Live data from Hacker News

Claude Code Unpacked : A visual guide

ccunpacked.dev

431–440 of 464 posts

Re: Claude Code Unpacked : A visual guide

#431

Earlier quoted context omitted.

The people who don’t know how to use an LLM to make them more productive, or are scared it’s going to take their job, are louder than the people who are making good use of them to make them more productive. That just seems to be human nature unfortunately - the complainers are always louder.

As someone currently "making good use of" generative AI while simultaneously being painfully aware of its shortcomings, I think the overall discourse is a bit more nuanced. Bucketing folks into simple "for" and "against" GenAI camps does nothing to cover the vast spectrum in between, making your take ultimately built on a false dichotomy. Further implying those camps fall on the lines of those "in the know" of AI vs…

Not sure why my comment is being downvoted. Am I mistaken and folks really see only for/against AI as a binary option here? Interesting to me if so. I would think that a technical community would view ai as a tool, but perhaps our existentialism is getting the better of us?

Re: Claude Code Unpacked : A visual guide

#432
post #321

Earlier quoted context omitted.

>> It would be insane to code anything by hand these days. I strongly disagree, but it made me chuckle a bit, thinking about labeling software as "handmade" or marketing software house as "artisanal".

There's a lot of errors you can miss by coding by hand, even as a seasoned developer. Try taking Claude Code, point it at your repo, and ask it to find bugs. I bet it will. Claude is actually a crazy good vuln researcher. If you use it that way, your code might just be more secure than written purely by hand.

Sure, just like drug-sniffing dogs. Whether they've actually found something or are just pleasing the operator is another story.

Re: Claude Code Unpacked : A visual guide

#433

Earlier quoted context omitted.

The author posted in this thread. It's AI.

You’re missing the point. It’s not a witch hunt, but rather a discussion on whether things are too quickly attributed to be AI generated.

That's one way to look at it but I don't think it was that deep.

Re: Claude Code Unpacked : A visual guide

#434

Earlier quoted context omitted.

No. We aren't talking about .h vs .c files nor PL interfaces. A GUI/client can be arbitrarily more or less complex than the things it's GUI'ing.

> A GUI/client can be arbitrarily more or less complex than the things it's GUI'ing. If it's an interface to ffmpeg, then sure, the GUI could be extremely complicated code. But that's not what we are talking about, is it? We are talking about an interface to a chatbot that can accept and return chats, accept and return files, and run a selection of internal commands (which include invoking itself recursively). The in…

Did your IRC client have a sandbox that let other users run commands on your box? I don't think there's enough LoC in the world before I'd let that happen!

Re: Claude Code Unpacked : A visual guide

#435

Earlier quoted context omitted.

I don’t understand what this is, is it satire? What is it supposed to be doing or solving?

Take a look at the demo or about page ;) edit: or click 'Start Pro Trial'

Tech world became so wild even in a topic that I’m confident I cannot say if something is real or satire. Amount of real but absolutely idiotic landing pages made me this way :)

Re: Claude Code Unpacked : A visual guide

#436
post #408

Earlier quoted context omitted.

Some of your comments have already been marked as "dead" oddly enough that just seemed like normal comments explaining your rationale. edit: Also seems like peoples replies are getting downvoted to hell and getting marked as dead and dissapear. Someone must not like your idea :-)

Comments are marked dead by automatic processes, not through downvotes. They're dead before anyone sees them, and you can't vote on a dead comment. amangsingh's comments have probably triggered some automated moderation. Probably at least partially because they sound LLM-generated.

Noticed that and was wondering, thanks for the explanation. Does this imply that human-people need to go “vouch” for the flagged comments to bring them back into HM’s good graces?

Re: Claude Code Unpacked : A visual guide

#437
post #137

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

I don't have a lot of experience with them but I would have thought static analysis tools circa 2020 would have managed it just fine.

The output wouldn't be anything nearly as good, comprehensive and informative as this website.

No tooling, no animation, no hidden features, no explanation of how things work upon clicking them.

But I'm glad to be proven wrong if you know a static analysis tool I can point to the repo and come up with comparable result.

Re: Claude Code Unpacked : A visual guide

#438

Earlier 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…

I hope whoever seeks to replace humans with AIs to write code never find this comment.

Re: Claude Code Unpacked : A visual guide

#440
post #43

> also related: https://www.ccleaks.com This deployment is temporarily paused

Apologies everyone, I launched the site minutes after the leak and vercel was my only fastest and quickest option, the site went down when I was sleeping cuz I was working on it day and night.

Shifted it from vercel the moment I woke up.

Post reply on HN