My experience with Claude Code after two weeks of adventures • Hacker News Board

Re: My experience with Claude Code after two weeks of adventures

#381

Post by taude » Mon, Jul 21, 2025, 5:52 PM UTC

gonzo41 wrote: post #112

taude wrote: post #51

Earlier quoted context omitted.

to continue on this, I wouldn't let claude or any agent actually create a project structure, i'd guide it in the custom system prompt. and then in each of the folders continue to have specific prompts for what you expect the assets to be coded like, and common behavior, libraries, etc....

So you've invented writing out a full business logic spec again. btw, I'm not throwing shade. I personally think upfront design through a large lumbering document is actually a good way to develop stuff. As you either do it upfront, or through endless iterations in sprints for years.

I spent 10 minutes writing out the business logic, you don't have to do it all at once. We're not talking about long complicated things here.

Re: My experience with Claude Code after two weeks of adventures

#382

Post by jatora » Tue, Jul 22, 2025, 4:06 PM UTC

beoberha wrote: post #165

graphememes wrote: post #87

It's great for me. I have a claude.md at the root of every folder generally, outlined in piped text for minimal context addition about the rulesets for that folder, it always creates tests for what it's doing and is set to do so in a very specific folder in a very specific way otherwise it tries to create debug files instead. I also have set rules for re-use so that way it doesn't proliferate with "enhanced" class va…

What do you consider an “agent stream”? I can’t even imagine the cognitive overhead of managing 60-70 agents let alone the physical ability to churn through them as they complete their work and re-launch them.

The only way they have 60-70 agent streams is if their definition of an agent is ridiculous.

Re: My experience with Claude Code after two weeks of adventures

#383

Post by Imanari » Tue, Jul 22, 2025, 7:11 PM UTC

Imanari wrote: post #65

PSA: you can use CC with any model via https://github.com/musistudio/claude-code-router The recent Kimi-K2 supposedly works great.

gpt4.1 works surprisingly well although it is not as proactive as Sonnet.

Re: My experience with Claude Code after two weeks of adventures

#384

Post by Myrmornis » Wed, Jul 23, 2025, 3:56 AM UTC

pxc wrote: post #308

Myrmornis wrote: post #249

Earlier quoted context omitted.

A lot of people don't realize that you can completely change the vscode UI. All the side bars in particular - just get rid of them. You're left with a blank screen on which syntax-highlighted code appears with LSP and either the command palette or if you want to be more vim/emacs-y then basically every operation is key-bindable.

I assume that on subsequent runs, it's less offensive, but every time I start a blank VSCode setup, I find myself repulsed by a series of pop-ups, persistent tooltips, extra tabs, etc., that are at best uninteresting and unwarranted. It definitely has strong Windows-y my-computing-environment-is-an-obstacle-course vibe.

I think if you can't be bothered to configure a text editor then the genre isn't really for you.

Re: My experience with Claude Code after two weeks of adventures

#385

Post by Adifounder » Fri, Jul 25, 2025, 7:07 PM UTC

seems like claudes strength is being overhyped by the people who can actually make it work for them. why is the learning curve so hard.

Re: My experience with Claude Code after two weeks of adventures

#386

Post by Adifounder » Fri, Jul 25, 2025, 7:08 PM UTC

cco wrote: post #366

muzani wrote: post #240

Earlier quoted context omitted.

From what I see, you have to get your claude.md instructions right, and most of it is using planning mode. The CLI is exactly how you interact with it. It's less vibe code and what I'd call supervisory code. It's less about writing code, more about building an engine that codes. It's hands off but unlike Cursor, it's not as eyes-off. You do observe and interrupt it. It is great for full on TDF - it figures out the fe…

Cursor does the exact same thing? Just in a GUI where you can see it all happen.

does it? i feel like you have a lot more command with claude code, they should have ui though i agree

Re: My experience with Claude Code after two weeks of adventures

#387

Post by Adifounder » Fri, Jul 25, 2025, 7:09 PM UTC

ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

i feel like it needs a ui, but then again that might kill the purpose of it, how should they go about it?

Re: My experience with Claude Code after two weeks of adventures

#388

Post by intrasight » Wed, Jul 30, 2025, 11:26 PM UTC

jimbokun wrote: post #332

intrasight wrote: post #239

Earlier quoted context omitted.

this desire to understand code will be soon be seen as rather anachronistic. What's important is that you understand your tests. Let the AI generate the code. The spec and the test are your human contribution.

If the tests are written with sufficient detail that you don't need to look at the code, the implementation of the code is such a small part of the overall work that you are gaining very little in terms of overall productivity.

I agree