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

221–230 of 464 posts

Re: Claude Code Unpacked : A visual guide

#221

Post by hombre_fatal »

mpalmer wrote: post #216
hombre_fatal wrote: post #171

Earlier quoted context omitted.

Software doesn’t end at the 20k loc proof of concept though. What every developer learns during their “psh i could build that” weekendware attempt is that there is infinite polish to be had, and that their 20k loc PoC was That said, doesn't TFA show you what they use their loc for?

Check out `print.ts` to see how "more LOC" doesn't mean "more polished"

Okay, I'm looking at it. Now what?

This file is exactly what I'm talking about.

Take the loadInitialMessage function: It's encumbered with real world incremental requirements. You can see exactly the bolted-on conditionals where they added features like --teleport, --fork-session, etc.

The runHeadlessStreaming function is a more extreme version of that where a bunch of incremental, lateral subsystems are wired together, not an example of superfluous loc.

Re: Claude Code Unpacked : A visual guide

#222

Post by TacticalCoder »

throwatdem12311 wrote: post #170

I know it seems counter-intuitive but are there any agent harnesses that aren’t written with AI? All these half a million LoC codebases seem insane to me when I run my business on a full-stack web application that’s like 50k lines of code and my MvP was like 10k. These are just TUIs that call a model endpoint with some shell-out commands. These things have only been around in time measured in months, half a million L…

> These are just TUIs that call a model endpoint with some shell-out commands.

Claude Code CLI is actually horrible: it's a full headless browser rendering that's then converted in real-time to text to show in the terminal. And that fact leaks to the user: when the model outputs ASCII, the converter shall happily convert it to Unicode (no latter than yesterday there was a TFA complaining about Unicode characters breaking Unix pipes / parsers expecting ASCII commands).

It's ultra annoying during debugging sessions (that is not when in a full agentic loop where it YOLOs a solution): you can't easily cut/paste from the CLI because the output you get is not what the model did output.

Mega, mega, mega annoying.

What should be something simple becomes a rube-goldberg machinery that, of course, fucks up something fundamental: converting the model's characters to something else is just pathetically bad.

Anyone from Anthropic reading? Get your shit together: if you keep this "headless browser rendering converted to text", at least do not fucking modify the characters.*

Re: Claude Code Unpacked : A visual guide

#223

Post by quantumquantara »

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;…

[dead]

Re: Claude Code Unpacked : A visual guide

#224

Post by raincole »

p-e-w wrote: post #176
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;…

> A 500k line codebase for an agent CLI proves one thing: making a probabilistic LLM behave deterministically is a massive state-management nightmare. Considering what the entire system ends up being capable of, 500k lines is about 0.001% of what I would have expected something like that to require 10 years ago. You can combine that with all the training and inference code, and at the end of the day, a system that li…

... what are you even talking about? "The system that literally writes code" has a few hundreds of trillions of parameters. How is this smaller than LibreOffice?

I know xkcd 1053, but come on.

Re: Claude Code Unpacked : A visual guide

#225

Post by amangsingh »

ramesh31 wrote: post #202
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;…

>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. Is that the case? I'm pretty sure Claude Code is one of the most massively successful pieces of software made in the last decade. I don't know how that proves your po…

Claude code is a massively successful generator, I use it all the time, but it's not a governance layer.

The fact that the industry is copying a 500k-line harness is the problem. We're automating security vulnerabilities at scale because people are trying to put the guardrails inside the probabilistic code instead of strictly above it.

Standardizing on half a million lines of defensive spaghetti is a huge liability.

Re: Claude Code Unpacked : A visual guide

#226

Post by ttcbj »

euphetar wrote: post #155

Appreciate the effort, but this is very basic and nothing you need the source code to understand. I was expecting a deep dive into what specific decisions they made, but not how an loop of tool calls works

I found it a useful overview. My primary question about the client source was - is there any secret sauce in it? Based on this site, the answer is no, the client is quite simple/dumb, and all the secret sauce resides on the server/in the model.

I particularly valued the tool list. People in these comments are complaining about how bad the code is, but I found the client-side tools that the model actually uses to be pretty clean/general.

My takeaway was more that at a very basic level they know what they are doing - keep the client general, so that you can innovate on the server side without revving the client as much.

Re: Claude Code Unpacked : A visual guide

#227

Post by saynay »

nicoburns wrote: post #218
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;…

Kinda depends how much of it is vibe coded. It could easily be 5x larger than it needs to be just because the LLM felt like it if they've not been careful.

Claude folks proudly claim to have Claude effectively writing itself. The CEO claims it will read an issue and automatically write a fix, tests, commit and submit a PR for it.

Re: Claude Code Unpacked : A visual guide

#228

Post by mywacaday »

amangsingh wrote: post #189
bogdanoff_2 wrote: post #180

Earlier quoted context omitted.

What do you mean by "actually governing the agents at the system level", and how is it different from "herding cats"?

Herding cats is treating the LLM's context window as your state machine. You're constantly prompt-engineering it to remember the rules, hoping it doesn't hallucinate or silently drop constraints over a long session. System-level governance means the LLM is completely stripped of orchestration rights. It becomes a stateless, untrusted function. The state lives in a rigid, external database (like SQLite). The database…

I started that very personal project on Monday, waiting with baited breath, make sure to add a sponsor me a coffee link.

Re: Claude Code Unpacked : A visual guide

#230

Post by amangsingh »

nicoburns wrote: post #218
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;…

Kinda depends how much of it is vibe coded. It could easily be 5x larger than it needs to be just because the LLM felt like it if they've not been careful.

Bingo. And them 'being careful' is exactly what bloats it to 500k lines. It's a ton of on-the-fly prompt engineering, context sanitizers, and probabilistic guardrails just to keep the vibes in check.
Post reply on HN