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

471–480 of 507 posts

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

#471

Post by Suppafly »

deepGem wrote: post #344
Bjorkbat wrote: post #294

Earlier quoted context omitted.

Tangential, but this reminds me of something someone said on Twitter that has resonated with me ever since. Startups targeting developers / building developer tooling are arguably one of the worst startups to build, because no matter how much of a steal the price is relative to the value you get, developers insist they can build their own or get by with an open-source competitor. We're as misguided on value as we are…

This is also why devs are not in charge of purchase decisions at tech companies. I don't mean FAANG but the usual tech shops. Someone buys a tool and you have to use it. I think the startups selling dev tools are not selling to developers at all, but to the IT folks of these big tech firms. Should they pull it off, it's not at all a bad startup to build. However, you need to now invest in a sales force that can sell…

> I think the startups selling dev tools are not selling to developers at all, but to the IT folks of these big tech firms.

They are often selling to IT managers against the advice of the developers and IT folks, and then they mostly don't get used because they don't actually add any value to the process.

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

#472

Post by biker142541 »

miki123211 wrote: post #130
abxyz wrote: post #26

Earlier quoted context omitted.

I think it's probably the difference between "code" and "programming". An LLM can produce code and if you're willing to surrender to the LLMs version of whatever it is you ask for, then you can have a great and productive time. If you're opinionated about programming, LLMs fall short. Most people (software engineers, developers, whatever) are not "programmers" they're "coders" which is why they have a positive impres…

Oh, this captures my experience perfectly. I've been using Claude Code a lot recently, and it's doing amazing work, but it's not exactly what I want it to do . I had to push it hard to refactor and simplify, as the code it generated was often far more complicated than it needed to be. To be honest though, most of the code it generated I would accept if I was reviewing another developer's work. I think that's the way…

My experience so far on Claude 3.7 has been over-engineered solutions that are brittle. Sometimes they work, but usually not precisely the way I prompted it to, and often attempts to modify them require more refactoring due to the unnecessary complexity.

This has been the case so far in both js for web (svelte, react) and python automation.

I feel like 3.5 generally came up "short" more often than 3.7, but in practical usage it meant I could more easily modify and build on top of. 3.7 has led to a lot of deconstructing, reprompting, starting over.

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

#473

Post by itsoktocry »

bluefirebrand wrote: post #448
leoedin wrote: post #357

Earlier quoted context omitted.

> 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?

It sounds fine as long as you can fully trust the AI to do good work right? I don't think there's any current AI that is fully trustworthy this way though. I wouldn't even put them at 50% trustworthy I think we are going to see a cliff where they become 80% good, and every tiny bit of improvement past that point will be exponentially more difficult and expensive to achieve. I don't think we reach 100% reliable AI in…

I think we are going to reach a cliff where a type of old school developers keep saying, "it just can't write code like I can" while at the same time wondering why they can't land a job.

Current AI is likely already beyond 50% trustworthiness, whatever that means.

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

#474

Post by ddawson »

101008 wrote: post #242
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…

Honesty question, and leaving aside implications about what's possible and all of that, what was particular positive about the experience? You didn't do anything, just asked a different entity to do it for you. And nothing noble or original, just a copy of existing games. I see no difference between this and getting a $500 coupon to use at Fiverrr and ask a freelance engineer to do the same while you chat with them.

I'm not asking for an award. lol. I'm not sure exactly what you're after here, with asking what was particularly positive.

It's a personal attempt to see how much I can do with an automaton. I could pay someone to do my taxes or file them myself (I'm in the US). There is much more room for frustration but also lots of benefits to the latter.

In particular, with Claude Artifacts, I had a chance to see an amazing innovation. Have you ever wanted to see something new just because it's new? It changes you, which of course is one of the purposes of exploring novelties. By the way, this was my experience in July 2024.

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

#475

Post by ddawson »

101008 wrote: post #273
atonse wrote: post #272

Earlier quoted context omitted.

Is there anything inherently noble about programming if not to solve a real world problem? If they were doing it for an exam where their skills were being evaluated, that’s one thing. But if they were doing it as a means to an end, does it matter if they found a more efficient way to do it?

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?

Exactly. It's also exciting to see things at the frontier, just because they're new. I wasn't planning to release the game, just get something working for myself. By the way, this was July 2024 shortly after Anthropic introduced Claude Artifacts.

