I thought this was going to be an article about intelligent use of LLM tools without vibecoding, but it's actually entirely against LLMs altogether. The person who wrote it used a free trial of some tool (most likely not a frontier model) and then gave up forever when the trial ran out.
> I then tried using one of the AI tools to analyze my code in a project and a few other small tasks before it all came to an awkward halt. The system informed me that I had just run out of credits and I would need to provide a credit card to purchase more tokens I wanted to keep going.
> So you must believe me that the idea of paying a service in perpetuity so I could think just seemed so laughably absurd and horrific that I didn’t even bother giving them my card. I closed the laptop. I uninstalled the IDE and went back to using Emacs even.
I wholly support their personal choice. I am tired of articles from people who haven't used LLMs preaching about how it's all vibecoding, though.
Acting like LLM use is (EDIT: I meant is not) a spectrum between doing everything manually or handing control over to the LLM and vibecoding everything is a tired strawman argument.
Regardless of the minimal time with LLMs, I think he hit major points on importance of clarity of abstractions, unreliability, shipping more features and working harder than even and losing touch with the underlying implementation.
I'm using Github copilot and I ran out of requests before the end of the month; this happens from time to time. But last month was the first time I decided to try the cheap models that were still accessible to me just to see what they were capable of. They're dumb as rocks.
I just don't know how many people have an overly negative opinion on AI assisted coding because they've just used the poor versions of these products given out for cheap/free. A similar critique is basing one's opinion on AI based on summary that Google provides for free in their search.
This article comes from a niche of people who read a lot of news articles about LLMs (links scattered throughout) but have also avoided learning about the tools directly.
Like you said, the models available on free trials are usually toys compared to what developers use. Even Opus and GPT-5.5 are available on $20/month plans and you can buy a single month to try it out. The way they write about paying for a tool seeming "absurd and horrific" says it all about the level of actual research that went into their understanding. It's entirely based on news headlines.
I still use LLMs in a "no-vibe coding" way. Essentially I use a combination of the typical auto-complete and asking it to generate tests or individual structs/classes that I then heavily modify. But no line of code goes unread and unvetted by me.
I'm doing agentic coding with Claude Max, and it's like giving methamphetamine to a software developer.
When I run out of tokens, I pay for extra. It doesn't feel good, but I do it because I didn't write the codebase - the drug dealer did. Just one more "fix" and the code should be good to ship. Oh no, out of tokens again? Just one more "fix", and another.
And the code that the AI writes is sprawling and almost incomprehensibly complicated. Overly complicated. It's like a tweaker wrote it, on methamphetamine.
I can make this comparison because many years ago I once had an ex that put methamphetamine (I didn't realize they had an addiction) in one of my vitamin capsules "as a joke", and I was up for 36 hours straight writing convoluted code, and then writing voluminous notes about the code I had yet to write. I had never done that drug before, or since (why they are an ex). I don't even drink. After that episode I re-read what I had written and it was quite scattershot.
And now I get the same exact feeling when using AI to write code, or have it write tickets, or plan out something, etc.
I use these tools daily, and it's like putting a drug dealer between me and the code. Sure it writes a lot more code than I could write without it, but at what cost? I really don't like where this is headed. And I don't think most software developers using AI realize what is happening.
> Acting like LLM use is a spectrum between doing everything manually or handing control over to the LLM and vibecoding everything is a tired strawman argument.
But isn't the strawman here was that it wasn't a spectrum. That they couldn't just use it some, but all or nothing.
LLM usage has costs that are open ended and rising. The author describe how he relates to that as a relentless cheapskate. This isn't supposed to be a directly applicable lesson to most, just a point of reference for further consideration. How much higher will costs go? How realistic will simple finishing off an odd idea be if the tools are charging professional rates? Much of the logic now seems to be can therefore do without much reference to costs or risks.
This is so good and almost exactly expresses my own thoughts. There's a narrow window where it's capable and fits a need of tedious work (mostly around automating tasks it would take me a bit to remember all the arguments and commands I'd have to chain together to do it). But a lot of it is the stuff I actually WANT to be doing. And solving the hard problems makes me a better developer just as training in the gym makes your body stronger.
