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

461–470 of 507 posts

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

#461

Post by MyOutfitIsVague »

risyachka wrote: post #411
bhaney wrote: post #355

Earlier quoted context omitted.

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…

If you're using the LLM poorly. Many team leads spend very little time programming, and spend a lot of time reviewing code, which is basically what working with LLMs is. If the LLM writes code that you couldn't have written yourself, you aren't qualified to approve it.

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

#462

Post by ignoramous »

bufferoverflow wrote: post #366
CGamesPlay wrote: post #255

I decided to check this out after seeing the discussion here. I had previously misunderstood that it required a Claude.ai plan, but it actually just uses your API keys. I did a comparison between Claude Code and Aider (my normal go-to): I asked it to do clone a minor feature in my existing app with some minor modifications (specifically, a new global keyboard shortcut in a Swift app). Claude Code spent about 60 secon…

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

> how long would it take you to code that diff?

My scrum/agile coach says, by parallelizing prompts, a single developer can babysit multiple changes in the same time slice. By having a sequence of prompts ready before hand, a single developer can pipeline those one after the other. With an IDE that helps schedule such work, a single developer can effectively hyper-thread their developmental workflow. If the developer is epoll'ing at 10x the hertz... that's another force multiplier. Of course context switches & side-channels are of concern, but a voice over my shoulder tells me that as long as memory safety is guaranteed, everything should turn up alrigd3adb33f.

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

#463

Post by ljm »

naasking wrote: post #450
aziaziazi wrote: post #445

Earlier quoted context omitted.

Bugs from engineers comes from a variety of reasons and most have nothing in common with an LLM hallucinating. For exemple I can’t remember seing a PR with an API that seems plausible but never ever existed, or an interpretation of the specs so convoluted and edgy that you couldn’t even use sarcasm as a justification for that code. Don’t take me wrong: some LLMs are capable of producing bugs that looks like humans on…

> For exemple I can’t remember seing a PR with an API that seems plausible but never ever existed A PR is code that has already been tested and refined, which is not comparable to the output of an LLM. The output of an LLM is comparable to the first, untested code that you wrote based off of your sometimes vague memory of how some API works. It's not at all uncommon to forget some details of how an API works, what ca…

But you don't submit that rough draft with the 110% conviction that it's correct, which is what an LLM will do when it hallucinates.

It won't say "I think it should look something like this but I might be wrong," it'll say "simple! here is how you do it."

Hence hallucination and not error. It thinks it's right.

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

#465

Post by nbardy »

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…

This is untrue.

You can be over specified in your prompts and say exactly what types and algorithms you want if you’re opinionated.

I often write giant page long specs to get exactly the code I want.

It’s only 2x as fast as coding, but thinking in English is way better than coding.

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

#466

Post by rcpt »

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.

LLMs absolutely destroy interview questions and programming contests. They can spit out well designed classes and nicely packaged functions instantly.

But in my experience they haven't been great whenever asked to something more high level

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

#467

Post by mkozlows »

turnsout wrote: post #408
bdangubic wrote: post #262

Earlier quoted context omitted.

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

The point is that he's not an AI guy, he's a long-time software dev guy going back decades.

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

#468

Post by Suppafly »

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?

>It turns every new feature into “implement this in someone else’s code base”.

It amazes me that more people aren't worried about this.

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

#469

Post by Suppafly »

radlad wrote: post #303
CGamesPlay wrote: post #300

Earlier quoted context omitted.

I think I pretty directly addressed that point. Yes, it would be more expensive to hire me to do what Claude Code / Aider did, but nobody would be satisfied with my work if I stopped where Claude Code / Aider did.

They aren't necessarily saying it can replace you. They're saying that even though it's expensive, it's cheaper than your time (which can be better spent on other tasks, as you point out.)

This, if you hire engineers, you want them doing tasks only engineers can do, not busy work.

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

#470

Post by tipsytoad »

I usually am a huge fan of “copilot” tools (I use cursor, etc) and Claude has always been my go to.

But Sonnet 3.7 actually seems dangerous to me, it seems it’s been RL’d _way_ too hard into producing code that won’t crash — to the point where it will go completely against the instructions to sneak in workarounds (e.g. returning random data when a function fails!). Claude Code just makes this even worse by giving very little oversight when it makes these “errors”

Post reply on HN