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

I've been using Claude Code for a couple of days

twitter.com

Post reply on HN
Print view View original

411–420 of 507 posts

Re: I've been using Claude Code for a couple of days

#411

Post by risyachka »

bhaney wrote: post #355
baq wrote: post #348

Earlier quoted context omitted.

The first half is correct, but the conclusions shouldn’t be ‘we’re replicating our software engineers with Claude today’, they’re ‘our experienced engineers just 10x their productivity, we’ll never need to hire an intern’

You mean "our experienced engineers just 10x'd their productivity, so we can fire 90% of them"

Productivity gains decrease exponentially after a few weeks as your engineering skills become rusty very fast (yes, they do, in 100% cases)

Thats the biggest part everyone misses. It’s all sunshine and rainbows until in a month you realize you start asking llm to think for you and at that point the code becomes shit and degrades fast.

Like with everything else “use it or lose it”

If you don’t code yourself- you will lose the ability to properly so it very fast, and you won’t realize it until too late

Re: I've been using Claude Code for a couple of days

#412

Post by pm215 »

cheema33 wrote: post #369
smallerfish wrote: post #45

Earlier quoted context omitted.

I've done code interviews with hundreds of candidates recently. The difference between those who are using LLMs effectively and those who are not is stark. I honestly think engineers who think like OP are going to get left behind. Take a weekend to work on getting your head around this by building a personal project (or learning a new language). A few things to note: a) Use the "Projects" feature in Claude web. The c…

> The difference between those who are using LLMs effectively and those who are not is stark. Same here. Most candidates I interviewed said they did not use AI for development work. And it showed. These guys were not well informed on modern tooling and frameworks. Many of them seemed stuck in/comfortable with their old way of doing things and resistant to learning anything new. I even hired a couple of them, thinking…

Isn't that more correlation than causation, though? The kind of person who's not keeping up with the current new tech hotness isn't going to be looking at AI or modern frameworks; and conversely the kind of person who's dabbling with AI is also likely to be looking at other leading-edge tech stuff in their field. That seems to me more likely to be the cause of what you're seeing than that the act of using AI/LLMs itself resulting in candidates improving their knowledge and framework awareness.

Re: I've been using Claude Code for a couple of days

#413

Post by 101008 »

throwaway743 wrote: post #320
101008 wrote: post #273

Earlier quoted context omitted.

But copying an existing game is not solving a real world problem. You may do it to see if "I can make it", during a learning process, or as a challenge. But when you ask something/someone else to do it for you, what's the purpose?

Why are you trying to shit on the guy and put him down? What's wrong with just having fun and testing it's capabilities? So what if there's a million TD games out there? They wanted to see if it's possible and they enjoyed the experience. Or maybe someone wants to make a personalized version for someone they love, or a million other things. And what's it matter if someone else made it? Do you make your own bread or m…

I asked him because I couldn't see the fun of it. And your examples about milk and car are exactly what I am saying. I don't create them...

About your last example, it's like asking a AI to write Harry Potter but where the character has a different name and be blown away for what I did in a weekend!

Re: I've been using Claude Code for a couple of days

#414

Post by biorach »

hleszek wrote: post #55

I must have been a little too ambitious with my first test with Claude Code. I asked it to refactor a medium-sized Python project to remove duplicated code by using a dependency injection mechanism. That refactor is not really straightforward as it involves multiple files and it should be possible to use different files with different dependencies. Anyway, I explain the problem in a few lines and ask for a plan of wh…

git commit after each change it makes. It will eventually get itself into a mess. Revert to the last good state and tell it to try a different approach. Squash your commits at the end

Re: I've been using Claude Code for a couple of days

#415

Post by biorach »

999900000999 wrote: post #227
MyOutfitIsVague wrote: post #100

Earlier quoted context omitted.

Depends a lot on what context you feed it. If you have decent internal documentation and can feed it the right files, it tends to do quite well for me, often needing corrections or style fixes. To use it most effectively, you have to know the vast majority of the code that you want it to write ahead of time. It saves time typing, looking up methods, wrangling APIs appropriately, and sometimes it surprises me by worki…

I think the next step is to get it to run some automated testing against the code it produces and then fix issues accordingly. If I was a better programmer I'd be working on that solution right now.

Claude code does this already

Re: I've been using Claude Code for a couple of days

#416

Post by Chaosvex »

tom_ wrote: post #101
hleszek wrote: post #76

Earlier quoted context omitted.

We should use xcancel instead.

There is also nitter.poast.org. There sites are possibly better than twitter.com or x.com, as more of the thread is made visible to non-users.

Giving away the secrets! ;)

If the few services that are left become well-known, they'll cease to function just like the majority. Such is scraping Twitter now

Re: I've been using Claude Code for a couple of days

#417

Post by namaria »

arresin wrote: post #82

It really feels like I’m in an alternate reality with these posts. Is this paid shilling? I’m honestly wondering now considering how different my experience is EVERY DAY with llms for code.

> You just open your heart and your wallet, and Claude Code takes the wheel.

Yeah it sounds a lot like marketing to me

Re: I've been using Claude Code for a couple of days

#418

Post by ing33k »

I tried Claude Code and gave it very clear instructions to build a web based tool I wanted to build over the weekend. It did exactly that ! sure, there were some minor modifications I had to make, but it completed over 80% of the work for me.

As for the app itself, it included a simple UI built on React with custom styling and real-time support using WSS . I provided it with my brand colors and asked it to use chadcn. It also includes a Node.js-based backend with socket.io and puppeteer. I even asked it to generate a Dockerfile and Kubernetes manifests. It almost did a perfect job—the only thing I had to fix manually was updating my Ingress to support WSS.

After studying the K8s manifests, I learned a bunch of new things as well.. spent around $6 for this session and I felt that it was worth it.

Re: I've been using Claude Code for a couple of days

#419

Post by kittikitti »

JohnKemeny wrote: post #397
rs186 wrote: post #233

Earlier quoted context omitted.

Reminder: "appeal to authority" is a classical logical fallacy. For me, I don't know this person, which means that all the words are completely meaningless. Which is exactly the point.

Exception: Be very careful not to confuse "deferring to an authority on the issue" with the appeal to authority fallacy . Remember, a fallacy is an error in reasoning . Dismissing the council of legitimate experts and authorities turns good skepticism into denialism. The appeal to authority is a fallacy in argumentation, but deferring to an authority is a reliable heuristic that we all use virtually every day on issu…

Where are you going with this? The authority provided no evidence so noting the logical fallacy is correct here. In this scenario, people are appealing to authority because there's nothing else to count on.

Re: I've been using Claude Code for a couple of days

#420

Post by coffeecantcode »

firtoz wrote: post #342
stevage wrote: post #339

Earlier quoted context omitted.

It's an interesting question. As a freelance consultant, theoretically a tool like this could allow me to massively scale up my income, assuming I could find enough clients. I'm a bit nervous where I'd end up though - with code I'd "written" but wasn't familiar with, and with who knows what kinds of limitations or subtle bugs baked in.

I currently pay around $200-300 to a combination of Cursor + Anthropic through the API. I have both a full time job and freelance work. It pays for itself. I end up reviewing more than manual coding, to ensure the quality of the results. Funnily, the work I did through this method has received more praise than my usual work.

Did you outgrow the vase 500 searches that Cursor gives you per month and connect your API key for usage based pricing?

I’m having a hard time coming close to the 500 included in the monthly subscription and I use it like, a lot.

Just curious how you’re hitting that 200-300 mark unless you’re talking about paying Anthropic outside of cursor. Which I just now realized is probably the case.

Post reply on HN