If 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
How was this generated ? I'm quite sure "with ai/claude code" but what are the actual steps ?
Claude Code Unpacked : A visual guide
51–60 of 464 posts
Re: Claude Code Unpacked : A visual guide
#52Is 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…
why do you think agents you make yourself will be better for you? integration with tooling that you prefer? your local dev setup built in?
curious as i haven't gotten around to writing my own agent yet
Re: Claude Code Unpacked : A visual guide
#53Earlier quoted context omitted.
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…
LLMs read and write human-code because humans have been reading and writing human-code. The sample size of assembly problems is, in my estimate, too small for LLMs to efficiently read and write it for common use cases.
I liken it to the problem of applying machine learning to hard video games (e.g. Starcraft). When trained to mimic human strategies, it can be extremely effective, but machine learning will not discover broadly effective strategies on a reasonable timescale.
If you convert "human strategies" to "human theory, programming languages, and design patterns", perhaps the point will be clear.
But: could the ouroboric cycle of LLM use decay the common strategies and design patterns we use into inexplicable blobs of assembly? Can LLMs improve at programming if humans do not advance the theory or invent new languages, patterns, etc?
Re: Claude Code Unpacked : A visual guide
#54Earlier quoted context omitted.
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…
> It's probably in the same line of "why doesn't an LLM just write assembly directly"
My suspicion is that the "language" part of LLMs means they tend to prefer languages which are closer to human languages than assembly and benefit from much of the same abstractions and tooling (hence the recent acquisition of bun and astral).
Re: Claude Code Unpacked : A visual guide
#55Thanks, 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.
Are you not feeling the vibes?
In all seriousness. I think you‘re supposed to run these in some kind of sandbox.
Re: Claude Code Unpacked : A visual guide
#56Re: Claude Code Unpacked : A visual guide
#57So 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...
I just stumbled on a fascinating replacement candidate while clicking around on embed models on hugging face: https://github.com/lightonai/next-plaid/tree/main/colgrep
it looks really interesting.
Re: Claude Code Unpacked : A visual guide
#58> also related: https://www.ccleaks.com This deployment is temporarily paused
Same!
Re: Claude Code Unpacked : A visual guide
#59I 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.
Yes but my point was that they seem to explicitly not care about code quality and/or the insane amount of bloat, and seem to just want the LLM to be able to deal with it.
Re: Claude Code Unpacked : A visual guide
#60Earlier quoted context omitted.
Boris Cherny, the creator of Claude Code said he uses CC to build CC.
Yes but my point was that they seem to explicitly not care about code quality and/or the insane amount of bloat, and seem to just want the LLM to be able to deal with it.
I've heard somewhere that they have roughly 100% code churn every few months, so yes, they unfortunately don't care about code quality. It's a shame, because it's still the best coding agent, in my experience.