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

441–450 of 507 posts

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

#441

Post by JKCalhoun »

cft wrote: post #389
baq wrote: post #350

Earlier quoted context omitted.

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...

In 2027 we'll have LLMs downloaded to our devices that are as good as Claude Code is today. (But as I have seen, as the leading edge of this stuff is always cooler than what you can run locally, we'll not be satisfied then with today's Claude Code.)

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

#442

Post by Sterling9x »

CGamesPlay wrote: post #282
personjerry wrote: post #269

Earlier quoted context omitted.

That seems like a steal? Engineers are paid much more to do much less

No, I'm paid much more to do much more than what I did in this simple task. Claude didn't even test the changes (in this case, it does not have the hardware required to do that), or decide that the feature needed to be implemented in the first place. But my comparison wasn't "how do I compare to Claude Code", it was "how does Aider compare to Claude Code". My boss does not use Aider or Claude Code, and would not be h…

[flagged]

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

#443

Post by habinero »

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…

It's not.

A lot -- and I mean a lot -- of people who hype it up are hobby or aspirational coders.

If you drill down on what exactly they use it for, they invariably don't write code in professional settings that will be maintained and which other humans have to read.

Everyone who does goes "eh, it's good for throwaway code or one offs and it's decent at code completion".

Then there's the "AGI will doom us all" cult weirdos, but we don't talk about them.

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

#444

Post by habinero »

fallinditch wrote: post #214
jmull wrote: post #190

Earlier quoted context omitted.

> …many (potentially thousands) of rules, and then iteratively adding to and amending the rules as you go… Is this an especially better (easier, more efficient) route to a working, quality app/system than conventional programming? I’m skeptical if the answer to the way to achieve 10x results is 10x more effort.

It's such a fast moving space, perhaps the need for 'rules' is just a temporary thing, but right now the rules will help you to achieve more predictable results and higher quality code. You could easily end up with a lot of rules if you are working with a reasonably large codebase. And as you work on your code, every time you have to deal with an issue of the code generation you ask Cursor to create a new rule so tha…

Or it's just a bubble and after diminishing returns they'll go in the bin with all the blockchain startups lol

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

#445

Post by aziaziazi »

naasking wrote: post #434
bayarearefugee wrote: post #374

Earlier quoted context omitted.

> 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…

> Also (most) engineers don't hallucinate answers. They absolutely do, where do you think bugs come from? The base rate is typically just lower than current AIs.

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 ones, but the term hallucinate is something else’s and doesn’t fit with much humans bugs.

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

#447

Post by darepublic »

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…

What model are you using

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

#448

Post by bluefirebrand »

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 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 any of our lifetimes

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

#449

Post by mikeocool »

Counter point: I just spent $1 and 25 minutes to try and have Claude Code figure out why a relatively simple test was failing. It repeatedly told me incorrect things about the basic functioning of the code, and ended with "Try adding debug logging in your code to see what's happening in that specific check, or look at the exact error message from the failing test."

In other words: "do your job, developer!"

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

#450

Post by naasking »

aziaziazi wrote: post #445
naasking wrote: post #434

Earlier quoted context omitted.

> Also (most) engineers don't hallucinate answers. They absolutely do, where do you think bugs come from? The base rate is typically just lower than current AIs.

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 calls it supports, the details of the parameters, etc.

Post reply on HN