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

Claude Code Unpacked : A visual guide

ccunpacked.dev

Post reply on HN
Print view View original

251–260 of 464 posts

Re: Claude Code Unpacked : A visual guide

#251

Post by oblio »

surajrmal wrote: post #237
johnisgood wrote: post #212

Earlier quoted context omitted.

All of them are really, REALLY bad.

Bad by whose definition? They work really well in my experience. They aren't perfect but the amount of hand holding has gone down dramatically and you can fix any glaring problems with a code review at the end. I work on a multimillion line code base which does not use any popular frameworks and it does a great job. I may be benefiting from the fact that the codebase is open source and all models have obviously been…

At least Gemini and Claude constantly break down with scrolling in various Linux terminals, something which was solved by countless TUIs decades ago.

I think a lot of the people prasing Claude & co are on Macs.

Re: Claude Code Unpacked : A visual guide

#252

Post by whiplash451 »

comboy wrote: post #191
amangsingh wrote: post #148

A 500k line codebase for an agent CLI proves one thing: making a probabilistic LLM behave deterministically is a massive state-management nightmare. Right now, they're great for prompting simple sites/platforms but they break at large enterprise repos. If you don't have a rigid, external state machine governing the workflow, you have to brute-force reliability. That codebase bloat is likely 90% defensive programming;…

It's hard to tell how much it says about difficulty of harnessing vs how much it says about difficulty of maintaining a clean and not bloated codebase when coding with AI.

Were human organizations (not individuals) any good at the latter anyway?

Re: Claude Code Unpacked : A visual guide

#253

Post by lelanthran »

samusiam wrote: post #197
ernst_klim wrote: post #123

> 500k lines of code Isn't it a simple REPL with some tools and integrations, written in a very high level language? How the hell is it so big? Is it because it's vibecoded and LLMs strive for bloat, or is it meaningful complexity?

I just checked competitors' codebases: - Opencode (anomalyco/opencode) is about 670k LOC - Codex (openai/codex) is about 720k LOC - Gemini (google-gemini/gemini-cli) is about 570k LOC Claude Code's 500k LOC doesn't seem out of the ordinary.

> Claude Code's 500k LOC doesn't seem out of the ordinary.

Aren't all the other products also vibe-coded? "All vibe-coded products look like this" doesn't really seem to answer the question "Why is it so damn large?"

It's a repl, that calls out to a blackbox/endpoint for data, and does basic parsing and matching of state with specific actions.

I feel the bulk of those lines should be actions that are performed. Either this is correct or this is not:

1. If the bulk of those lines implement specific and simple actions, why is it so large compared to other software that implements single actions (coreutils, etc)

2. If the actions constitute only a small part of the codebase, wtf is the rest of it doing?

Re: Claude Code Unpacked : A visual guide

#254

Post by johnisgood »

oblio wrote: post #251
surajrmal wrote: post #237

Earlier quoted context omitted.

Bad by whose definition? They work really well in my experience. They aren't perfect but the amount of hand holding has gone down dramatically and you can fix any glaring problems with a code review at the end. I work on a multimillion line code base which does not use any popular frameworks and it does a great job. I may be benefiting from the fact that the codebase is open source and all models have obviously been…

At least Gemini and Claude constantly break down with scrolling in various Linux terminals, something which was solved by countless TUIs decades ago. I think a lot of the people prasing Claude & co are on Macs.

Most of their issues have been solved a long time ago, with 1000x less code. It is depressing at this point. I really had no clue IT was in the shitters this much. I knew it was theatrical but I had no idea that it was by this much.

Re: Claude Code Unpacked : A visual guide

#255

Post by ontouchstart »

autocracy101 wrote: post #114

Author here. I built this in a few hours after the Claude Code leak. I've been working on my own coding agent setup for a while. I mostly use pi [0] because it's minimal and easy to extend. When the leak happened, I wanted to study how Anthropic structured things: the tool system, how the agent loop flows, A 500K line codebase is a lot to navigate, so I mapped it visually to give myself a quick reference I could come…

I’m using pi and cc locally in a docker container connected to a local llama.cpp so the whole agentic loop is 100% offline.

I had used pi and cc to analyze the unpacked cc to compare their design, architecture and implementation.

I guess your site was also coded with pi and it is very impressive. Wonderful if you can do a visualization for pi vs cc as well. My local models might not be powerful enough.

