[HN Gopher] My experience with Claude Code after two weeks of ad...
       ___________________________________________________________________
        
       My experience with Claude Code after two weeks of adventures
        
       Author : dejavucoder
       Score  : 95 points
       Date   : 2025-07-17 18:27 UTC (4 hours ago)
        
 (HTM) web link (sankalp.bearblog.dev)
 (TXT) w3m dump (sankalp.bearblog.dev)
        
       | wahnfrieden wrote:
       | One approach to improving CC's search is to use Repo Prompt
       | https://repoprompt.com
        
         | dejavucoder wrote:
         | Thanks, I will check this out
        
       | voicedYoda wrote:
       | Be lovely if i could sign up for Claude using my g voice number
        
         | fuzzy2 wrote:
         | Or no number even. Sucks to be missing out, but I won't budge
         | on this.
        
       | ctoth wrote:
       | Sometimes, you'll just have a really productive session with
       | Claude Code doing a specific thing that maybe you need to do a
       | lot of.
       | 
       | One trick I have gotten some milage out of was this: have Claude
       | Code research Slash commands, then make a slash command to turn
       | the previous conversation into a slash command.
       | 
       | That was cool and great! But then, of course you inevitably will
       | interrupt it and need to do stuff to correct it, or to make a
       | change or "not like that!" or "use this tool" or "think harder
       | before you try that" or "think about the big picture" ... So you
       | do that. And then you ask it to make a command and it figures out
       | you want a /improve-command command.
       | 
       | So now you have primitives to build on!
       | 
       | Here are my current iterations of these commands (not saying they
       | are optimal!)
       | 
       | https://github.com/ctoth/slashcommands/blob/master/make-comm...
       | 
       | https://github.com/ctoth/slashcommands/blob/master/improve-c...
        
         | whatever1 wrote:
         | I find amazing all the effort that people put trying to program
         | a non deterministic black box. True courage.
        
           | ctoth wrote:
           | 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!
        
             | blub wrote:
             | 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.
        
               | ctoth wrote:
               | I asked my contractor to install a door over the back
               | stairs opening outward, came back, and it was installed
               | opening inward. He told me he tried to figure out a way
               | he could do it in-code, but there wasn't one, so that's
               | what he had to do. I was slightly miffed he didn't
               | consult me first, but he did the pragmatic thing.
               | 
               | This actually happened to me Monday.
               | 
               | But sure, humans are deterministic clockwork mechanisms!
               | 
               | Are you now going to tell me how I got a bad contractor?
               | Because that sure would sound a lot like "you're using
               | the model wrong"
        
               | tick_tock_tick wrote:
               | 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.
        
           | simlevesque wrote:
           | Our brains are non deterministic black box. We just don't
           | like to admit it.
        
       | iambateman wrote:
       | 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.
        
         | dejavucoder wrote:
         | Almost feels like a game as you level up!
        
         | arealaccount wrote:
         | 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
         | manual debugging, at worst I spend an hour and some amount of
         | tokens on a total dead end
        
           | jm4 wrote:
           | You can tell Claude to verify its work. I'm using it for data
           | analysis tasks and I always have it check the raw data for
           | accuracy. It was a whole different ballgame when I started
           | doing that.
           | 
           | Clear instructions go a long way, asking it to review work,
           | asking it to debug problems, etc. definitely helps.
        
             | vunderba wrote:
             | _> You can tell Claude to verify its work_
             | 
             | Definitely - with ONE pretty big callout. This only works
             | when a clear and quantifiable rubric for verification can
             | be expressed. Case in point, I put Claude Code to work on a
             | simple react website that needed a "Refresh button" and
             | walked away. When I came back, the button was there, and it
             | had used a combination of MCP playwright + screenshots to
             | _roughly_ verify it was working.
             | 
             | The problem was that it decided to "draw" a circular arrow
             | refresh icon and the arrow at the end of the semicircle was
             | facing towards the circle centroid. Anyone (even a layman)
             | would take one look at it and realize it looked ridiculous,
             | but Claude couldn't tell even when I took the time to
             | manually paste a screenshot asking if it saw any issues.
             | 
             | While it would also be unreasonable to expect a junior
             | engineer to _hand-write_ the coordinates for a refresh icon
             | in SVG - they would never even attempt to do that in the
             | first place realizing it would be far simpler to find one
             | from Lucide, Font Awesome, emojis, etc.
        
