Hacker News new | past | comments | ask | show | jobs | submit | brandonchen's comments login

Proud to have helped edit an earlier draft of this — go Dexter go!


Thanks! Yup, so long as you don't have key bindings for meta-x and meta-c, you ought to be good in the terminal. We honor any repository's .gitignore and won't touch those files. We don't even let Codebuff know they exist, which has caused some issues with hallucinations in the past.

Making sure that our word is trustworthy to the broader world at large is going to be a big challenge for us. Do you have any ideas for what we can do? We're starting to think about open source, but we aren't quite ready for that yet.


It seems like we're all in our own tech bubbles more and more. Distribution is clearly a tough problem to crack, and no one in this space has really mastered it yet, aside from arguably Github Copilot.

No comment on YC here, but I think it's easy to criticize from the outside. I've personally have been impressed by all the peers, group partners, and alumni I've met so far. I'm biased, but I think YC knows what it's doing. Also, YC backs founders, not ideas.


Thanks! That's awesome to hear – if you wouldn't mind me asking, what was the context and tech stack of your side project? We love hearing about the wide variety of use cases people have found for Codebuff!


It's a pretty small, straight forward web app. Think: python backend and a vanilla html / JS frontend, served over flask. The frontend is mostly in one file, so maybe it's not the best test case for crossfile reading, but still very happy with the user experience!


I assume you're referring to it guessing at what command you might type next? If so, the closest I can think of is Warp. Have you tried it?


Good question – here are a few reasons:

- It chooses files to read automatically on each message — unlike Cursor’s composer feature. It also reads a lot more than Cursor's @codebase command. - It takes 0 clicks — Codebuff just edits your files directly (you can always peek at the git diffs to see what it’s doing). - It has full access to your existing tools, scripts, and packages — Codebuff can install packages, run terminal commands and tests, etc. - It is portable to any development environment

We use OpenAI and Anthropic, so unfortunately we have to abide by their policies. But we only grab snippets of your code at any given point, so your codebase isn't seen by any entity in its entirety. We're also considering open-sourcing, so that might be a stronger privacy guarantee.

I should note that my cofounder James uses both and gets plenty of value by combining them. Myself, I'm more of a plain VSCode guy (Zed-curious, I'll admit). But because Codebuff lives in your terminal, it fits in anywhere you need.

No comment on our batchmates


Alright. That gives me some directional signal. I will be interested if you make it open source. We have massive and critical code base so I am always wary of giving access to 3Ps.


brace yourself.

the night critics are coming.


Don't take it personally or get too discouraged. You are not your product, and you're certainly not your first demo of your first product. But, knowing your competition, how you stack up against them, and how the people you're selling to feel about them, is a huge part of your job as a founder. It will only get more important.

You have to constantly do your research. It is one of those anxiety-inducing tasks that's easy to justify avoiding when all you want to do is code your idea up and there's so much other work to do. But it's your job. Even when you hire someone else to run product for you it'll be your responsibility to own it.

What you've built is cool, a lot of people love it even though they know about the other tools available. Now you know what your main competition does, you also know what it doesn't do, so you get to solve for that - and if you solved the context problem in isolation with treesitter then you're obviously capable.

You'll have realised by now that Aider didn't use treesitter when it started. Instead it used ctags - a pattern-matching approach to code indexing from 40 years ago that doesn't capture signatures or create an ast, it effectively just indexes the code with a bunch of regex. And it's not like treesitter wasn't around when aider was first written. Keep that in mind.

Good luck.


> The sexy demos don't, in my opinion and experience, win over the engineers and leaders you need.

Great point, we're in talks with a company and this exact issue came up. An engineer used Codebuff over a weekend to build a demo app, but the CEO wasn't particularly interested even after he enthusiastically explained what he made. It was only when the engineer later used Codebuff to connect the demo app to their systems that the CEO saw the potential. Figuring out how to help these two stakeholders align with one another will be a key challenge for us as we grow. Thanks for the thought!


Tongue-in-cheek! No idea what you're talking about. But I appreciate the kind words :)

Ultimately, I think a future where the limit to good software is good ideas and agency to realize them, as opposed to engineering black boxes, mucking with mysterious runtime errors, holy wars on coding styles, etc. is where all the builders in this space are striving towards. We just want to see that happen sooner than later!


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?


Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: