alt Hacker NewsCongratulations 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 you, it's open source, so you could probably just add a config to always add files when requested.
Aider can also run commands for you.
What am I missing?
Replies
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.
I did find codebuff a lot easier to install and get started with...usability can make or break a project. Just as a user, I think it's nice to have multiple projects doing the same thing -- exploring more of the solution space.
(I've just played a little bit with aider and codebuff. I've previously tried aider and it always errored out on my code base, but inspired by this comment I tried again, and now it works well.)
Beyond what James highlighted, I personally really like how simple Codebuff is. CLI tools tend to go a bit overboard with options and configurations imo, which is ok if you're just setting them up once or twice. But for a tool I want to rely upon every day for my work, I want them to be as simple as possible, but no simpler.
Have you used Aider extensively? How are you finding it for your coding needs vs IDE-based chats?
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.)