Live data from Hacker News

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

news.ycombinator.com

181–190 of 248 posts

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

#181
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,…

Absolutely! Imaging setting a bunch of css styles through a long winded AI conversation, when you could have an IDE to do it in a few seconds. I don't need that. The long tail of niche engineering problems is the time consuming bit now. That's not being solved at all, IMHO.

Which IDE do you use for CSS editing/adjustment?

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

#182

Does anyone know of a “copilot” style autocomplete in the CLI? I don’t want it to run anything for me, just predict what command I might type next

I'm currently hacking together a prototype of such a tool. The problem I noticed is that in CLI, commands are way less predictable than lines in code files, so such a tool will probably have a pretty low correct completion rate. However, there are clearly cases where it could be very helpful.

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

#184
Have an upvote! I've been trying it out, it's quite nice. What I like about this vs CoPilot and Cursor is that I feel like (especially with CoPilot) I'm always "racing" the editor. Also Cursor conflicts with some longstanding keybindings I have, vs this which is just the terminal. Having worked on a similar system before, I know it's difficult to implement some of these things, but I am concerned about security. For instance, how well does it handle sensitive files like dot.env or gitignored files. At some point an audit, given that you're closed source would go a long way.

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

#186
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,…

> 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?

We have a lot of code in production which are AI written. The important thing is that you need to consciously make a module or project AI-ready. This means that things like modularity and smaller files are even more important than they usually are.

I can't share those PRs, but projects on my profile page are almost entirely AI written (except the https://bashojs.org/ link). Some of them might meet your definition of niche based on the example you provided.

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

#187

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…

I don't think you're missing anything.

Aider tends to maintain near "state of the art" including e.g. treesitter, and an actually refined (as in, iterated improvements over time) user experience.

Aider has been refining for 8000 commits since May of 2023. Codebuff "all started" circa Claude Sonnet 3.5.

The story of discovery (e.g. git patch) at best feels like a lack of researching the landscape since leaderboards for SOTA indicate whether a model performs better as whole code or diffs and Anthropic even cites Aider benchmarks, but cynically, the narrative feels a bit like looking through the things Aider has been doing differently/better, and putting them in an origin story so the feature list might sound less like the “sincerest form of flattery.”

Particularly concerning is the story talking about "seeing" users coding loops. Perhaps this is a figure of speech. As designed, Codebuff are in the middle of all users' code slinging, so perhaps it isn't.

Checking the Privacy Policy shows it's only about cookies and tracking, not about information privacy or IP protection of any kind.

Checking the Terms of Service says they own any code you post through it and can give it to others:

"However, by posting Content using Service you grant us the right and license to use, modify, publicly perform, publicly display, reproduce, and distribute such Content on and through Service. You agree that this license includes the right for us to make your Content available to other users of Service."

Meaning, the TOS is a for a public social media type service, not for an intellectual property service.

(Note that in VSCode "cline" can give Aider a run for its money.)

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

#188

Earlier quoted context omitted.

first time?

Heh, this is an underrated comment. Fundamentally, I think codegen a pretty new space and lots of people are jumping in because they see the promise. Remains to be seen what the consolidation looks like. With the rate of advancement in LLMs and codegen in particular, I wouldn't be surprised to see even more tools than we do now...

And they all converging towards one use case, and targeting one consumer base. It's still unclear for consumers, at least based on this thread what differetiate them.

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

#189

Congrats on the launch guys! Tried the product early on and it’s clearly improved a ton. I’m still using Cursor every day mainly because of how complete the feature set is - autocomplete, command K, highlight a function and ask questions about it, and command L / command shift L. I am not sure what it’ll take for me to switch - maybe I’m not an ideal user somehow… I’m working in a relatively simple codebase with few…

Sweet. Personally, I use both Cursor and Codebuff.

I open the terminal panel at the bottom of the Cursor window, start up `codebuff`, and voila, I have an upgraded version of Cursor Compose!

Depending on what exactly I'm implementing I rely more on codebuff or do more manual coding in Cursor. For manual coding, I mostly just use the tab autocomplete. That's their best feature IMO.

But codebuff is very useful for starting features out if I brain dump what I want and then go fix it up. Or, writing tests or scripts. Or refactoring. Or integrating a new api.

As codebuff has gotten better, I've found it useful in more cases. If I'm implementing a lot of web UI, I can nearly stop looking at the code altogether and just keep prompting it until it works.

Hopefully that gives you some idea of how you could use codebuff in your day-to-day development.

Post reply on HN