Developers were not solving hard problems. The last decade was brutal—mainly frameworks, libraries, configurations, etc. The hard problems were in research.
And regarding the gym, sure, you might enjoy lifting dumbbells and solving puzzles to sharpen your brain. But that is not what engineers are hired for; they are hired to deliver a system using the best tools available. You can choose to farm by hand while the industry moves to using tractors, but sooner or later, you will be left behind.
And lastly, moving higher in abstraction allows us to tackle even more complex problems—I'd argue much more complex than the narrow puzzles we were facing before. Part of the resistance is simply an avoidance of facing higher-level complexity once the lower tier is automated.
However, these are likely not the "hard" problems you've mentioned. I feel like I can architect solutions at a higher-level now, without having to be completely caught up in many technical nuances. I'd rather not learn the extensive PDFjs API, for example, because it would take weeks of effort to understand.
This is like reading an article "I Don't Drive Cars" that goes on like
- They're too expensive
- My buddy's 1995 Accord breaks down a lot
- Walking is healthier, plus you can stop and smell the roses
- I enjoy caring for my horse
- Sometimes you can get stuck in traffic
Fine if that's the way you want and can afford to live your life. But it is an exotic luxury belief. For those of us who are participating in the economy for real, the preference to not drive cars is not realistic.
You're going to get picked apart by people who live within walking distance or public transport distance of their office and don't understand why everyone else uses cars.
If you can walk to your office and the temperature is always between 50 and 70 degrees F you would probably think cars are crazy, too.
Which, funnily enough, proves the point even further. Some people get so comfortable in their bubble that they become unable to even comprehend why other people make other choices in other situations.
Is this bait? What are you talking about? I just use public transport to go to work. Basically, all of those points about cars are correct, except for the last one because here you almost always get stuck in traffic during rush hours. Often buses get to a destination faster than cars because of Bus Rapid Transit.
EDIT: Oh, you are talking just about the US. Then your comparison doesn't make any sense because LLMs are available worldwide.
Tbh. Those are all good reasons not to drive. I my self would add:
- They dangerous both to me as a driver, my passengers, and other road users, including pedestrians and bicyclists.
- They ruin cities which constantly have to accommodate ever increasing number of cars by destroying previously walkable neighborhoods to make room for roads and parking.
- They destroy our climate
- They are loud.
- Busses are nicer and I can read a book while riding the bus.
You're welcome to feel that way but it's a luxury belief. In reality, outside of a few (one?) major city in the US with public transportation infrastructure, you need a car. 92% of people own a car, higher if you exclude the dense urban areas I'm talking about.
People only need cars because people have cars and cars make cities worse for everyone outside of one. If nobody owned cars everyone would get by just fine. It's a race to the bottom.
Car ownership is lowest in the lowest income brackets, and public transit ridership is highest among the lower income brackets. I really don‘t understand how you can reach your conclusion that not driving is a luxury. Data would suggest the exact opposite.
EDIT: To clarify on the public transit usage. The data is by-modal. Lower income levels are by far more likely to use road based public transit (such as busses), but high earners are more likely to live near a rail station and use rail based transit: https://cepr.org/voxeu/columns/public-transit-access-and-inc...
> However, the process was far more important than the product (again!). Not every whimsy needs to become a reality.
I mean, I get it, there's different kinds of people out there with different motivations, goals, spare time, etc.
But there's also a process of product design that I think the author is overlooking.
Lately I've been working and iterating on a number of DSLs, projects that might be a total waste of my time because they end up being poorly conceived or not very useful compared to a general purpose language!
I'm also working on a video game that is basically Magic: The Gathering meets StarCraft with Civilization style hex-grid conflict. It could be a total bust and entirely no fun to play (it's hard to tell if it's fun by itself because I enjoy working on the game while testing out the play patterns). It would suck to spend a couple of years on this if it's no good.
I very much enjoy the process of trying to figure out the best syntax and semantics for a new DSL or the process of iterating on gameplay elements when working on a game. The destination is also less important. I don't really expect anyone to use my DSLs or play my video games. I'm ultimately doing it for my own enjoyment.
