It’s mostly beginners thinking of it as a shortcut to making software without learning any of the underlying theory. Basically, why struggle your way through a Rust tutorial on fighting the borrow checker when you can just get AI to do it? Though the issue is as soon as there’s something too complex for the AI to figure out, you’re out of luck because you’ve been deliberately avoiding learning the necessary concepts to fix it yourself.
As for whether serious people are pushing it, most actual software engineers, not really, but company management would absolutely like nothing more than to replace all their developers with AI, so yes they’re pushing it pretty hard.
The expectation is that they’ll have to hire back a lot of developers back in a panic once the consequences start hitting.
There is a small chance a new AI is developed in time that is actually good at coding and debugging in a complex environment before that point but for now that seems unlikely.
Insofar as the skills hierarchy that software engineers develop well after learning to write in a programming language, I’m left wondering what scenarios or industries are the most “vibe coding” proof. That is to say, situations that absolutely require from day 1 a strong sense of design theory, creativity, and intimate knowledge of the available resources.
Musing out loud, history has given us examples of major feats of software engineering, from the Voyager spacecrafts, to retro console games squeezing every byte of ROM for value, to the successful virtualization of the x86 instruction set. In these scenarios, those charges with the task has to contend with outerworldly QA requirements and the reality that there would be no redo. Or with financial constraints where adding an extra PROM would cascade into requiring a wider memory bus, thus an upgraded CPU, and all sorts of other changes that would doom the console before its first sale. Or having to deal with the amazing-yet-arcane structure of Intel’s microchip development from the 80s and 90s.
It is under these extreme pressures that true diamonds of engineering emerge, conquering what must have appeared to be unimaginably complex, insurmountable obstacles. I think it’s fair to say that the likes of NASA, Sony and Nintendo, and VMWare could not possibly have gotten any traction with their endeavors had they used so-called “vibe coding”.
And looking forward, I can’t see how “vibe coding” could ever yield such “ugly”-yet-functional hacks like the fast inverse square root. A product of its time, that algorithm had its niche on systems that didn’t have hardware support for inverse square roots, and it is as effective as it is surprising. Nowadays, it’s easy to fuzz a space for approximations of any given mathematical function, but if LLMs were somehow available in the 90s, I still can’t see how “vibe coding” could produce such a crude, ugly, inspirating, and breathtaking algorithm. In the right light, though, those traits might make it elegant.
Perhaps my greatest concern is that so-called “vibe coding” presents the greatest departure from the enduring ethos of computer science, a young field not too tainted by airs of station. This field, I like to think, does not close its doors based on socioeconomic class, on the place of one’s birth, or upon the connections of one’s family. Rather, the field is so wide that all who endeavor for this space find room to grow into it. There is a rich history of folks from all sorts of prior occupations joining into the ranks of computer science and finding success. The field itself elevates them based on what they contribute and how they solve puzzles.
What strikes against this ideal is how so-called “vibe coding” elevates mediocrity, a simulacra of engineering that produces a result without the personal contribution or logic solving to back it up. It is akin to producing artwork that is divorced from the artist’s experience. It embodies nothing.
To be clear, the problem isn’t that taking shortcuts is bad. Quite the opposite, shortcuts can allow for going farther with the same initial effort. But the central premise of “vibe coding” is to give off the appearance of major engineering but with virtually no effort. It is, at its core, deceitful and dilutes from bona fide engineering effort and talent.
Circling back to the earlier question, in my personal opinion, something like the Linux kernel might fit the bill. It’s something that is now so colossally large, is contributed to by an enormous user and developer base, and fills such a sizable role in the industry, that it’s hard to see how “vibe coding” can meaningful compete in that space.
Right now it’s just buzz and empty promises to not sound “left behind” to shareholders.
Even if it could generate code that could be massaged into a production-ready state at a cost less than having human-only developers (colour me skeptical), I think middle-management would actively sabotage it. You can’t fill your day with pointless meetings when your developers are AI agents.
So, I actually think the idea is only taken “seriously” at the very highest levels. I expect several layers of resistance even before it hits the actual engineers… Not because it’s a fantasy with no grounding in engineering reality which is ultimately doomed to fail, merely out of self-preservation.
As a former script kiddie myself I think it’s not much different from how I used to blindly copy and paste code snippets from tutorials. Well, environmental impact aside. Those who have the drive and genuine interest will actually come to learn things properly. Those who don’t should stay tf out of production code, which is why we genuinely shouldn’t let “vibe coding” be legitimized.
The term was coined by an OpenAI co-founder. No idea, if I would call the OpenAI folks “serious”, but it’s not just a derogatory term, like you might think.
Two days ago I watched a video by Explosions&Ire (PhD) when he began adding unknown amounts of chemicals he thought might work to produce a color change to his solution. He lamented that what he was doing amounted to “Vibe Chemistry.” In that moment I understood how inappropriate it was for a skilled programmer to do vibe coding.
I’m not sure I even really understand what “vibe coding” even means.
Telling an LLM what you want the program to do and blindly trusting whatever it outputs, basically.
Are serious people really pushing that?