             | yakz wrote:
             | I second this and would add that you really need an
             | automated way to do it. For coding, automated test suites
             | go a long way toward catching boneheaded edits. It will
             | understand the error messages from the failed tests and fix
             | the mistakes more or less by itself.
             | 
             | But for other tasks like generating reports, I ask it to
             | write little tools to reformat data with a schema
             | definition, perform calculations, or do other things that
             | are fairly easy to then double-check with tests that
             | produce errors that it can work with. Having it "do math in
             | its head" is just begging for disaster. But, it can easily
             | write a tool to do it correctly.
        
           | tcdent wrote:
           | This has a lot to do with how you structure your codebase; if
           | you have repeatable patterns that make conventions obvious,
           | it will follow them for the most part.
           | 
           | When it drops in something hacky, I use that to verify the
           | functionality is correct and then prompt a refactor to make
           | it follow better conventions.
        
           | hnaccount_rng wrote:
           | Yeah that is kind of my experience as well. And - according
           | to the friend who highly recommended it - I gave it a task
           | that is "easily within its capabilities". Since I don't think
           | I'm being gaslighted, I suspect it's me using it wrong. But I
           | really can't figure out why. And I'm on my third attempt
           | now..
        
           | 0x_rs wrote:
           | 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 someone that enjoys problem-solving more than actually
           | implementing them, it's very fun.
        
             | taude wrote:
             | 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....
        
           | taude wrote:
           | do you create the claude.md files at several levels of your
           | folder structure, so you can teach it how to do different
           | things? Configuring these default system prompts is required
           | to get it to work well.
           | 
           | I'd definitely watch Boris's intro video below [1]
           | 
           | [1] Boris introduction:
           | https://www.youtube.com/watch?v=6eBSHbLKuN0 [2] summary of
           | above video: https://www.nibzard.com/claude-code/
        
             | dawnerd wrote:
             | By the time you do all of that you might as well just write
             | code by hand.
        
           | libraryofbabel wrote:
           | 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!
        
             | reactordev wrote:
             | Seconded, that a summary description of your problem,
             | codebase, programming dialect in use, should be included
             | whenever a "<Model> didn't work for me" response.
        
             | dejavucoder wrote:
             | Fair point.
             | 
             | For context, I was using Claude Code on a Ruby + Typescript
             | large open source codebase. 50M+ tokens. They had specs and
             | e2e tests so yeah I did have feedback when I was done with
             | a feature - I could run specs and Claude Code could form a
             | loop. I would usually advise it to fix specs one by one.
             | --fail-fast to find errors fast.
             | 
             | Prior to Claude Code, I have been using Cursor for an year
             | or so.
             | 
             | Sonnet is particularly good at NextJS and Typescript stuff.
             | I also ran this on a medium sized Python codebase and some
             | ML related work too (ranging from langchain to Pytorch lol)
             | 
             | I don't do a lot of prompting, just enough to describe my
             | problem clearly. I try my best to identify the relevant
             | context or direct the model to find it fast.
             | 
             | I made new claude.md files.
        
             | state_less wrote:
             | Here's a few general observations.
             | 
             | Your LLM (CC) doesn't have your whole codebase in context,
             | so it can run off and make changes without considering that
             | some remote area of the codebase are (subtly?) depending on
             | the part that claude just changed. This can be mitigated to
             | some degree depending on the language and tests in place.
             | 
             | The LLM (CC) might identify a bug in the codebase, fix it,
             | and then figure, "Well, my work here is done." and just
             | leave it as is without considering ramifications or that
             | the same sort of bug might be found elsewhere.
             | 
             | I could go on, but my point is to simply validate the
             | issues people will be having, while also acknowledging
             | those seeing the value of an LLM like CC. It does provides
             | useful work (e.g. large tedious refactors, prototyping,
             | tracking down a variety of bugs, and so on...).
        
