Are you sure you read that here? I came back yesterday after a hiatus and I’ve been dismayed how many posts are just “yeah, I just run Claude all day” without a hint of embarrassment or shame.
I run Claude all day, and produced some good shit, but I'll admit to being thoroughly embarrassed that I haven't looked at it all, won't make it public, won't put my name on it, won't pick a license. I'm depressed about the whole thing and might take it up with a therapist.
My eyes are still rolling from GP's comment:
> he single-handedly developed it by leveraging agentic coding
I agree with this sentiment so much but before I could figure I turned into it. I'm feeling torn - it's helping me write and ship good code as I couldn't before, but it feels like I don't understand the real price of using it non-stop.
Yes. Every day. Look at the replies for crying out loud. Including yours.
Why should anyone be embarrassed? You should be embarrassed that you think you are morally superior for not using Claude. Let me guess, you don't own a tv either? So cool.
Claude is regularly finding bugs and security issues people like you slop coded into widely used tools.
The big question is: how do we tell the difference?
If 99.9% of LLM-smelling projects is vibecoded garbage, why should anyone assume that your LLM-smelling project is the 0.1%? If I spend all day digging through dogshit to find the one diamond, I'll just end up going home empty-handed smelling of dogshit.
AI tells are a giant red flag indicating to potential users not to waste time on it. Want people to take your new pet project seriously? Don't use AI! And yes, that does include even the genius 100x engineers who can use LLMs responsibly.
Who says this? "Beautiful" vibecoded apps are a dime a dozen. Getting support or continued feature development for those beautiful apps after the developer's AIDHD moves on to their next half-baked idea is usually the differentiator between a good vibecoded app and a bad one.
> But I read here every day that agents can't code. And that "real developers" spend more time fixing AI bugs than producing code, and it slows them down.
This is all correct, though. I haven't tried this, but I can guarantee it's a buggy, incoherent mess, same as every other vibe coded app I've ever tried, no exceptions.
These kind of comments just spike the conversation and leave no room for nuanced opinions or discussion.
A lot of garbage is also being produced and a lot of people have to clean it up, right? Hopefully that’s not too controversial of statement?
Are you sure you read that here? I came back yesterday after a hiatus and I’ve been dismayed how many posts are just “yeah, I just run Claude all day” without a hint of embarrassment or shame.
I run Claude all day, and produced some good shit, but I'll admit to being thoroughly embarrassed that I haven't looked at it all, won't make it public, won't put my name on it, won't pick a license. I'm depressed about the whole thing and might take it up with a therapist.
My eyes are still rolling from GP's comment:
> he single-handedly developed it by leveraging agentic coding
>he single-handedly developed it by leveraging agentic coding
so, unmaintained in a year because the sole developer got bored/didn't make money from it/burned out ?
Great, I'll run my entire company on it!
6 replies →
I agree with this sentiment so much but before I could figure I turned into it. I'm feeling torn - it's helping me write and ship good code as I couldn't before, but it feels like I don't understand the real price of using it non-stop.
Yes. Every day. Look at the replies for crying out loud. Including yours.
Why should anyone be embarrassed? You should be embarrassed that you think you are morally superior for not using Claude. Let me guess, you don't own a tv either? So cool.
Claude is regularly finding bugs and security issues people like you slop coded into widely used tools.
I run Claude when it isn't broken, I run Opencode the rest of the time. I probably haven't written a line of code in months.
It took him a year to build. So yeah, obviously if someone spends a year working on something with an LLM they can produce a good product.
The slop we're seeing from people using AI is because they pump it out in a month or two and then call it a day.
The big question is: how do we tell the difference?
If 99.9% of LLM-smelling projects is vibecoded garbage, why should anyone assume that your LLM-smelling project is the 0.1%? If I spend all day digging through dogshit to find the one diamond, I'll just end up going home empty-handed smelling of dogshit.
AI tells are a giant red flag indicating to potential users not to waste time on it. Want people to take your new pet project seriously? Don't use AI! And yes, that does include even the genius 100x engineers who can use LLMs responsibly.
don't forget "where are all these beautiful apps that supposedly everybody vibe codes now?"
Who says this? "Beautiful" vibecoded apps are a dime a dozen. Getting support or continued feature development for those beautiful apps after the developer's AIDHD moves on to their next half-baked idea is usually the differentiator between a good vibecoded app and a bad one.
> But I read here every day that agents can't code. And that "real developers" spend more time fixing AI bugs than producing code, and it slows them down.
This is all correct, though. I haven't tried this, but I can guarantee it's a buggy, incoherent mess, same as every other vibe coded app I've ever tried, no exceptions.
Yeah, the crap I vibe coded is buggy as hell too. It takes a lot of tokens and time to polish my agentic turds.
Better learn to plumb bro
[dead]