Saying this, I am interested in the overall architecture and I've definitely learned from my mistakes, especially with creating DSLs. Like, having a TypeScript language server with a Rust runtime has some issues. It's kind of better to build the language server into the runtime so you're not maintaining multiple parsers, and depending on the language features, an additional pseudo-runtime in the language server.
It's a really interesting PoV, and one I'm in polar opposition to.
Context engineering is allowing me to do things I've always wanted to do but don't have the time/energy. I'm writing in C++, assembly, Rust, Go. I'm fucking with boot loaders and all kinds of things.
It's brought me a far greater understanding of how cryptography, GPUs, CUDA, Apple Metal - all topics I have a vague interest in but have no time to work on.
The current raft of LLM models are genius children. It's like that 15 year old at college. But I have 30 years of experience and a genius child is pure power in my hands.
And it's a genius child that never gets tired. For a few hundred bucks a month I can have 3 geniuses working on my ideas through the night. Last night they wrote 20 different research theses on a topic and benchmarked them all. Then combined them into a best of breed algorithm better than anything that has been done before. It's an amazing world we live in.
I don't write this to throw mud at OP - they are entitled to their opinion. Merely to point out the contrast.
I taught myself linux/coding/servers because there was a long period of time where all I had was a chromebook for school, but I still wanted to explore this thing called "pure data" that i'd heard about, and thought I could make art with it. I distinctly remember being continually amazed at how you could get so many things for free, if you know where to look. And yeah.. once I found emacs it was all over. To this day I am definitely going to always go "the hard way" where I can instead of pay any SaaS even $5 a month. In my head its like: "I am a mechanic, or at least, I can get by as one, why would I take my car to the shop and pay money??"
I know its not rational, but it would be pretty darn terrible in my brain to pay for an IDE. Even more unimaginable to me to pay $100 a month for something...
All to say, "cheapskate"-ness from TFA really resonated with me, I don't see the sentiment around a lot.
To experienced devs. Why are you enjoying vibecoding? It is soulless and the job is really becoming unbearable having to discuss with an agent that alternates between “good at” and totally consensual and low iq.it feels miserable to have a few turns then seeing the tool
Became so bad and so low iq that you stuck in doing things garder than if you did it by yourself
I get the conversational aspect and value of it I just dont get people saying “I dont code anymore I manage agents” - besides obviously people selling AI
"painting is just procrastination that gets in the way of implementing your ideas."
"woodwork is just procrastination that gets in the way of implementing your ideas."
We can find plenty of others, but my main point is that industrializing a process doesn't make it "procrastinating". There are plenty of jobs that are done by machines but are still practiced by humans for multiple reasons. If we think of coding as a means to create, then we have plenty of examples of good reasons to have both the industrialized process and the 'handmade' one.
I thought this was going to be an article about intelligent use of LLM tools without vibecoding, but it's actually entirely against LLMs altogether. The person who wrote it used a free trial of some tool (most likely not a frontier model) and then gave up forever when the trial ran out.
> I then tried using one of the AI tools to analyze my code in a project and a few other small tasks before it all came to an awkward halt. The system informed me that I had just run out of credits and I would need to provide a credit card to purchase more tokens I wanted to keep going.
> So you must believe me that the idea of paying a service in perpetuity so I could think just seemed so laughably absurd and horrific that I didn’t even bother giving them my card. I closed the laptop. I uninstalled the IDE and went back to using Emacs even.
I wholly support their personal choice. I am tired of articles from people who haven't used LLMs preaching about how it's all vibecoding, though.
Acting like LLM use is (EDIT: I meant is not) a spectrum between doing everything manually or handing control over to the LLM and vibecoding everything is a tired strawman argument.
Regardless of the minimal time with LLMs, I think he hit major points on importance of clarity of abstractions, unreliability, shipping more features and working harder than even and losing touch with the underlying implementation.
I'm using Github copilot and I ran out of requests before the end of the month; this happens from time to time. But last month was the first time I decided to try the cheap models that were still accessible to me just to see what they were capable of. They're dumb as rocks.
