Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My experience with Claude Code after two weeks of adventures

sankalp.bearblog.dev

Post reply on HN
Print view View original

51–60 of 388 posts

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

#51

Post by taude »

0x_rs wrote: post #35
arealaccount wrote: post #12

Earlier quoted context omitted.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

Some great advice I've found that seems to work very well: ask it to keep a succinct journal of all the issues and roadblocks found during the project development, and what was done to resolve or circumvent them. As for avoiding bloating the code base with scatterbrained changes, having a tidy architecture with good separation of concerns helps leading it into working solutions, but you need to actively guide it. For…

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....

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

#52

Post by Quarrelsome »

gjsman-1000 wrote: post #30
iambateman wrote: post #7

Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.

> It’s the first time it really does feel like working with a junior engineer to me. I have mixed feelings; because this means there’s really no business reason to ever hire a junior; but it also (I think) threatens the stability of senior level jobs long term, especially as seniors slowly lose their knowledge and let Claude take care of things. The result is basically: When did you get into this field, by year? I’m…

> because this means there’s really no business reason to ever hire a junior

aren't these people your seniors in the coming years? Its healthy to model an inflow and outflow.

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

#53

Post by tortila »

After reading and hearing rave reviews I’d love to try Claude Code in my startup. I already manage Claude Team subscription, but AFAIK Code is not included, it only exists in Pro/Max which are for individual accounts. How do people use it as a subscription for a team (ideally with central billing)?

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

#54

Post by Quarrelsome »

deeshee wrote: post #31
ardit33 wrote: post #21

Earlier quoted context omitted.

1.So far, it is great if you know what you want, and tell it exactly how you want it, and AI can help you on that (basically intern level work). 2. When you are in a new area, but you don't want to dive deep and just want something quick and it is not core of the app/service. But, if you are experienced, you can see how AI can mess things up pretty quickly, hence for me it has been best used to 'fill in clear and wel…

I agree. But it's also a mindset game. Experienced devs often approach AI with preconceptions that limit its utility - pride in "craftsmanship, control issues, and perfectionism can prevent seeing where AI truly shines. I've found letting go of those instincts and treating AI as a thought partner rather than just a code generator be super useful. The psychological aspects of how we interact with these tools might be…

> pride in "craftsmanship, control issues, and perfectionism

I mean, do we really want our code base to not follow a coding standard? Or are network code not to consider failure or transactional issues? I feel like all of these traits are hallmarks of good senior engineers. Really good ones learn to let go a little but no senior is going to watch a dev automated or otherwise, circumvent six layers of architecture by blasting in a static accessor or smth.

Craftsmanship, control issues and perfectionism, tend to exist for readability, to limit entropy and scope, so one can be more certain of the consequences of a chunk of code. So to consider them a problem is a weird take to me.

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

#55

Post by tick_tock_tick »

blub wrote: post #29
ctoth wrote: post #8

Earlier quoted context omitted.

Oh do let me tell you how much effort I put into tending my non-deterministic garden or relationships or hell even the contractors I am using to renovate my house! A few small markdown documents and putting in the time to understand something interesting hardly seems a steep price!

The contractors working on my house sometimes paint a room bright pink for no particular reason. When I point that out, they profusely apologize and say that of course the walls must be white and wonder why they even got the idea of making them pink in the first place. Odd, but nice fellows otherwise. It feels like they’re 10x more productive than other contractors.

I mean I get your trying to make a joke but a contractors fucking up paint and trying to gaslight you into believing it's the one you signed off on isn't that rare.

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

#56

Post by dukeyukey »

tortila wrote: post #53

After reading and hearing rave reviews I’d love to try Claude Code in my startup. I already manage Claude Team subscription, but AFAIK Code is not included, it only exists in Pro/Max which are for individual accounts. How do people use it as a subscription for a team (ideally with central billing)?

You can use CC with AWS Bedrock, with all the centralised billing AWS offers. That's how my company handles it.

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

#57

Post by ivanech »

iambateman wrote: post #7

Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.

Just got it at work today and it’s a dramatic step change beyond Cursor despite using the same foundation models. Very surprising! There was a task a month ago where AI assistance was a big net negative. Did the same thing today w/ Claude Code in 20ish minutes. And for Much less context babysitting too. Claude code is really good at finding the things it needs and adding them to its context. I find Cursor’s agent mode ceases to be useful at a task time horizon of 3-5 minutes but Claude Code can chug away for 10+ minutes and make meaningful progress without getting stuck in loops.

Again, all very surprising given that I use sonnet 4 w/ cursor + sometimes Gemini 2.5 pro. Claude Code is just so good with tools and not getting stuck.

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

#58

Post by libraryofbabel »

arealaccount wrote: post #12
iambateman wrote: post #7

Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase."

I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are _completely useless_, unless they're accompanied with a careful summary of at least:

* what kind of codebase you were working on (language, tech stack, business domain, size, age, level of cleanliness, number of contributors)

* what exactly you were trying to do

* how much experience you have with the AI tool

* is your tool set up so it can get a feedback loop from changes, e.g. by running tests

* how much prompting did you give it; do you have CLAUDE.me files in your codebase

and so on.

As others pointed out, TFA also has the problem of not being specific about most of this.

We are still learning as an industry how to use these tools best. Yes, we know they work really well for some people and others have bad experiences. Let's try and move the discussion beyond that!

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

#60

Post by reactordev »

libraryofbabel wrote: post #58
arealaccount wrote: post #12

Earlier quoted context omitted.

Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…

Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…

Seconded, that a summary description of your problem, codebase, programming dialect in use, should be included whenever a “ didn’t work for me” response.
Post reply on HN