               | simonw wrote:
               | Right, which is why having a comprehensive test suite is
               | such an enormous unlock for this class of technology.
               | 
               | If your tests are good, Claude Code can run them and use
               | them to check it hasn't broken any distant existing
               | behavior.
        
               | dawnerd wrote:
               | Not always the case. It'll just go and "fix" the tests to
               | pass instead of fixing the core issue.
        
             | imiric wrote:
             | It's telling that you ask these details from a comment
             | describing a negative experience, yet the top-most comment
             | full of praises and hyperbole is accepted at face value.
             | Let's either demand these things from both sides or from
             | neither. Just because your experience matches one side,
             | doesn't mean that experiences different from yours should
             | require a higher degree of scrutiny.
             | 
             | I actually think it's more productive to just accept how
             | people describe their experience, without demanding some
             | extensive list of evidence to back it up. We don't do this
             | for any other opinion, so why does it matter in this case?
             | 
             | > Let's try and move the discussion beyond that!
             | 
             | Sharing experiences using anecdotal evidence covers most of
             | the discussion on forums. Maybe don't try to police it, and
             | either engage with it, or move on.
        
               | libraryofbabel wrote:
               | I should have been clearer - I'd like to see this kind of
               | information from positive comments as well. It's just as
               | important. If someone is having success with Claude Code
               | while vide-coding a toy app, I don't care. If they're
               | having success with it on a large legacy codebase, I want
               | them to write a blog post all about what they're doing,
               | because that's extremely useful information.
        
               | gilfoy wrote:
               | It's telling that they didn't specifically address it at
               | the negative experience and you filled that in yourself
        
             | 0x457 wrote:
             | There are some tasks that it can fail and not, but a lot 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." IMO is "i know how to use
             | it" vs "I don't know how to use it" with a side of "I have
             | good test coverage" vs "tests?"
        
             | rstuart4133 wrote:
             | [delayed]
        
           | wyldfire wrote:
           | I have seen both success and failure. It's definitely cool
           | and I like to think of it as another perspective for when I
           | get stuck or confused.
           | 
           | When it creates a bunch of useless junk I feel free to
           | discard it and either try again with clearer guidelines (or
           | switch to Opus).
        
         | pragmatic wrote:
         | Could you elaborate a bit on the tasks,languages,domain etc
         | you're using it with?
         | 
         | People have such widely varying experiences and I'm wondering
         | why.
        
           | criddell wrote:
           | I haven't had great luck with Claude writing Windows Win32
           | (using MFC) in C++. It invents messages and APIs all the time
           | that read like exactly what I want it to do.
           | 
           | I'd think Win32 development would be something AIs are very
           | strong at because it's so old, so well documented, and
           | there's a ton of code out there for it to read. Yet it still
           | struggles with the differences between Windows messages,
           | control notification messages, and command messages.
        
           | thegrim33 wrote:
           | I find it pretty interesting that it's a roughly 2,500 word
           | article on "using Claude Code" and they never once actually
           | explain what they're using it for, what type of project
           | they're coding. It's all just so generic. I read some of it
           | then realize that there was absolutely no substance in what I
           | just read.
           | 
           | It's also another in my growing list of data points towards
           | my opinion that if an author posts meme pictures in their
           | article, it's probably not an article I'm interested in
           | reading.
        
             | kraftman wrote:
             | Yeah I got about half way through before thinking "wow
             | theres no information in this" and giving up.
        
