Show HN: Vibe coding a bookshelf with Claude Code • Hacker News Board

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

#211

Post by ncallaway » Tue, Dec 30, 2025, 6:15 PM UTC

BeetleB wrote: post #150

ncallaway wrote: post #86

Earlier quoted context omitted.

> 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.

Obviously I disagree.

The parent specifically noted that generally "people keep asking AI coding tools to be something other than what they currently are."

There's an explanation for why that is happening, so I think it's relevant here.

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

#212

Post by __MatrixMan__ » Tue, Dec 30, 2025, 7:16 PM UTC

aurareturn wrote: post #202

__MatrixMan__ wrote: post #172

Earlier quoted context omitted.

Improved benchmarks are undeniably an improvement, but the bottleneck isn't the models anymore, it's the context engineering necessary to harness them. The more time and effort we put into our benchmarking systems the better we're able to differentiate between models, but then when you take an allegedly smart one and try to do something real with it, it behaves like a dumb one again because you haven't put as much wo…

The systems around the LLM will get built out. But do you think it will take 50 years to build out like you said before? I’m thinking 5 years at most. The key is that the LLMs get smart enough.

The more I think of it the less likely I think it is that "all code written via LLM" will happen at all.

I use LLMs to generate systems that interpret code that I use to express my wishes, but I don't think is would be desirable to express those wishes in natural language all of the time.

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

#213

Post by theshrike79 » Tue, Dec 30, 2025, 8:46 PM UTC

rabf wrote: post #141

anthonypasq wrote: post #91

Earlier quoted context omitted.

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.

The harnesses are where most progress is made at the moment. There are some definite differences in the major models as to what kind of code they prefer, but I feel the harnesses make the biggest difference.

Copilot + Sonnet is a complete idiot at times, while Claude Code + Sonnet is pretty good.

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

#214

Post by theshrike79 » Tue, Dec 30, 2025, 9:10 PM UTC

pigpop wrote: post #143

anon7000 wrote: post #67

Earlier quoted context omitted.

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 stor…

Exactly. LLMs aren't taking the jobs of developers - unless they're selling some micro-SaaS stuff that anyone with enough domain knowledge can duplicate with a Claude subscription over a weekend.

Like the DVD catalogue software I was using[0] became subscription based, and I'm not paying 50€/year for that.

Just rewrote the bits that I need this afternoon with Claude. It definitely doesn't have the same features as the CLZ Movies app had, but it has all the ones I need specifically (adding movies easily, quickly seeing if I already own a movie).

And the same will happen to more and more SaaS style things unless they offer something unique a self-made and self-hosted one can't provide.

[0] https://clz.com/movies

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

#215

Post by theshrike79 » Tue, Dec 30, 2025, 9:14 PM UTC

shimman wrote: post #149

simonw wrote: post #113

Earlier quoted context omitted.

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.

I think it might be more about the fact that he has free and unlimited access to Opus =)

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

#216

Post by theshrike79 » Tue, Dec 30, 2025, 9:23 PM UTC

m-hodges wrote: post #25

> I decided that 90 percent accuracy was enough. So many systems are fault-tolerant, and it’s great to remember that in a world where LLMs introduce new faults. Kudos to OP for this mindset; more anti-AI posters would benefit from sitting with the idea from time to time.

Don't let perfect be the enemy of good.

So many people's lives would be better if 90% of their daily tasks could be automated by LLMs, letting them spend more time doing the hard 10% properly.

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

#217

Post by NewsaHackO » Wed, Dec 31, 2025, 12:09 AM UTC

ear7h wrote: post #198

NewsaHackO wrote: post #176

Earlier quoted context omitted.

I don't think you fully understood the purpose of the project. He wanted an end product (the bookshelf app) that he had been putting off due to the time commitment. He did not say he wanted to learn about how to program in general, nor did he even say he liked programming. People care about results and the end product. If you like to program as a hobby, LLMs in no way stop you from doing this. At the end of the day,…

I'm not trying to _convince_ a stranger on the internet whether to use AI for their vibe shelf hobby project; I'm engaging with a project being presented by it's creator. Interesting that you think continuing to use AI is some enormous own against my presumed attempt at persuasion. Sounds like maybe you're the one needing validation for your viewpoint. It's clearly easy to achieve such validation given the evidence i…

Since you said you read the post, explain this to me:

>To me, this project perfectly encapsulates the uselessness of AI, small projects like this are good learning or relearning experience and by outsourcing your thinking to AI you deprive yourself of any learning, ownership, or the self fulfillment that comes with it. Unless, of course, you think engaging in "tedious" activities with things you enjoy have zero value, and if getting lost in the weeds isn't the whole point.

In the context of his first paragraph

>I own more books than I can read. Not in a charming, aspirational way, but in the practical sense that at some point I stopped knowing what I owned. Somewhere around 500 books, memory stopped being a reliable catalog.[...] For years, I told myself I would fix this. Nothing elaborate, nothing worthy of a startup idea. A spreadsheet would have been enough. I never did it, not because it was hard, but because it was tedious.

Wouldn't your statement be completely moot because he plainly said the purpose of the project was to create a system to handle his books, and the only reason he hasn't done it yet was because it was tedious? (Hint: if you need the paragraph or thge rest of his article to be broken down for you more, I suggest asking ChatGPT to give a summary for you).

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

#218

Post by fragmede » Wed, Dec 31, 2025, 12:21 AM UTC

tzs wrote: post #145

pigpop wrote: post #115

Earlier quoted context omitted.

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?

Or should we just call them microservices instead?

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

#219

Post by aurareturn » Wed, Dec 31, 2025, 8:28 AM UTC

__MatrixMan__ wrote: post #212

aurareturn wrote: post #202

Earlier quoted context omitted.

The systems around the LLM will get built out. But do you think it will take 50 years to build out like you said before? I’m thinking 5 years at most. The key is that the LLMs get smart enough.

The more I think of it the less likely I think it is that "all code written via LLM" will happen at all. I use LLMs to generate systems that interpret code that I use to express my wishes, but I don't think is would be desirable to express those wishes in natural language all of the time.

That's why people don't think software engineers as a profession will disappear. It'll just change.

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

#220

Post by yarlinghe » Wed, Dec 31, 2025, 1:51 PM UTC

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…

One thing I’ve noticed building a small “use it and leave” tool is that the models tend to self-select into roles.

For me, Codex ended up being the reliable executor for actual logic and glue code, while Claude Code (especially the frontend design skill) was much better at overall UI structure, spacing, and interaction flow. I stopped trying to make one model do everything and just let them do what they seemed naturally good at.

This only worked because the project was tiny and mostly stateless — once scope or dependencies grow, the coordination cost goes up fast. Curious if others have seen a similar split in practice, or if this is just project-type dependent.