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

Show HN: Vibe coding a bookshelf with Claude Code

balajmarius.com

Post reply on HN
Print view View original

141–150 of 221 posts

Re: Show HN: Vibe coding a bookshelf with Claude Code

#141

Post by rabf »

anthonypasq wrote: post #91
__MatrixMan__ wrote: post #54

Earlier quoted context omitted.

It seems like it's approaching a horizontal asymptote to me, or is at the very least concave down. You might be describing a state 50 years from now.

sonnet 3.7 was released 10 months ago! (the first model truly capable of any sort of reasonable agentic coding at all) and opus 4.5 exists today.

To add to this: the tooling or `harness` around the models has vastly improved as well. You can get far better results with older or smaller models today than you could 10 months ago.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#142

Post by zwnow »

MontyCarloHall wrote: post #78
zwnow wrote: post #74

Earlier quoted context omitted.

> Being able to not only look up but automatically integrate things into your codebase that already exist in some form in the training data is incredibly useful. Until it decides to include code it gathered from a stackoverflow post 15 years ago probably introducing security related issues or makes up libraries on the go or even worse, tries to make u install libs that were part of a data poisoning attack.

It's no different from supervising a naïve junior engineer who also copy/pastes from 15 year old SO posts (a tale as old as time): you need to carefully review and actually grok the code the junior/AI writes. Sometimes this ends up taking longer than writing it yourself, sometimes it doesn't. As with all decisions in delegating work, the trick is knowing ahead of time whether this will be the case.

I have yet to see a junior trying to install random/non existing libs.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#143

Post by pigpop »

anon7000 wrote: post #67
spzb wrote: post #56

I am yet to see a vibe coded success that isn't a small program that already exists in multiple forms in the training data. Let's see something ground-breaking. If AI coding is so great and is going to take us to 10x or 100x productivity let's see it generate a new, highly efficient compression algorithm or a state-of-art travelling salesman solution.

You’re right, but at the same time, 99% of software people need has already been done in some form. This gets back to the article on “perfect software” [1] posted last week. This bookshelf is perfect for the guy who wrote it and there isn’t anything exactly like it out there. The common tools on the App Store (goodreads) don’t fit his needs. But he was able to create a piece of “perfect software” that exactly meets h…

Yes, that's an excellent framing of where we're at and the role that LLM generated software is excelling in. Custom software has been out of reach for many people who would benefit from it due to requiring either a lot of money to pay someone to build it or a lot of time to learn how to build it yourself and execute on that process. Right now you can essentially use services like Claude as a custom software "app store", although I'd really call it a service, where you can say "I'd like an app that does X" and depending on the scope you can get that app as a Claude Artifact in a few minutes or, if you're familiar with software development and build/deployment processes, in a few hours to days as a more traditional software artifact which you can host somewhere or install locally. Google is working hard to make this even more achievable for non-developers with Google AI Studio https://aistudio.google.com/ and Firebase Studio https://firebase.studio/

Re: Show HN: Vibe coding a bookshelf with Claude Code

#144

Post by pigpop »

zwnow wrote: post #142
MontyCarloHall wrote: post #78

Earlier quoted context omitted.

It's no different from supervising a naïve junior engineer who also copy/pastes from 15 year old SO posts (a tale as old as time): you need to carefully review and actually grok the code the junior/AI writes. Sometimes this ends up taking longer than writing it yourself, sometimes it doesn't. As with all decisions in delegating work, the trick is knowing ahead of time whether this will be the case.

I have yet to see a junior trying to install random/non existing libs.

If you forced them to try it from memory without giving them access to the web you sure would.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#145

Post by tzs »

pigpop wrote: post #115
spicyusername wrote: post #4

These are the perfect size projects vibe coding is currently good for. At some point you hit a project size that is too large or has too many interdependencies, and you have to be very careful about how you manage the context and should expect the llm to start generating too much code or subtle bugs. Once you hit that size, in my opinion, it's usually best to drop back to brainstorming mode, only use the llm to help…

Or you can apply software architecture methods that are designed to help humans with exactly the same type of problems. Once your codebase exceeds a certain size, it becomes counter-productive to have code that is dependent on the implementation of other modules (tight coupling). In Claude Code terms this means your current architecture is forcing the model to read too many lines of code into its context which is deg…

Is vibe architecting a thing too, or is architecting to make your vibe coder work better something that the human needs to know?

