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

91–100 of 203 posts

Re: The Claude Code Leak

#91

Post by theshrike79 »

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

There is a reason why Copilot+Opus4.6 is shit, while Claude Code + Opus 4.6 produces excellent results.

The harness matters A LOT.

The model is the engine, the harness is the driver and chassis. Even the best top of the line engine in a shitty car driven by a bad driver won't win any races.

Re: The Claude Code Leak

#92

Post by sheept »

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 wonder if GitHub would rule it a copyright violation if the source code was rewritten by an agent, i.e. copy my answers but change a few words. Legally, if the original source code is copyrighted then an agent rewriting it likely doesn't lose that copyright, but I wonder if GitHub would go through the effort of determining whether it was a derived work.

Re: The Claude Code Leak

#93

Post by JonChesterfield »

sirpilade wrote: post #81
mergesort wrote: post #11

Earlier quoted context omitted.

Hey there, author of the post here! I actually wrote this piece myself on my phone while I was out for a walk this morning. It was initially meant to be a quick note more than a full blog post —- whereas Coding As A Creative Expression took me a couple of days to write. I made a commitment to write more this year and put my thoughts out quicker than I used to, so that’s likely the primary reason it’s not as deep of a…

As a more general comment, I hope we’ll stop trying to discriminate whether a certain text was or not written/polished/extended by AI and focus more on content and author’s responsibility for what they do or do not say with that text.

I've stopped reading anything on blogs on the basis that it's now probably llm spew and life is too short for the signal to noise ratio that implies.

With the exception of things that places like HN seems to consider worth reading, which is why I'm looking through the comments to this and others to find recommendations.

Re: The Claude Code Leak

#94

Post by himata4113 »

Aloisius wrote: post #72
yeahforsureman wrote: post #41

Earlier quoted context omitted.

I guess you'd be assuming that both the original CC code and its ports are computer/AI-generated? As a lawyer, though, I'd still maintain that you wouldn't need much original human input in the CC code to kind of ruin that theory. The threshold for copyright protection isn't that high, really.

The copyright office has indicated that AI generated elements lacking human contributions to the expression (rather than input) would still not be copyrightable even if some human authored elements are made to the expression as well. Seems like it would be a nightmare to provide evidence of what parts of a half a million line codebase were written by humans if no one bothered to track it.

They have publically and proudly stated that vast amount of claude code was entirely vibe coded so they've already lost that argument.

Re: The Claude Code Leak

#95

Post by barnabee »

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…

This code matters for exactly one reason: they’re playing stupid DRM games restricting what subscriber tokens can be used for to force you to use their front ends and harnesses or buy more expensive API credits.

Claude Code is strictly worse than e.g. OpenCode in my experience. Not much to see in the app’s code except how it authenticates itself…

Sure I try and use all my subscription allowance with CC on side tasks, etc. but I still end up burning a bunch of API tokens (via OpenRouter) for more serious work (even the UI and ability to quickly review what the agent has done/is doing is vastly inferior in CC).

What they have done is got me experimenting with cheaper models from other providers with those API credits.

Re: The Claude Code Leak

#96

Post by ggrab »

I don't think it's vibe coded garbage. Sure, the 3000-line print.ts is terrible, but there's some good patterns in there that were definitely prompted in by some experienced engineers -- the feature flag setup, the `..I_VERIFIED_THIS_IS_NOT_PATH_OR_CODE` funny type hints, the overall structure. Just the usual signs this started as a PoC but quickly evolved into something much bigger. The codebase is a really interesting read.

Re: The Claude Code Leak

#98

Post by bakugo »

hxugufjfjf wrote: post #50
stbev wrote: post #24

Earlier quoted context omitted.

Have you noticed that comments like "this post seems written with AI" are now appearing on all posts, even those written without AI? We're starting to become wary due to the abuse of AI and proliferation of sloppy content, but also because we often have trouble distinguishing authentic from sloppy content. Another feature of this AI era that I hate.

Agreed. Its so tedious that the top comment section on every HN post the last six months is "this seems be written by LLM" with a bunch of back and forth on whether it is or not.

Probably because most HN posts in the last six months have been written by LLMs. Not all, but that doesn't matter, the trust has been eroded to the point that clicking on an article on the front page of HN and not being immediately met with the sloppiest slop imaginable is now a standout event in my mind.

Re: The Claude Code Leak

#99

Post by operatingthetan »

croes wrote: post #68
raincole wrote: post #65

Earlier quoted context omitted.

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…

If there is a market for a mature harness, surely it will be built right?

Re: The Claude Code Leak

#100

Post by rustystump »

I think this misses the target.

First, the twitter quote is standard toxic clapback nonsense. Gambling makes billions and does not add any value. Even facebook can argue it adds more value than gambling so this one is a dud.

People use claud code because of claud the model and not claud the harness. Cursor or a hacked up agent loop using opus or whatever are about as good. The magic is in the model not the harness here. This isnt to say the hardness is doesnt do anything.

The other bit this misses is that yes the product matters more then the code, and if the product burns battery/ram/etc doing nothing because the ai has crappy code or maybe something leaks or has a security issue, then that impacts the product.

Post reply on HN