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

The Claude Code Leak

build.ms

Post reply on HN
Print view View original

61–70 of 203 posts

Re: The Claude Code Leak

#61

Post by tipiirai »

grey-area wrote: post #16

Points from the article. 1. The code is garbage and this means the end of software. Now try maintaining it. 2. Code doesn’t matter (the same point restated). No, we shouldn’t accept garbage code that breaks e.g. login as an acceptable cost of business. 3. It’s about product market fit. OK, but what happens after product market fit when your code is hot garbage that nobody understands? 4. Anthropic can’t defend the co…

What exactly makes you say that "the author who seems to have fully signed up for the LLM hype train"?

I feel the author is just stating the obvious: code quality has very little to do with whether a product succeeds

Re: The Claude Code Leak

#62

Post by uduni »

steve_adams_86 wrote: post #40
uduni wrote: post #36

" The real value in the AI ecosystem isn’t the model or the harness — it’s the integration of both working seamlessly together. " Wut? The value in the ecosystem is the model. Harnesses are simple. Great models work nearly identically in every harness

Harnesses are simple (kind of? Some certainly aren't, but I'd agree that they can be simple) but they deliver a ton of value. They have a significant ROI. I agree that good models have more value because a harness can't magically make a bad model good, but there's a lot that would be inordinately difficult without a proper harness. Keeping models on rails is still important, if not essential. Great models might behav…

Sure... A good harness can be built in 1 day tho. A good model is 1000x more sophisticated

Re: The Claude Code Leak

#63

Post by MrDresden »

And this is why so much software today runs extremely hot.

It's creators clearly care not for the efficiency of how it is built, which translates directly into how it runs.

This blog post is effectively being apologetic about the fact that this is alright, since at least they got product market fit. Except Anthropic is never going to go back and clean up the mess once (if) they become profitable.

I doubt anyone will like how things will be in 5 years time if this trend of releasing badly engineered spaghetti continues.

Re: The Claude Code Leak

#64

Post by jona777than »

leduyquang753 wrote: post #7

> Many software developers have argued that working like a pack of hyenas and shipping hundreds of commits a day without reading your code is an unsustainable way to build valuable software, but this leak suggests that maybe this isn’t true — bad code can build well-regarded products. The product hasn't been around long enough to decide whether such an approach is "sustainable". It is currently in a hype state and ne…

I have flip-flopped more than ever in the last 365 days about prioritizing good code vs good product, in the AI age. This helps clarifies why.

I have come to the conclusion that we just do not know yet. There is a part of me that believes there is a point somewhere on the grand scale where the code quality genuinely does not matter if the outcome is reliably and deterministically achieved. (As an image, I like to think of Wall—E literally compressing garbage into a cube shape.)

This would ignore maintenance costs (time and effort inclusive.) Those matter to an established user base (people do not love change in my experience, even if it solves the problem better.)

On the other hand, maybe software is meant to be highly personal and not widely general. For instance, I have had more fun in the past two years than the entire 15 years of coding before it, simply building small custom-fitted tools for exactly what I need. I aimed to please an audience of one. I have also done this for others. Code quality has not mattered all that much, if at all. It will be interesting to see where things go.

Re: The Claude Code Leak

#65

Post by raincole »

kstenerud wrote: post #30

> It should serve as a warning to developers that the code doesn’t seem to matter, even in a product built for developers. Code doesn't matter IN THE EARLY DAYS. This is similar to what I've observed over 25 years in the industry. In a startup, the code doesn't really matter; the market fit does. But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather th…

Claude Code (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

In less than four years the AI coding workflow has been overhauled at least twice: from Chat interface (ChatGPT) to editor integration (Cursor), then to CLI agent harnesses (CC/Codex). It would be crazy to assume that harnesses are the end of evolution.

Re: The Claude Code Leak

#66

Post by steve_adams_86 »

uduni wrote: post #62
steve_adams_86 wrote: post #40

Earlier quoted context omitted.

Harnesses are simple (kind of? Some certainly aren't, but I'd agree that they can be simple) but they deliver a ton of value. They have a significant ROI. I agree that good models have more value because a harness can't magically make a bad model good, but there's a lot that would be inordinately difficult without a proper harness. Keeping models on rails is still important, if not essential. Great models might behav…

Sure... A good harness can be built in 1 day tho. A good model is 1000x more sophisticated

Okay, fair. I was thinking in the context of actually using the tools, but yes, in the bigger picture the model is worth far more.

Re: The Claude Code Leak

#67

Post by DANmode »

uduni wrote: post #36

" The real value in the AI ecosystem isn’t the model or the harness — it’s the integration of both working seamlessly together. " Wut? The value in the ecosystem is the model. Harnesses are simple. Great models work nearly identically in every harness

The model defines the ceiling, but the harness determines how much of that ceiling you actually reach.

It is not everyone’s experience that models work the same in every harness.

Re: The Claude Code Leak

#68

Post by croes »

raincole wrote: post #65
kstenerud wrote: post #30

> It should serve as a warning to developers that the code doesn’t seem to matter, even in a product built for developers. Code doesn't matter IN THE EARLY DAYS. This is similar to what I've observed over 25 years in the industry. In a startup, the code doesn't really matter; the market fit does. But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather th…

Claude Code (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that. In less than four years the AI coding workflow has been overhauled at least twice: from Chat interface (ChatGPT) to editor integration (Cursor), then to CLI agent harnesses (CC/Codex). It would be crazy to assume that harnesses are the end…

Claude Code 2.0 (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

Claude Code 3.0 (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

And so on and on and on.

A promise of AI was mature software

Re: The Claude Code Leak

#69

Post by kristopolous »

himata4113 wrote: post #20

I personally found it really amusing how they weaponized the legal system to DMCA all the claude code source code repositories. Code ingested into the model is not copyrightable, but produced code apparently is when by legal definition computer generated code can not be copyrighted and that's one of their primary arguments in legal cases.

I did an interesting spin to avoid it: generated Claude abstracted as a set of PRD style architectural instructions so you can do your claude-code inspired program effortlessly.

There's even a GUI called claudia for a piecemeal extraction with a PRD.

https://github.com/kristopolous/Claudette

I've got a web, rust and tkinter version (for fun) right now just making sure this approach works.

The answer is... Mostly...

Enjoy

Re: The Claude Code Leak

#70

Post by croes »

tomjen3 wrote: post #44
kstenerud wrote: post #30

> It should serve as a warning to developers that the code doesn’t seem to matter, even in a product built for developers. Code doesn't matter IN THE EARLY DAYS. This is similar to what I've observed over 25 years in the industry. In a startup, the code doesn't really matter; the market fit does. But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather th…

You are right. But you can use AI to improve your codebase too. Plus models are only going to get smarter from here (or stay the same).

> Plus models are only going to get smarter from here (or stay the same).

Training models on AI generated content leads to model collapse so they hardly become smarter if more and more code is from AI

Post reply on HN