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

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

news.ycombinator.com

Post reply on HN
Print view View original

141–150 of 248 posts

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

#141

Post by jahooma »

carom wrote: post #126

How do you end up handling line numbers in patches? Counting has always been a sticking point for LLMs.

I wrote a custom `applyPatch` function that tries to use the line numbers, but falls back to searching for the context lines to line up the +/- patched lines.

It actually got line number not too wrong, and so they might have been helpful. (I included the line numbers for the original file in context).

Ultimately though, this approach was still error prone enough that we recently switched away.

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

#142

Post by ilrwbwrkhv »

jahooma wrote: post #135
ilrwbwrkhv wrote: post #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.

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?

Yup I did.

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

#143

Post by fullstackwife »

v3ss0n wrote: post #97

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

one size does not fit them all, and such tools are quite straightforward to develop. I even created one myself: https://npmjs.com/genaicode, I started with CLI tool, but eventually learned that such UX is not good (even interactive CLI), and I created a web UI.

where the problems start: cost of inference vs quality, latency, multi modality (vision + imagen), ai service provider issues (morning hours in US time zones = poor quality results)

the best part is being able to adjust it to my work style

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

#144

Post by jahooma »

iandanforth wrote: post #103

Does this send code via your servers? If so, why? Nothing you've described couldn't be better implemented as a local service. Could this tool get a command from the LLM which would result in file-loss? How would you prevent that?

Good question! There's a couple reasons.

One is that I think it is simpler for the end user to not have to add their own keys. It allows them to start for free and is less friction overall.

Another reason is that it allows us to use whichever models we think are best. Right now we just use Anthropic and OpenAI, but we are in talks with another startup to use their rewriting model. Previously, we have used our own fine-tuned model for one step, and that would be hard to do with just API keys.

The last reason that might be unpopular is that keeping it closed source and not allowing you to bring your keys means we can charge more money. Charging money for your product is good because then we can invest more energy and effort to make it even better. This is actually beneficial to you, the end user, because we can invest in making the product good. Capitalism works, cheers.

Per your last question, I do advise you use git so that you can always revert to return to your old file state! Codebuff does have a native "undo" command as well.

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

#145

Post by bambax »

haxton wrote: 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,…

Every experience I have had with LLMs generating code. LLMs tend to follow the prompt much too closely and produce large amounts of convoluted code that in the end prove not only unnecessary but quite toxic.

Where LLMs shine is in being a personal Stack Overflow: asking a question and having a personalized, specific answer immediately, that uses one's data.

But solving actual, real problems still seem out of reach. And letting them touch my files sound crazy.

(And yes, ok, maybe I just suck at prompting. But I would need detailed examples to be convinced this approach can work.)

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

#148

Post by robertlagrant »

Retr0id wrote: post #110
israrkhan wrote: post #92

Earlier quoted context omitted.

I am not afraid of rm -rf whole directory. I am afraid of other stuff that it can do to my machines. leak my ssh keys, cookies, persnal data, network devices, and making persistent modifications (malware) to my system. Or maybe inadvertently messing with my python version, or globally installing some library to mess up whole system.

I, as a well-intending human, have run commands that broke my local python install. At least I was vaguely aware of what I did, and was able to fix things. If I didn't know what had happened I'd be pretty lost.

You'd hope that most of it is just rm -rf .venv && poetry install, or similar.

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

#149

Post by brandonchen »

fragmede wrote: post #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 discus…

Ah, good catch. We (read: I) introduced a bug that gave customers $500 worth of credits in a month as opposed to the $100 they paid for, and this user saw that and took advantage. Needless to say, we fixed the issue and added more copy to show to users when they _do_ exceed their thresholds. We haven't had that issue since. And of course, we ate the cost because it was our (expensive!) mistake.

The user had spent the entire weekend developing the app, and admitted that he would have been more careful to manage his Codebuff usage had it not been for this bug.

We're open to adding hard limits to accounts, so you're never charged beyond the credits you paid for. We just wanted to make sure people could pay a bit more to get to a good stopping point once they passed their limits.

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

#150

Post by nisten »

I'm not paying $20 for my ssh keys and rest of the clipboard to be sent to multiple unknown 3rd parties, thanks, not for me.

Would however pay for actual software that I can just buy instead of rent to do the task of inline shell assitance, without making network calls behind my back that i'm not in complete perfectionist one hundred point zero zero per cent control of.

Sorry just my opinion in general with these types of products. If you don't have the skills to make a fully self contained language model type of product or something do this then you are not skilled enough team for me to trust with my work shell.

Post reply on HN