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

#476

Post by bodhi_mind »

abxyz wrote: post #26
develoopest wrote: post #4

I must be the dumbest "prompt engineer" ever, each time I ask an AI to fix or even worse, create something from scratch it rarely returns the right answer and when asked for modification it will struggle even more. All the incredible performance and success stories always come from these Twitter posts, I do find value in asking simple but tedious task like a small refactor or generate commands, but this "AI takes the…

I think it's probably the difference between "code" and "programming". An LLM can produce code and if you're willing to surrender to the LLMs version of whatever it is you ask for, then you can have a great and productive time. If you're opinionated about programming, LLMs fall short. Most people (software engineers, developers, whatever) are not "programmers" they're "coders" which is why they have a positive impres…

I’m a software developer by trade but also program art creation tools as a hobby. Funny thing is, at work, code is definitely a means to an end. But when I’m doing it for an art project, I think of the code as part of the art :) the process of programming and coming up with the code is ultimately a part of the holistic artistic output. The two are not separate, just as the artists paint and brushes are also a part of the final work of a painting.

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

#477

Post by collingreen »

esafak wrote: post #211
collingreen wrote: post #209

Earlier quoted context omitted.

> Are you serious? I am serious and didn't think anything I said here was contentious. Which part are you feeling incredulity over? I'll try to clarify if I've been unclear or learn from your perspective.

You seem to be unsure if checking the code is likely to lead to better outcomes.

I'm not passing judgement in that comment about if carefully crafting and curating code is a net win productivity wise over quickly churning out ai slop that is ostensibly viable long term.

I _personally_ follow the careful crafting and review approach. I think a deep understanding of the systematic ideas underlying a project is critical to continuing to improve it effectively and I believe code that is easy to understand is extremely valuable for that. I'm my experience so far the ai stuff seems to create more, harder work for me in the long run and I end up with worse understanding after than if I just wrote it myself but I recognize that's just my person anedata so far and we're at the beginning of this ai coding landscape.

I'm also open to the idea that lots of software we currently carefully craft by hand could likely be autogenerated ad hoc as needed. Moreover, good engineers are extremely expensive and most software is quite bad anyway so I expect there is a new balance to be found here.

For my 2 cents, I'm not removing my or my company's ability to understand our own software in exchange for vendor lock in with ai (even if they weren't all owned by the current set of megalomaniacs) but I see the angles and I'm not afraid to consider the tradeoffs or have the conversation.

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

#478

Post by bluefirebrand »

itsoktocry wrote: post #473
bluefirebrand wrote: post #448

Earlier quoted context omitted.

It sounds fine as long as you can fully trust the AI to do good work right? I don't think there's any current AI that is fully trustworthy this way though. I wouldn't even put them at 50% trustworthy I think we are going to see a cliff where they become 80% good, and every tiny bit of improvement past that point will be exponentially more difficult and expensive to achieve. I don't think we reach 100% reliable AI in…

I think we are going to reach a cliff where a type of old school developers keep saying, "it just can't write code like I can" while at the same time wondering why they can't land a job. Current AI is likely already beyond 50% trustworthiness, whatever that means.

> "it just can't write code like I can" while at the same time wondering why they can't land a job

People had this same prediction about offshore development

Those old school devs are able to find well paying work fixing broken software churned out by overseas code sweatshops

I predict if you can read and understand code without the help of AI models you will be in even higher demand to fix the endless broken software built by AI assisted coders who cannot function without AI help

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

#479

Post by mhh__ »

Bjorkbat wrote: post #295
mhh__ wrote: post #277

Earlier quoted context omitted.

> vibe People do literally call it vibe coding. https://en.wikipedia.org/wiki/Vibe_coding (it turns out there is a wikipedia page already although suspect it'll be gone soon)

I'm amused by all the flags this article has. It reinforces this belief that "vibe-coding" isn't something that evolved organically, but was forced. I wouldn't go as far as to call it "astroturfed", I believe it was a spontaneous emergence, but otherwise it feels like an effort by a disproportionately small group of people desperately trying to make vibe-coding a thing for whatever reason.

it's definitely more organic than you think. I know smart productive people doing it as purely a 0 to 1 thing.

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

#480

Post by bv_dev »

I have been using the Claude Code for about 48 hours now and nearly done with one full MVP. It did both my FastAPI side, building all the models guiding me through the Postgres part as well as a well polished React frontend. Burnt about $25 in 2 days [I have a lot of Anthropic credits] and created about 10k lines of good quality code all the way to a deployment. It is scary how much it can do to the point I'm not sure how long I will be needed.
Post reply on HN