you’re saying is valid for agentic coding. But I’m also missing the regular Cursor Tab inline autocomplete when I’m coding, cuz I still often write code line by line like a caveman. So what’s the cline alternative to it? Or am I thinking of this wrong?

Like a caveman! :)

I actually haven't explored the inline autocomplete space that much yet. I really like Cursor Tab (or Supermaven or even plain 'ol Copilot) -- they all seem really good. I'm sure there's a Cline equivalent out there, but I don't know what it is (yet).

Re: Why Cline doesn't index your codebase

#124

Post by noman-land »

dpe82 wrote: post #100
silverlake wrote: post #95

Have you guys at Cline considered using LLMs to create summaries of files and complex functions? Rather than read a 500 line function, feed it a short comment on what the function is doing. I'd like to use a local LLM to create summaries at every level: function, file, directory. Then let the LLM use that to find the right code to read. This is basically how I navigate a large code base.

I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.

So you're effectively keeping two copies of the codebase but the second copy is written in prose?

Re: Why Cline doesn't index your codebase

#125

Post by Bjartr »

noman-land wrote: post #124
dpe82 wrote: post #100

Earlier quoted context omitted.

I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.

So you're effectively keeping two copies of the codebase but the second copy is written in prose?

aka documentation

Re: Why Cline doesn't index your codebase

#126

Post by pdimitar »

kohlerm wrote: post #118
nick-baumann wrote: post #46

Earlier quoted context omitted.

Fair point Jeff -- you're right that we're still doing retrieval. The key distinction is how we retrieve. Traditional RAG for code uses vector embeddings and similarity search. We use filesystem traversal and AST parsing - following imports, tracing dependencies, reading files in logical order. It's retrieval guided by code structure rather than semantic similarity. I highly recommend checking out what the Claude Cod…

Following dependencies is the way to go IMHO. Saying "Code Doesn't Think in Chunks", is IMHO not correct. Developers do thing in chunks of codes. E.g. this function calls that function uses that type and is used here and there. It is not really a file based model like Cline uses. The file based model is "just" simpler to implement :-) . We use a more sophisticated code chunking approach in https://help.sap.com/docs/b…

Maybe you should indeed! Without looking into too much details, how CLI-friendly would this tool be?

Re: Why Cline doesn't index your codebase

#127

Post by dpe82 »

noman-land wrote: post #124
dpe82 wrote: post #100

Earlier quoted context omitted.

I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.

So you're effectively keeping two copies of the codebase but the second copy is written in prose?

It's basically an index.

Re: Why Cline doesn't index your codebase

#128

Post by zentara_code »

dpe82 wrote: post #100
silverlake wrote: post #95

Have you guys at Cline considered using LLMs to create summaries of files and complex functions? Rather than read a 500 line function, feed it a short comment on what the function is doing. I'd like to use a local LLM to create summaries at every level: function, file, directory. Then let the LLM use that to find the right code to read. This is basically how I navigate a large code base.

I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.

Would it double your codebase? Do you think it would work for a large codebase?

Re: Why Cline doesn't index your codebase

#129

Post by dpe82 »

zentara_code wrote: post #128
dpe82 wrote: post #100

Earlier quoted context omitted.

I've just used Cline to produce files like that, and then later when starting a task in plan mode I tell it to read those files to get a sense of the project's structure. I also tell it to update them as necessary after whatever task we're doing is finished.

Would it double your codebase? Do you think it would work for a large codebase?

Not anywhere close. It's basically just maintaining a simple descriptive index the model can later use to decide what files it needs to read given the task you've given it.

Re: Why Cline doesn't index your codebase

#130

Post by humpty-d »

consumer451 wrote: post #55
fkyoureadthedoc wrote: post #52

Earlier quoted context omitted.

GPT 4.1 / mini / nano

As the context grows, all LLMs appear to turn into idiots, even just at 32k! > We evaluate 12 popular LLMs that claim to support contexts of at least 128K tokens. While they perform well in short contexts ( https://news.ycombinator.com/item?id=44107536

[dead]
Post reply on HN