Re: Show HN: Vibe coding a bookshelf with Claude Code

#146

Post by cube2222 »

xur17 wrote: post #135
OptionOfT wrote: post #125

Earlier quoted context omitted.

> I know more or less exactly what I want the end result to be This is key. And this is also why AI doesn't work that well for me. I don't know yet how I want it to work. Part of the work I do is discovering this, so it can be defined.

I've found this to be the case as well. My typical workflow is: 1. Have the ai come up with an implementation plan based on my requirements 2. Iterate on the implementation plan / tweak as needed, and write it to a markdown file 3. Have it implement the above plan based on the markdown file. On projects where we split up the task into well defined, smaller tickets, this works pretty well. For larger stuff that is les…

Yeah, this exactly. And if the AI wanders in confusion during #3, it means the plan isn’t well-defined enough.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#147

Post by cdcarter »

I vibe coded an app to track my movie watches, at https://moviesonthe.computer.

I really enjoy the ability to get started quickly with a known idea like “make a single user letterboxd clone” with a system prompt that explains my preferred tech stack. From there it’s relatively easy to start going in and being the tastemaker for the project.

I think people being able to build their own bespoke apps is a huge super power. Unfortunately I don’t think the tools today do a good job of teaching you how to think if you aren’t already a software engineer. Sonnet rarely grasps for an abstraction.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#148

Post by rabf »

belter wrote: post #139
gjimmel wrote: post #122

Earlier quoted context omitted.

Ok, but if you wrote some massive corpus of code with no testing it probably would not compile either. I think if you want to make this a useful experiment you should use one of the coding assistants that can test and iterate on its code, not some chatbot which is optimized to impress nontechnical people while being as cheap as possible to run.

>> Chatbot which is optimized to impress nontechnical people Is that how we call Opus 4.5 now? :-)

That depends a lot on the system prompt and the tooling available to the model. Are you trying thin in Claude code or Factory.ai, or are you using a chat interface? The difference in the outcome can be large.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#149

Post by shimman »

simonw wrote: post #113
MontyCarloHall wrote: post #97

Earlier quoted context omitted.

Might the creator of Claude Code have some … incentives … to develop like that, or at least claim that he does? As someone who frequently uses Claude Code, I cannot say that a year's worth of features/improvements have been added in the last month. It bears repeating: if AI is truly a 10x force multiplier, you should expect to see a ~year's worth of progress in a month.

Opus 4.5 is just a few days over a month old. Boris would have had access to that for a while before its release though.

Boris is someone that is employed by Anthropic and has a massive stake in them going public, standing to make millions.

They are by definition a biased source and should not be referenced as such.

Re: Show HN: Vibe coding a bookshelf with Claude Code

#150

Post by BeetleB »

ncallaway wrote: post #86
boplicity wrote: post #75

Earlier quoted context omitted.

> Let's see something ground-breaking Why? People don't ask hammers to do much more than bash in nails into walls. AI coding tools can be incredibly powerful -- but shouldn't that power be focused on what the tool is actually good at? There are many, many times that AI coding tools can and should be used to create a "small program that already exists in multiple forms in the training data." I do things like this very…

> People keep asking AI coding tools to be something other than what they currently are. I think it's for a very reasonable reason: the AI coding tool salespeople are often selling the tools as something other than what they currently are. I think you're right, that if you calibrate your expectations to what the tools are capable of, there's definitely. It would be nice if the marketing around AI also did the same th…

> I think it's for a very reasonable reason: the AI coding tool salespeople are often selling the tools as something other than what they currently are.

And if this submission was an AI salesperson trying to sell something, the comment/concern would be pertinent. It is otherwise irrelevant here.

Post reply on HN