It’s mostly beginners thinking of it as a shortcut to making software without learning any of the underlying theory. Basically, why struggle your way through a Rust tutorial on fighting the borrow checker when you can just get AI to do it? Though the issue is as soon as there’s something too complex for the AI to figure out, you’re out of luck because you’ve been deliberately avoiding learning the necessary concepts to fix it yourself.
As for whether serious people are pushing it, most actual software engineers, not really, but company management would absolutely like nothing more than to replace all their developers with AI, so yes they’re pushing it pretty hard.
Pentesters must have dollar signs in their eyes like a Looney tunes character
Very, yes
The expectation is that they’ll have to hire back a lot of developers back in a panic once the consequences start hitting.
There is a small chance a new AI is developed in time that is actually good at coding and debugging in a complex environment before that point but for now that seems unlikely.
Insofar as the skills hierarchy that software engineers develop well after learning to write in a programming language, I’m left wondering what scenarios or industries are the most “vibe coding” proof. That is to say, situations that absolutely require from day 1 a strong sense of design theory, creativity, and intimate knowledge of the available resources.
Musing out loud, history has given us examples of major feats of software engineering, from the Voyager spacecrafts, to retro console games squeezing every byte of ROM for value, to the successful virtualization of the x86 instruction set. In these scenarios, those charges with the task has to contend with outerworldly QA requirements and the reality that there would be no redo. Or with financial constraints where adding an extra PROM would cascade into requiring a wider memory bus, thus an upgraded CPU, and all sorts of other changes that would doom the console before its first sale. Or having to deal with the amazing-yet-arcane structure of Intel’s microchip development from the 80s and 90s.
It is under these extreme pressures that true diamonds of engineering emerge, conquering what must have appeared to be unimaginably complex, insurmountable obstacles. I think it’s fair to say that the likes of NASA, Sony and Nintendo, and VMWare could not possibly have gotten any traction with their endeavors had they used so-called “vibe coding”.
And looking forward, I can’t see how “vibe coding” could ever yield such “ugly”-yet-functional hacks like the fast inverse square root. A product of its time, that algorithm had its niche on systems that didn’t have hardware support for inverse square roots, and it is as effective as it is surprising. Nowadays, it’s easy to fuzz a space for approximations of any given mathematical function, but if LLMs were somehow available in the 90s, I still can’t see how “vibe coding” could produce such a crude, ugly, inspirating, and breathtaking algorithm. In the right light, though, those traits might make it elegant.
Perhaps my greatest concern is that so-called “vibe coding” presents the greatest departure from the enduring ethos of computer science, a young field not too tainted by airs of station. This field, I like to think, does not close its doors based on socioeconomic class, on the place of one’s birth, or upon the connections of one’s family. Rather, the field is so wide that all who endeavor for this space find room to grow into it. There is a rich history of folks from all sorts of prior occupations joining into the ranks of computer science and finding success. The field itself elevates them based on what they contribute and how they solve puzzles.
What strikes against this ideal is how so-called “vibe coding” elevates mediocrity, a simulacra of engineering that produces a result without the personal contribution or logic solving to back it up. It is akin to producing artwork that is divorced from the artist’s experience. It embodies nothing.
To be clear, the problem isn’t that taking shortcuts is bad. Quite the opposite, shortcuts can allow for going farther with the same initial effort. But the central premise of “vibe coding” is to give off the appearance of major engineering but with virtually no effort. It is, at its core, deceitful and dilutes from bona fide engineering effort and talent.
Circling back to the earlier question, in my personal opinion, something like the Linux kernel might fit the bill. It’s something that is now so colossally large, is contributed to by an enormous user and developer base, and fills such a sizable role in the industry, that it’s hard to see how “vibe coding” can meaningful compete in that space.
deleted by creator
Right now it’s just buzz and empty promises to not sound “left behind” to shareholders.
Even if it could generate code that could be massaged into a production-ready state at a cost less than having human-only developers (colour me skeptical), I think middle-management would actively sabotage it. You can’t fill your day with pointless meetings when your developers are AI agents.
So, I actually think the idea is only taken “seriously” at the very highest levels. I expect several layers of resistance even before it hits the actual engineers… Not because it’s a fantasy with no grounding in engineering reality which is ultimately doomed to fail, merely out of self-preservation.
So, lazier script kiddies?
As a former script kiddie myself I think it’s not much different from how I used to blindly copy and paste code snippets from tutorials. Well, environmental impact aside. Those who have the drive and genuine interest will actually come to learn things properly. Those who don’t should stay tf out of production code, which is why we genuinely shouldn’t let “vibe coding” be legitimized.
Not any lazier. Script kiddies didn’t write the code themselves, either.
The term was coined by an OpenAI co-founder. No idea, if I would call the OpenAI folks “serious”, but it’s not just a derogatory term, like you might think.
Two days ago I watched a video by Explosions&Ire (PhD) when he began adding unknown amounts of chemicals he thought might work to produce a color change to his solution. He lamented that what he was doing amounted to “Vibe Chemistry.” In that moment I understood how inappropriate it was for a skilled programmer to do vibe coding.
It’s the new hyped up version of “no-code” or low-code solutions, but with AI so you have more flexibility to footgun.
Sticking a vibrating egg up your ass while you code. The debugger controls the speed in inverse proportion to the number of syntax errors.
That’s just training for a chess championship