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

241–250 of 464 posts

Re: Claude Code Unpacked : A visual guide

#241

Post by GuB-42 »

criley2 wrote: post #146
troupo wrote: post #135

Earlier quoted context omitted.

It's a TUI API wrapper with a few commands bolted on. I doubt it needs to be more than 20-50kloc. You can create a full 3D game with a custom 3D engine in 500k lines. What the hell is Claude Code doing?

Honest question: Why does it matter? They got the product shipped and got millions of paying customers and totally revolutionized their business and our industry. Engineers using LOC as a measure of quality is the inverse of managers using LOC as a measure of productivity.

Among the hundreds of thousands of lines of code that Anthropic produced was one that leaked the source code. It is likely to be a config file, not part of the Claude Code software itself, but it still something to track.

The more lines of code you have the more likely there is for one of them to be wrong and go unnoticed. It results in bugs, vulnerabilities,... and leaks.

Re: Claude Code Unpacked : A visual guide

#242

Post by menaerus »

troupo wrote: post #127
menaerus wrote: post #79

Earlier quoted context omitted.

> they unfortunately don't care about code quality. > It's a shame, because it's still the best coding agent, in my experience. If it is the best, and if it delivers the value users are asking for, then why would they have an incentive to make further $$$ investments to make it of a "higher" quality if the value this difference could make is not substantial or hurts the ROI? On many projects I found this "higher qual…

Is this why they ran into a bug with people hitting usage limits even on very short sessions and had to cease all communications for over a day after a week of gaslighting users because they couldn't find the root cause in the "quality doesn't matter" code base? Or that's why tgey had to buy bun with actual engineers to work on Claude Code to reduce memory peaks from 68 GB (yes, 68 gigabytes ) to a "measely" 1.7? Bec…

Sure, now the only thing remaining is you convincing Anthropic that they're doing wrong. Or alternatively you change your perspective.

Re: Claude Code Unpacked : A visual guide

#244

Post by oblio »

whycombagator wrote: post #233
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;…

> Right now, they're great for prompting simple sites/platforms but they break at large enterprise repos Can you expand on this? My experience is they require excessive steering but do not “break”

I think the "breakage" is in terms of conciseness and compactness, not outright brokenness.

Like that drunk uncle that takes half an hour and 20 000 words to tell you a 500 word story.

Re: Claude Code Unpacked : A visual guide

#246

Post by oblio »

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…

It even wrote an entire browser!

By "just" wrapping a browser engine.

Re: Claude Code Unpacked : A visual guide

#247

Post by olejorgenb »

ttcbj wrote: post #232
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;…

I find it really strange that there is so much negative commentary on the _code_, but so little commentary on the core architecture. My takeaway from looking at the tool list is that they got the fundamental architecture right - try to create a very simple and general set of tools on the client-side (e.g. read file, output rich text, etc) so that the server can innovate rapidly without revving the client (and also so…

The tools was mostly already known, no? (I wish they had a "present" tool which allowed to model to copy-paste from files/context/etc. showing the user some content without forcing it through the model)
Post reply on HN