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

381–390 of 507 posts

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

#381

Post by mns »

Balgair wrote: post #112
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…

Hey, I've been hearing about this issue that programmers have on HN a lot. But I'm in the more 'bad programmer/hacker' camp and think that LLMs are amazing and really helpful. I know that one can post a link to the chat history. Can you do that for an example that you are comfortable sharing? I know that it may not be possible though or very time consuming. What I'm trying to get at is: I suck at programming, I know…

I can give you an example here. We had to do some basic local VAT validation for EU countries and as the API that you can use for that has some issues for some countries (as it checks this in the national databases) we wanted to also have a basic local one. So using Claude 3.7 I wanted to get some basic VAT validation, in general the answer and solution was good, you would be impressed, but here comes the fun part. The basic solution was just some regular expressions and then it went further on its own and created specific validations for certain countries. These validations were something like credit card number validations, sums, check digits, quite nice you would say. But the thing is in a lot of these countries these numbers are basically assigned randomly and have no algorithm, so it went on to hallucinate some validations that don't exist providing a solution that looks nice, but basically it doesn't work in most cases.

Then I went on github and found that it used some code written by someone in JS 7 years ago and just converted and extended it for my language, but that code was wrong and simply useless. We'll end up with people publishing exploits and various other security flaws in Github, these LLMs will get trained on that and people that have no clue what they are doing will push out code based on that. We're in for fun times ahead.

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

#382

Post by leptons »

baq wrote: post #356
leptons wrote: post #334

Earlier quoted context omitted.

>" The practice defies the belief in the software industry that software engineering demands great skill. " But actual software engineering does demand great skill. What "vibe coders" are doing isn't engineering. It's not even programming. It's like calling yourself a chef when you microwaved a frozen meal.

Not even programming? That’s even better! Great engineers know that code is 10-20% of the whole solution to a problem and it doesn’t matter too much. Code is not an asset, it’s a liability.

>Code is not an asset, it’s a liability.

Then AI generated code is a time bomb. Maintainability? Who needs that if you can sell the company quickly enough, I guess.

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

#383

Post by popcorncowboy »

TheDong wrote: post #325
cwalv wrote: post #318

Earlier quoted context omitted.

I've noticed this tendency in myself and thought about the 'why' a lot, and I think it comes down to subconsciously factoring in the cost of lock-in, or worse, lack of access to fix/improve a tool I've come to rely on

For me, a larger part than "cost of lock-in" is the "hacker spirit", the curiosity to understand how it works. Sure, I can pay google or fastmail to host a mailserver for me, but that deprives me of the joy of configuring and updating dovecot/postfix/etc, writing custom backup scripts, writing my own anti-spam tooling, etc. I want to know how all those pieces work. Sure, I can pay kagi to search its index of webpages…

> but that deprives me of the joy of configuring and updating dovecot/postfix/etc, writing custom backup scripts, writing my own anti-spam tooling

I'm 90% sure you're serious, but that didn't stop me having the best belly laugh for a solid few minutes at this. Thank you.

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

#384

Post by off_by_inf »

CGamesPlay wrote: post #375
bufferoverflow wrote: post #366

Earlier quoted context omitted.

Now, the billion dollar question is - how long would it take you to code that diff?

Probably about 3 minutes? That's my main usage of these types of coding tools, honestly. I already know generally what I want to happen and validating that the LLM is on the right track / reached the right solution is easy. I'm not saying that "Claude Code makes me 300% more effective", but I guess it did for this (simple) task.

And how long would it take you to debug AI generated code again and again?

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

#386

Post by baq »

leptons wrote: post #382
baq wrote: post #356

Earlier quoted context omitted.

Not even programming? That’s even better! Great engineers know that code is 10-20% of the whole solution to a problem and it doesn’t matter too much. Code is not an asset, it’s a liability.

>Code is not an asset, it’s a liability. Then AI generated code is a time bomb. Maintainability? Who needs that if you can sell the company quickly enough, I guess.

Always has been! Not sure what AI changes here.

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

#387

Post by generic92034 »

CGamesPlay wrote: post #375
bufferoverflow wrote: post #366

Earlier quoted context omitted.

Now, the billion dollar question is - how long would it take you to code that diff?

Probably about 3 minutes? That's my main usage of these types of coding tools, honestly. I already know generally what I want to happen and validating that the LLM is on the right track / reached the right solution is easy. I'm not saying that "Claude Code makes me 300% more effective", but I guess it did for this (simple) task.

Are you comparing only the generation time with your coding time? How are the figures if you include the necessary step of checking the generated code? And how do these times change if you are coding in a very complex environment?

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

#388

Post by internet_points »

iwasbirchyfirst wrote: post #311

I went from copying and pasting with ChatGPT Canvas, to Claude Artifacts, to Cursor w Claude. I haven't explored Rules yet, but have been using the Notepads for much of this. Much of my time is spent managing git commits/reverts, and preparing to bring Claude up to speed after the next chat renewal. AI coding is like having a partner who is both the smartest person in town, but also a functional alcoholic, who's real…

> AI coding is like having a partner who is both the smartest person in town, but also a functional alcoholic, who's really, really good at hiding it.

I'm stealing this :-) (And from now on I'll be imagining coding alongside Columbo. Claude Columbo.)

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

#389

Post by cft »

baq wrote: post #350
beepbooptheory wrote: post #293

Earlier quoted context omitted.

I know this is not really in the spirit of the room here, but before I ever dreamed of getting paid to code, I only learned to at all because I was cheap and/or poor cook/grad student that wanted to make little artsy musical things on the computer. I remember the first time I just downloaded pure data. No torrent, no cracks, it was just there for me and all it asked for was my patience. The only reason I ever got int…

It must be said, preferably in bold, that: > this pervasive sense that "the way to do things now" is seemingly inseparable from a credit card number and monthly charge …is true, but it only applies to experienced engineers who can sculpt the whole solution using these tools, not just random code. You need the whole learning effort to be able to ground the code the slop generators make. The passion absolutely helps he…

in 2027 a lot programming will simply be a question of who has the largest LLM budget.

I wonder what it means for the open source...

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

#390

Post by dailykoder »

AI Policy for Application *

While we encourage people to use AI systems during their role to help them work faster and more effectively, please do not use AI assistants during the application process. We want to understand your personal interest in Anthropic without mediation through an AI system, and we also want to evaluate your non-AI-assisted communication skills. Please indicate 'Yes' if you have read and agree.

Post reply on HN