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

401–410 of 507 posts

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

#401

Post by kuschku »

mrheosuper wrote: post #315
majormajor wrote: post #253

Earlier quoted context omitted.

> it's basically "build a [tiny] product to specs", in a series of steps That seems like exactly what the person you're replying to is saying - that sounds like basic standard product-engineering stuff, but simpler, like any of a million examples out there that an LLM has seen a million times. "Here's a problem LLMs are good at, wow, the people using the LLMs do best at it." Tautolgy. So it's great for finding people…

But what LLM haven't look at ?

LLMs have looked at everything that exists so far. If all you're creating is yet another "Uber for Dogs", LLMs will do fine.

But if you want to create a paradigm shift, you need to do something new. Something LLMs don't yet know about.

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

#402

Post by kypro »

ddawson wrote: post #236

I do not know how to code, nothing beyond the simplest things but I am obsessed with AI development. Several month’s ago I decided to see if Claude could do the work for me. My test was to create a tower defense game that would run in a web browser. It took me about eight prompts, each time refining it, including agreeing to the suggesting that Claude recommended and seeing Claude agree with me on the bugs that I poi…

I was talking to some colleagues about this recently, and I think the reason non-coders and amateur coders seem to be so much more impressed by the current state of AI code gen is that they don't fully understand what actually goes into the average software project.

Setting up a simple game on your local machine really isn't that hard. For example, you can probably take an open-source project and with some minor alterations have something working pretty quickly.

But most software development doesn't work like this. You are typically given very explicit requirements and when you're working for a corporate with real customers you have high quality standards that need to be met. Often this is going to require a lot of bespoke code and high-level solutionising which you're not going to get out of some open source project (at least not without significant changes).

Similarly, productionising products requires a lot of work and consideration which spinning something up locally doesn't. You need to think about security, data persistence, hosting, deployment, development environments, documentation, etc, etc, etc...

I think this partly explains why people have such widely different opinions on these tools at the moment. I acknowledge they write pretty good code, but for me they're almost useless in 90% of the things I do and think about as a software engineer.

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

#403

Post by optimalsolver »

leoedin wrote: post #357
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'm a bit nervous where I'd end up though - with code I'd "written" but wasn't familiar with This does seem like quite a big downside. It turns every new feature into “implement this in someone else’s code base”. I imagine you’d very quickly have complete dependency on the AI. Maybe that’s an inevitability in this new world?

>you’d very quickly have complete dependency on the AI

That's a feature, not a bug. At least from OAI/Anthropic's point of view.

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

#404

Post by konha »

immibis wrote: post #400
zo1 wrote: post #393

Earlier quoted context omitted.

I use Grok and it's free (even Grok3). I definitely don't hit limits unless it's a pretty heavy day and I do a lot of adjustments. Also, don't send entire codebases to it, just one-off files. What's quite amazing is how it doesn't matter that it doesn't have the source to dependent files, it figures it out and infers what each method does based on its name and context, frigging amazing if you ask me. And it doesn't f…

You send your company's trade secrets directly to Elon Musk?

So? Most of your code is worthless to anyone except yourself.

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

#405

Post by turnsout »

ptsd_dalmatian wrote: post #385

for those who don't want to go to twitter: https://xcancel.com/Steve_Yegge/status/1898674257808515242

Yeah, the author needs to get off X/Twitter. At this point posting to X is like driving around in a Cybertruck with a bumper sticker reading "I Approve of the Current Situation"

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

#406

Post by artdigital »

zo1 wrote: post #393
artdigital wrote: post #297

Earlier quoted context omitted.