           | _se wrote:
           | It's always POC apps in js or python, or very small libraries
           | in other popular languages with good structure from the
           | start. There are ways to make them somewhat better in other
           | cases (automated testing/validation/linting being a big one),
           | but for the type of thing that 95% of developers are doing
           | day to day (working on a big, sprawling code base where none
           | of those attributes apply), it's not close to being there.
           | 
           | The tools really do shine where they're good though. They're
           | amazing. But the moment you try to do the more "serious" work
           | with them, it falls apart rapidly.
           | 
           | I say this as someone that uses the tools every day. The only
           | explanation that makes sense to me is that the "you don't get
           | it, they're amazing at everything" people just aren't working
           | on anything even remotely complicated. Or it's confirmation
           | bias that they're only remembering the good results - as we
           | saw with last week's study on the impact of these tools on
           | open source development (perceived productivity was up, real
           | productivity was down). Until we start seeing examples to the
           | contrary, IMO it's not worth thinking that much about. Use
           | them at what they're good at, don't use them for other tasks.
           | 
           | LLMs don't have to be "all or nothing". They absolutely are
           | not good at everything, but that doesn't mean they aren't
           | good at anything.
        
             | Herring wrote:
             | I also like them for refactoring, writing tests, and
             | "explain this massive codebase please". Basically polishing
             | or investigating things that already work.
             | 
             | But I think we should expect the scope of LLM work to
             | improve rapidly in the next few years.
             | 
             | https://metr.org/blog/2025-03-19-measuring-ai-ability-to-
             | com...
        
         | kbuchanan wrote:
         | I've had the same experience, although I feel like Claude is
         | far more than a junior to me. It's ability to propose options,
         | make recommendations, and illustrate trade-offs is just unreal.
        
         | gjsman-1000 wrote:
         | > 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 actually almost afraid I need to start crunching Leetcode,
         | learning other languages, and then apply to DoD-like jobs where
         | Claude Code (or other code security concerns) mean they need
         | actual honest programmers without assistance.
         | 
         | However, the future is never certain, and nothing is ever
         | inevitable.
        
           | Quarrelsome wrote:
           | > 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.
        
             | toomuchtodo wrote:
             | The pipeline dries up when orgs would rather get the
             | upfront savings of gen AI productivity gains versus invest
             | in talent development.
        
         | apwell23 wrote:
         | half the posts on hackernews is same discussion over and over
         | about coding agent usefulness or lack of
        
         | ivanech wrote:
         | 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 <$10 in API usage!
         | 
         | 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.
        
           | iambateman wrote:
           | Cool! If you're on pro, you can use a _lot_ of claude code
           | without paying for API usage, btw.
        
       | wrs wrote:
       | There is a VS Code extension for Claude Code. It's hardly more
       | than a terminal window really, but that in itself is pretty
       | handy. If you do /ide to connect up the extension it does a few
       | things, but not yet anything resembling the Cursor diff
       | experience (much less the Cursor tab experience, which is the
       | reason I still use it).
        
         | dejavucoder wrote:
         | I use Claude Code 50% of times with Cursor now due to the diff
         | and tab. The extension is just a bit buggy sometimes otherwise
         | I would use it much more. I hit some node related bugs today
         | while searching stuff with it (forgot to report to Anthropic
         | lol). Other bugs include a scroll stuttering.
        
         | mike1o1 wrote:
         | Claude Code has pretty much replaced Copilot overnight for me,
         | though I wish the VS Code plugin was a bit more integrated, as
         | it's only a little bit more than a terminal, though I guess
         | that's the point. I was hoping for syntax highlighting to match
         | my editor and things like that (beyond just light/dark theme).
         | 
         | What I'd really want is a way to easily hide it, which I did
         | quite frequently with Copilot as its own pane.
        
       | deeshee wrote:
       | It's great to see even the most hardcore developers who are not
       | fond of change being happy with the latest releases related to
       | AI-assisted development.
       | 
       | My workflow now boils down to 2 tools really - leap.new to go
       | from 0 to 1 because it also generates the backend code w/ infra +
       | deployment and then I pick it up in Zed/Claude Code and continue
       | working on it.
        
         | ardit33 wrote:
         | 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 well defined functionality' at peacemeal.
         | Basically it is best for small bites, then large chunks.
        
