Live data from Hacker News

Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

news.ycombinator.com

131–140 of 248 posts

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#131
post #97

We already have AIDE, Continue, Cody , Aider, Cursor.. Why this?

Codebuff is the easiest to use of all these, because you just chat, and it finds all the right files to edit. There's no clicking and you don't have to confirm edits. It is also a true agent. It can run terminal commands to aid the request. For one request it could: 1. Write a unit test 2. Run the test 3. Edit code to fix the error 4. Run it again and see it pass If you try out Codebuff, I think you'll see why it's u…

Can codebuff handle larger files (6,000 loc) and find the right classes/functions in that code, or if it finds the file with the necessary info does it load the entire file in?

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#132

Earlier quoted context omitted.

> We build a description of the codebase including the file tree and parsed function names and class names This sounds like RAG and also that you’re building an index? Did you just mean that you’re not using vector search over embeddings for the retrieval part, or have I missed something fundamental here?

Ah yeah, that's what I mean! I thought RAG is synonymous with this vector search approach. Either way, we do the search step a little different and it works well.

I didn't mean to be down on it, and I'm really glad it's working well! If you start to reach the limits of what you can achieve with your current approach, there are lots of cute tricks you can steal from RAG, eg nothing stopping you doing a fuzzy keyword search for interesting-looking identifiers on larger codebases rather than giving the LLM the whole thing in-prompt, for example

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#133
It couldn't write a simple test for my typescript node system. Kept telling me credits left, login. I don't know who gets success from these tools and what they are building but none of them actually work for me. Yesterday there was Aide which I tried and found to be broken and so is this one.

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#134

Congrats on the launch! I tried this on a migration project I'm working on (which involves a lot of rote refactoring) and it worked very well. I think you've nailed the ergonomics for terminal-based operations on the codebase. I've been using Zed editor as my primary workhorse, and I can see codebuff as a helper CLI when I need to work. I'm not sure if a CLI-only interface outside my editor is the right UX for me to…

Amazing, glad it worked well for you! I main VSCode but tried Zed in my demo video and loved the smoothness of it.

Totally understand where you're coming from, I personally use it in a terminal tab (amongst many) in any IDE I'm using. But I've been surprised to see how different many developers' workflows are from one another. Some people use it in a dedicated terminal window, others have a vim-based setup, etc.

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#135

It couldn't write a simple test for my typescript node system. Kept telling me credits left, login. I don't know who gets success from these tools and what they are building but none of them actually work for me. Yesterday there was Aide which I tried and found to be broken and so is this one.

That's surprising to me, usually it works quite well at this. Did you start codebuff in the root of your project so that it can get context on your codebase?

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#136

Congratulations on your launch! But I confess that I am really confused. This sounds exactly like Aider, but closed source and it's locked into a single LLM API? I just watched you use it, and looks a lot like Aider too? Why would I use this over Aider? I've seen people say "you don't have to add files to Codebuff", but Aider tells me when the LLM has requested to see files. I just have to approve it. If that bothers…

It sounds minor that it finds files for you, but if you try it out, you'll see that it's a giant leap in UX and the extra files help it generate better code because it has more examples from your codebase.

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#137
post #71

Earlier quoted context omitted.

Ah, but in Cursor you (mostly) have to manually choose files to edit and then approve all the changes. With Codebuff, you just chat from the terminal. After trying it, I think you might not want to go back to Cursor haha.

That sounds cool and I like the idea, but definitely won't pay 5x. Maybe charge $30/month plus bring your own key. Let me know when you lower the price :)

https://aider.chat/

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#138
Sounds pretty interesting, I was thinking that would be the way to work past limited context window sizes automatically.

> Codebuff has limited free usage, but if you like it you can pay $99/mo to get more credits...

> One user racked up a $500 bill...

Those two statements are kind of confusing together. Past the free tier, what does $99/month get you? It sounds like there's some sort of credit, but that's not discussed at all here. How much did this customer do to get to that kind of bill? I get that they built a flutter app, but did it take a hour to run up a $500 bill? 6 hours? a whole weekend? Is there a way to set a limit?

The ability to rack up an unreasonable bill by accident, even just conceptually, is a non-starter for many. This is interactive so it's not as bad as accidentally leaving a GPU EC2 instance on overnight, but I'll note that Aider shows per query and session costs.

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#139
post #24

The demos I see for these types of tools are always some toy project and doesn't reflect day to day work I do at all. Do you have any example PRs on larger more complex projects that have been written with codebuff and how much of that was human interactive? The real problem I want someone to solve is helping me with the real niche/challenging portion of a PR, ex: new tiptap extension that can do notebook code eval,…

Great question – we struggled for a long time to put our demo together precisely for this reason. Codebuff is so useful in a practical setting, but we can't bore the audience with a ton of background on a codebase when we do demos, so we have to pick a toy project. Maybe in the future, we could start our demo with a half-built project? Hopefully the demo on our homepage shows a little bit more of your day-to-day work…

If you're not worried about showing off little hints of your own codebase, record running it on one of your day to day engineering tasks. It's perfect dog fooding and would be a fun meta example.

> To give a concrete example of usefulness, I was implementing a referrals feature in Drizzle a few weeks ago, and Codebuff was able to build out the cli app, frontend, backend, and set up db schema

Record this!

Better yet, stream it on Twitch and/or YouTube and/or Discord and build a small community of followers.

People would love to watch you.

Re: Launch HN: Codebuff (YC F24) – CLI tool that writes code for you

#140
post #24

The demos I see for these types of tools are always some toy project and doesn't reflect day to day work I do at all. Do you have any example PRs on larger more complex projects that have been written with codebuff and how much of that was human interactive? The real problem I want someone to solve is helping me with the real niche/challenging portion of a PR, ex: new tiptap extension that can do notebook code eval,…

Great question – we struggled for a long time to put our demo together precisely for this reason. Codebuff is so useful in a practical setting, but we can't bore the audience with a ton of background on a codebase when we do demos, so we have to pick a toy project. Maybe in the future, we could start our demo with a half-built project? Hopefully the demo on our homepage shows a little bit more of your day-to-day work…

Why not take a large and complex code-base such as the firefox source code, feed that in and demonstrate how that goes?
Post reply on HN