So it does use ripgrep and not unix grep. [0] I knew it from some other commenters here on HN, but it's nice to see it in the source as well.
0 - https://github.com/zackautocracy/claude-code/blob/main/src/u...
Claude Code Unpacked : A visual guide
41–50 of 464 posts
Re: Claude Code Unpacked : A visual guide
#42Is 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 yourself is better than CC if you really don't want to go through the trouble of making your own thing.
Re: Claude Code Unpacked : A visual guide
#43> also related: https://www.ccleaks.com
This deployment is temporarily paused
Re: Claude Code Unpacked : A visual guide
#44Kairos and auto-dream are more interesting than anything in the agent loop section. Memory consolidation between sessions is the actual unsolved problem. The rest is just plumbing tbh
Projects like Beads help with memory consolidation by making it somewhat moot, since it stays "offline" and can be recollected at any moment.
Re: Claude Code Unpacked : A visual guide
#45There's this weird thing about AI generated content where it has the perfect presentation but conveys very little. For example the whole animation on this website, what does it say beyond that you make a request to backend and get a response that may have some tool call?
When you're picking most likely tokens, you get least surprising tokens, ones with least entropy and least information per token.
Re: Claude Code Unpacked : A visual guide
#46I guess they really do eat their own dogfood and vibe code their way through it without care for technical debt? In a way, it’s a good challenge, but it’s fairly painful to watch the current state of the project (which is about a year old now, so it should be in prime shape).
Boris Cherny, the creator of Claude Code said he uses CC to build CC.
Which makes for an interesting thought / discussion; code is written to be read by humans first, executed by computers second. What would code look like if it was written to be read by LLMs? The way they work now (or, how they're trained) is on human language and code, but there might be a style that's better for LLMs. Whatever metric of "better" you may use.
Just a thought experiment, I very much doubt I'm the first one to think of it. It's probably in the same line of "why doesn't an LLM just write assembly directly"
Re: Claude Code Unpacked : A visual guide
#47If it was 2020, it would be hard to imagine that after some hours/days you getting a visual representation of the leak with such detailed stats lol
Re: Claude Code Unpacked : A visual guide
#48would be nice if the transformers code for one of these frontier LLM models got leaked, HN will have a field day with a reveal like that
I doubt there is anything special about the transformer code the frontier labs use. The only thing proprietary in it are probably the infrastructure-specific optimizations for very large scale distributed training and some GPU kernel tricks. The real moat is the training data, especially the RLHF/finetuning data and verifiable reward environments, and the GPU clusters of course. The open source models are quite close…
That’s what I‘m thinking as well.
However, I assume that usage data could be increasingly valuable as well. That will likely help the big commercial cloud models to maintain a head start for general use.
Re: Claude Code Unpacked : A visual guide
#49Is 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…
That’s what every agent does. They are fundamentally simple.
But you can do a lot of interesting things on top of this. I highly recommend writing an agent and hooking it up to a local model.
Re: Claude Code Unpacked : A visual guide
#50Thanks, I'll use this for teaching next week (on what not to do). BashTool.ts :D But, in general, I guess it just shows yet again that the emperor has no clothes.
> it just shows yet again that the emperor has no clothes
Which emperor, specifically?