           | deeshee wrote:
           | 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 as important as the technical ones.
           | 
           | Bunch of comments online also reflect how there's a lot of
           | "butthurt" developers shutting things down with a closed mind
           | - focusing only on the negatives, and not letting the
           | positives go through.
           | 
           | I sound a bit philosophical but I hope I'm getting my point
           | across.
        
             | financltravsty wrote:
             | What's your track record. What is your current scope of
             | work for Claude Code?
             | 
             | This conversation is useless without knowing the author's
             | skillset and use-case.
        
             | Quarrelsome wrote:
             | > 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.
        
         | 2sk21 wrote:
         | I'm curious: Do you scrutinize every line of code that's
         | generated?
        
           | cmrdporcupine wrote:
           | At first I dd not. Now I have learned I have to.
           | 
           | You have to watch Claude Code like a hawk. Because it's
           | inconsistent. It will cheat, give up, change directions, and
           | not make it clear to you that is what it's doing.
           | 
           | So, while it's not "junior" in capabilities, it is definitely
           | "junior" in terms of your need as a "senior" to thoroughly
           | review everything it does.
           | 
           | Or you'll regret it later.
        
       | bluetidepro wrote:
       | How are people using this without getting rate limited non stop?
       | I pay for Claude Pro and I sometimes can't go more than 5 prompts
       | in an hour without it saying I need to wait 4 hours for a
       | cooldown. I feel like I'm using it wrong or something, it's such
       | a frustrating experience. How do you give it any real code
       | context without using all your tokens so quickly?
        
         | terhechte wrote:
         | you need the max plan to break free of most rate limits
        
           | bluetidepro wrote:
           | I wish there was a Max trial (while on Pro) to test if this
           | was the case or not. Even if it was just a 24 hour trial. Max
           | is an expensive trigger to pull, and hope it just solves
           | this.
        
             | cmrdporcupine wrote:
             | FWIW I went Claude Max after Pro, and the trick is to turn
             | off Opus. If you do that you can pretty much use Sonnet all
             | working day in a normal session. I don't personally find
             | Opus that useful, and it burns through quota at 5x the
             | speed of Sonnet.
        
         | tomashubelbauer wrote:
         | I have the same issue and in recent days I seem to have gotten
         | an extra helping of overload errors which hit extra hard when I
         | realize how much this thing costs.
         | 
         | Edit: I see a sibling comment mention the Max plan. I wanna be
         | clear that I am not talking about rate limits here but actual
         | models being inaccessible - so not a rate limit issue. I hope
         | Anthropic figures this out fast, because it is souring me on
         | Claude Code a bit.
        
         | mbrumlow wrote:
         | No clue. I use it for hours on end. Longest run cost me $30 in
         | tokens. I think it was 4 hours of back and forth.
         | 
         | Here is an example of chat gpt, followed by mostly Claude that
         | finally solved a backlight issue with my laptop.
         | 
         | https://github.com/mbrumlow/lumd
        
           | singron wrote:
           | I haven't used Claude Code a lot, but I was using about
           | $2-$5/hour, but it varied a lot. If I used it 6 hours/day and
           | worked a normal 21 workday month (126 hours), then I would
           | rack up $250-$630/month in API costs. I think I could be a
           | more efficient with practice (maybe $1-$3/hour?). If you
           | think you are seriously going to use it, then the $100/month
           | or $200/month subscriptions could definitely be worth it as
           | long as you aren't getting rate limited.
           | 
           | If you aren't sure whether to pull the trigger on a
           | subscription, I would put $5-$10 into an API console account
           | and use CC with an API key.
        
         | manmal wrote:
         | Try giving it a repomap, eg by including it in CLAUDE.md. It
         | should pull in less files (context) that way. Exactly telling
         | it which files you suspect need editing also helps. If you let
         | it run scripts, make sure to tell it to grep out only the
         | relevant output, or pipe to /dev/null.
        
         | ndr_ wrote:
         | I had success through Amazon Bedrock on us-east1 during
         | European office hours. Died 9 minutes before 10 a.m. New York
         | time, though.
        