Thanks for the hard work!

Re: Claude Code Unpacked : A visual guide

#256

Post by ramraj07 »

59nadir wrote: post #42
jen729w wrote: post #16

Is it just me or do I not find the Claude Code application that fascinating? I use it all day and love it. Don't get me wrong. But it's a terminal-based app that talks to an LLM and calls local functions. Ooookay…

I think it's good that it's out there, and I wonder why Anthropic have been keeping it closed source; clearly they can't possibly think that the CC source code is a competitive advantage...? Agents in general are easy to make, and trivial to make for yourself especially, and the result will be much better than what any of the big providers can make for you. `pi` with whatever commands/extensions you want to make for…

If you think this is not a competitive advantage then youre missing the point. LLMs arent so good that they work through bad abstractions and pretty much everyone has bad abstractions. CC is what invents some of the best abstractions (not the first). I think theyre they first ones who nailed subagents well. Theres a lot to learn from them and while im learning a lot from their source code my heart bleeds that this happened to them.

Sincerely, someone running a team building similar things for analytics.

Re: Claude Code Unpacked : A visual guide

#257

Post by troupo »

hombre_fatal wrote: post #215
sarchertech wrote: post #208

Earlier quoted context omitted.

It is a different domain but that wasn’t your argument. Your argument was that someone was comparing it to a POC when in fact they were comparing to a finished product. Also a AAA game (with the engine) with physics, networking, and rendering code is up there in terms of the most complex pieces of software.

They just claimed that you can build a 3D game in 500k loc, thus Claude Code shouldn't use so many loc. They/you didn't render the argument for that. For example, without looking at the code, the superstition also works in the opposite direction: Claude Code is an interface to using AI to do any computer task while a 3D game just lets you shoot some bad guys, so surely the 3D game must be done in fewer loc. That's eq…

> Claude Code is an interface to using AI to do any computer task

Claude Code is quite literally a wrapper around a few APIs. At one point it needed 68GB of RAM to run and requires 11ms to "lay a scene graph" to display a few hundred characters on screen. All links here: https://news.ycombinator.com/item?id=47598488

> while a 3D game just lets you shoot some bad guys, so surely the 3D game must be done in fewer loc.

Yes, most games should be done in fewer loc

Re: Claude Code Unpacked : A visual guide

#258

Post by lelanthran »

hombre_fatal wrote: post #215
sarchertech wrote: post #208

Earlier quoted context omitted.

It is a different domain but that wasn’t your argument. Your argument was that someone was comparing it to a POC when in fact they were comparing to a finished product. Also a AAA game (with the engine) with physics, networking, and rendering code is up there in terms of the most complex pieces of software.

They just claimed that you can build a 3D game in 500k loc, thus Claude Code shouldn't use so many loc. They/you didn't render the argument for that. For example, without looking at the code, the superstition also works in the opposite direction: Claude Code is an interface to using AI to do any computer task while a 3D game just lets you shoot some bad guys, so surely the 3D game must be done in fewer loc. That's eq…

> Claude Code is an interface to using AI to do any computer task

Shouldn't interfaces be smaller than the implementation?

Re: Claude Code Unpacked : A visual guide

#259

Post by sunir »

RALaBarge wrote: post #235
sunir wrote: post #175

Earlier quoted context omitted.

It’s not surprising. There has been quite a bit of industrial research in how to manage mere apes to be deterministic with huge software control systems, and they are an unruly bunch I assure you.

Sunir! Hope you are doing well man, I got a good chuckle from this.

I am! I’ll reach out in another channel to connect.

Re: Claude Code Unpacked : A visual guide

#260

Post by samusiam »

oblio wrote: post #251
surajrmal wrote: post #237

Earlier quoted context omitted.

Bad by whose definition? They work really well in my experience. They aren't perfect but the amount of hand holding has gone down dramatically and you can fix any glaring problems with a code review at the end. I work on a multimillion line code base which does not use any popular frameworks and it does a great job. I may be benefiting from the fact that the codebase is open source and all models have obviously been…

At least Gemini and Claude constantly break down with scrolling in various Linux terminals, something which was solved by countless TUIs decades ago. I think a lot of the people prasing Claude & co are on Macs.

I haven't seen the scrolling glitch in months, where previously it was happening multiple times a day. Also haven't seen anyone complain about it in quite some time. Pretty sure they have resolved that.
Post reply on HN