Live data from Hacker News

Claude Code Unpacked : A visual guide

ccunpacked.dev

291–300 of 464 posts

Re: Claude Code Unpacked : A visual guide

#291

Earlier quoted context omitted.

The biggest reason would be: do you know a single developer who could have produced this in a couple of hours?

I'm not familiar enough with this animation library to answer that. Someone could be very used to this type of website and just copy paste things they've done before.

What does Occam's razor say?

Re: Claude Code Unpacked : A visual guide

#292

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…

> They work really well in my experience.

Yeahhh strong disagree there, I find Codex and CC to be buggy as hell. Desktop CC is very bad and web version is nigh unusable.

Re: Claude Code Unpacked : A visual guide

#293

Earlier quoted context omitted.

How about releasing your own source code? It is a beautiful site, love the UX as well as functionality.

Guess what? People have ZERO reason to Open Source anything now.

This said Jeavon's Paradox will likely mean far more code is open sourced simply due to how much code will get written in total.

Re: Claude Code Unpacked : A visual guide

#294
post #251

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'm on a mac! And I still find bugs on a regular basis...

Re: Claude Code Unpacked : A visual guide

#295

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 brea…

No it is not. Ink does not use a browser.

Re: Claude Code Unpacked : A visual guide

#296

Earlier quoted context omitted.

Just check the leaked code yourself. Two biggest areas seem to be the `utils` module, which is a kitchen sink that covers a lot of functionality from sandboxing, git support, sessions, etc, and `components` module, which contains the react ui. You could certainly build a cli agent with much smaller codebase, with leaner ui code without react, but probably not with this truckload of functionality.

They are doing some strange "reinvent the wheel" stuff. For example, I found an implementation of a PRNG, mulberry32 [1], in one of the files. That's pretty strange considering TS and Javascript have decent PRNGs built into the language and this thing is being used as literally just a shuffle. [1] https://github.com/AprilNEA/claude-code-source/blob/main/src...

Well, at least that confirms they weren't lying when they said all recent updates to claude code were made by claude. You certainly won't do this stuff if you were writing the code yourself.

Re: Claude Code Unpacked : A visual guide

#297

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…

> just TUIs For starters, CC's TUI is React-based.

Somebody somewhere is bragging to someone about using React to render a grid of ASCII characters.

Re: Claude Code Unpacked : A visual guide

#298

Enshitification galore

What exactly is shitty here? A program i use for hours every day to do the job previously done by many N human beings, without many bugs, seems to have code thats seemingly messy but still clearly works.

Maybe if it was working the way it was 2 months ago, life would be good?

Re: Claude Code Unpacked : A visual guide

#299

> 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?

There’s probably a subconscious incentive to make a tool that’s “complex” because the underlying LLM also is complex.
Post reply on HN