Same here, I did a few small taks with Claude Code after seeing this discussion here and is too expensive for me. A small change to create a script file (20 LoC) was 10cts, a quick edit to a README was 7ct Yes yes engineers make more than that blah blah but the cost would quickly jump out of control for bigger tasks. I’d easy burn through $10-20 upwards a day with this, or upwards $100-$300 a month. Unless you have a…

I use Grok and it's free (even Grok3). I definitely don't hit limits unless it's a pretty heavy day and I do a lot of adjustments. Also, don't send entire codebases to it, just one-off files. What's quite amazing is how it doesn't matter that it doesn't have the source to dependent files, it figures it out and infers what each method does based on its name and context, frigging amazing if you ask me. And it doesn't f…

> I use Grok and it's free (even Grok3). I definitely don't hit limits unless it's a pretty heavy day and I do a lot of adjustments

Okay maybe need to clarify: I hit those limits when I do agentic stuff, which is what Claude Code does: So let the LLM automatically pull in files into the context it thinks it needs, analyze my codebase, follow imports, add more code, etc. It can quickly balloon out of control when the LLM pulls in too many LoC and the context window gets too big.

Then do a few back and forth actions like "let's refine this plan, instead of X pls do Y", or "hmm I think maybe we should also look into file blah.ts" and you quickly hit 500k tokens.

If I use Cody only, which has some agentic capabilities but is much more "how can I implement Y in this file @src/file1.ts db models are in @src/models/foo.ts", then I rarely ever hit any rate limitations. That's more similar to what you describe of copying code back and forth, except it's in the editor and you can do it by writing @somefile.

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

#407

Post by artdigital »

bayarearefugee wrote: post #374
artdigital wrote: post #297

Earlier quoted context omitted.

Same here, I did a few small taks with Claude Code after seeing this discussion here and is too expensive for me. A small change to create a script file (20 LoC) was 10cts, a quick edit to a README was 7ct Yes yes engineers make more than that blah blah but the cost would quickly jump out of control for bigger tasks. I’d easy burn through $10-20 upwards a day with this, or upwards $100-$300 a month. Unless you have a…

> Yes yes engineers make more than that blah blah but the cost would quickly jump out of control for bigger tasks. Also (most) engineers don't hallucinate answers. Claude still does regularly. When it does it in chat mode via a flat rate Pro plan I can laugh it off and modify the prompt to give it the context it clearly didn't understand but if its costing me very real money for the LLM to over-eagerly over-engineer…

Exactly! Especially agentic tools like Aider and Claude that are designed to pull in more files into their context automatically, based on what the LLM thinks it should read. That can very quickly go out of control and result in huge context windows.

Right now with Copilot or other fixed subscriptions I can also laugh it off and just create a new tab with fresh context. Or if I get rate-limited because of too much token use I can wait 1 day. But if these actions are linked to directly costing money on my card, then that's becoming a lot more scary.

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

#408

Post by turnsout »

bdangubic wrote: post #262
chaosprint wrote: post #56

It seems the original poster hasn't extensively tried various AI coding assistants like Cursor or Windsurf. Just a quick heads-up based on my recent experience with agent-based AI: while it's comfortable and efficient 90% of the time, the remaining 10% can lead to extremely painful debugging experiences. In my view, the optimal scenarios for using LLM coding assistants are: - Architectural discussions, effectively re…

duuuuude :) you should seriously consider deleting this post… if you do not know who Steve Yegge is (the original poster as you call him) you really should delete this post

I appreciate that you're super attuned to this frothy space, but not everyone cares about learning all the many personalities in the ecosystem… even people who care about this stuff

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

#410

Post by namaria »

smallerfish wrote: post #125
triyambakam wrote: post #92

Earlier quoted context omitted.

Hundreds of candidates? That's significant if not an exaggeration. What are the stark differences you have seen? Did you inquire about the candidate's use of language models?

Yes. I do async video interviews in round 1 of my interview process in order to narrow the candidate funnel. Candidates get a question at the start of the interview, with a series of things to work through in their own IDE while sharing their screen. I review all recordings (though I will skip around, and if candidates don't get very far I won't spend a lot of time watching at 1x speed.) The question as laid out enco…

Are you concerned that eventual LLM price hikes in the near future reflecting their real cost might explode your cost or render your workforce ineffective?
Post reply on HN