         | SwiftyBug wrote:
         | I've been using it pretty heavily and never have I been rate
         | limited. I'm not even on the Pro Max plan.
        
         | cmrdporcupine wrote:
         | Claude Max, honestly. Worth it to me.
        
         | stavros wrote:
         | Are you using Opus?
        
       | ToJans wrote:
       | Whenever I'm rate limited (pro max plan), I stop developing.
       | 
       | For anything but the smallest things I use claude code...
       | 
       | And even then...
       | 
       | For the bigger things, I ask it to propose to me a solution (when
       | adding new features).
       | 
       | It helps when you give proper guidance: do this, use that, avoid
       | X, be concise, ask to refactor when needed.
       | 
       | All in all, it's like a slightly autistic junior dev, so you need
       | to be really explicit, but once it knows what to do, it's
       | incredible.
       | 
       | That being said, whenever you're stuck on an issue, or it keeps
       | going in circles, I tend to rollback, ask for a proper analysis
       | based on the requirements, and fill in the details of necessary.
       | 
       | For the non-standard things (f.e. detect windows on a photo and
       | determine the measurement in centimetres), you still have to
       | provide a lot of guidance. However, once I told it to use xyz and
       | ABC it just goes. I've never written more then a few lines of PHP
       | in my life, but have a full API server with an A100 running,
       | thanks to Claude.
       | 
       | The accumulated hours saved are huge for me, especially front-end
       | development, refactoring, or implementing new features to see if
       | they make sense.
       | 
       | For me it's a big shift in my approach to work, and I'd be really
       | sad if I have to go back to the pre-AI area.
       | 
       | Truth to be told, I was a happy user of cline & Gemini and spent
       | hundreds of dollars on API calls per month. But it never gave me
       | the feeling Claude code gave me, the reliability for this thing
       | is saving me 80% of my time.
        
         | dontlaugh wrote:
         | I still don't get why I should want that.
         | 
         | I've mentored and managed juniors. They're usually a net
         | negative in productivity until they are no longer juniors.
        
       | erentz wrote:
       | There must at this point be lots and lots of actual walkthroughs
       | of people coding using Claude Code, or whatever, and producing
       | real world apps or libraries with them right? Would be neat to
       | have a list because this is what I want to read (or watch),
       | rather than people just continuously telling me all this is
       | amazing but not showing me it's amazing.
        
       | tortila wrote:
       | 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)?
        
         | dukeyukey wrote:
         | You can use CC with AWS Bedrock, with all the centralised
         | billing AWS offers. That's how my company handles it.
        
       | 38 wrote:
       | Claude is absolute trash. I am on the paid plan and repeatedly
       | hit the limits. and their support is essentially non existing,
       | even for paid accounts
        
       | kypro wrote:
       | HN has flipped so quickly on saying how AI produces unreliable
       | slop, to most people using it to replace junior devs at their org
       | - something I was heavily criticised for saying orgs should be
       | doing a few months back.
       | 
       | Progress doesn't end here either, imo CC is more a mid-level
       | engineer with a top-tier senior engineer's knowledge. I think
       | we're getting to the point where we can begin to replace the
       | majority of engineers (even seniors) for just a handful of
       | seniors engineers to prompt and review AI produced code and PRs.
       | 
       | Not quite there yet, of course, but definitely feeling that shift
       | starting now... There's going to be huge productivity boosts for
       | tech companies towards the end this year if we can get there.
       | 
       | Exciting times.
        
         | hooverd wrote:
         | Where do the juniors come from?
        
       | Imanari wrote:
       | PSA: you can use CC with any model via
       | https://github.com/musistudio/claude-code-router
       | 
       | The recent Kimi-K2 supposedly works great.
        
         | dejavucoder wrote:
         | thanks!
        
         | chrismustcode wrote:
         | I'd just use sst/opencode if using other models (I use it for
         | Claude through Claude pro subscription too)
        
       ___________________________________________________________________
       (page generated 2025-07-17 23:00 UTC)