I just don't know how many people have an overly negative opinion on AI assisted coding because they've just used the poor versions of these products given out for cheap/free. A similar critique is basing one's opinion on AI based on summary that Google provides for free in their search.
This article comes from a niche of people who read a lot of news articles about LLMs (links scattered throughout) but have also avoided learning about the tools directly.
Like you said, the models available on free trials are usually toys compared to what developers use. Even Opus and GPT-5.5 are available on $20/month plans and you can buy a single month to try it out. The way they write about paying for a tool seeming "absurd and horrific" says it all about the level of actual research that went into their understanding. It's entirely based on news headlines.
Get your company to pay for it (points to head)
Oh they do. And I could get them to pay even more but with the changes to copilot licensing, I'm not sure we will continue with it.
Is claude code any better for the value
I still use LLMs in a "no-vibe coding" way. Essentially I use a combination of the typical auto-complete and asking it to generate tests or individual structs/classes that I then heavily modify. But no line of code goes unread and unvetted by me.
I'm doing agentic coding with Claude Max, and it's like giving methamphetamine to a software developer.
When I run out of tokens, I pay for extra. It doesn't feel good, but I do it because I didn't write the codebase - the drug dealer did. Just one more "fix" and the code should be good to ship. Oh no, out of tokens again? Just one more "fix", and another.
And the code that the AI writes is sprawling and almost incomprehensibly complicated. Overly complicated. It's like a tweaker wrote it, on methamphetamine.
I can make this comparison because many years ago I once had an ex that put methamphetamine (I didn't realize they had an addiction) in one of my vitamin capsules "as a joke", and I was up for 36 hours straight writing convoluted code, and then writing voluminous notes about the code I had yet to write. I had never done that drug before, or since (why they are an ex). I don't even drink. After that episode I re-read what I had written and it was quite scattershot.
And now I get the same exact feeling when using AI to write code, or have it write tickets, or plan out something, etc.
I use these tools daily, and it's like putting a drug dealer between me and the code. Sure it writes a lot more code than I could write without it, but at what cost? I really don't like where this is headed. And I don't think most software developers using AI realize what is happening.
> Acting like LLM use is a spectrum between doing everything manually or handing control over to the LLM and vibecoding everything is a tired strawman argument.
But isn't the strawman here was that it wasn't a spectrum. That they couldn't just use it some, but all or nothing.
I think they meant "binary" rather than "spectrum".
LLM usage has costs that are open ended and rising. The author describe how he relates to that as a relentless cheapskate. This isn't supposed to be a directly applicable lesson to most, just a point of reference for further consideration. How much higher will costs go? How realistic will simple finishing off an odd idea be if the tools are charging professional rates? Much of the logic now seems to be can therefore do without much reference to costs or risks.
Imagine being disappointed that an article is NOT clickbait :|
This is so good and almost exactly expresses my own thoughts. There's a narrow window where it's capable and fits a need of tedious work (mostly around automating tasks it would take me a bit to remember all the arguments and commands I'd have to chain together to do it). But a lot of it is the stuff I actually WANT to be doing. And solving the hard problems makes me a better developer just as training in the gym makes your body stronger.
Developers were not solving hard problems. The last decade was brutal—mainly frameworks, libraries, configurations, etc. The hard problems were in research.
And regarding the gym, sure, you might enjoy lifting dumbbells and solving puzzles to sharpen your brain. But that is not what engineers are hired for; they are hired to deliver a system using the best tools available. You can choose to farm by hand while the industry moves to using tractors, but sooner or later, you will be left behind.
And lastly, moving higher in abstraction allows us to tackle even more complex problems—I'd argue much more complex than the narrow puzzles we were facing before. Part of the resistance is simply an avoidance of facing higher-level complexity once the lower tier is automated.
Some developers solve hard problems and some don't. It depends entirely on your specific work.
I have the opposite experience:
* https://repo.autonoma.ca/repo/treetrek/tree/HEAD/render/rule... - syntax highlighting for 40 languages and file formats in ~10 minutes
* https://shufflenblues.com/expenses/ - real-time expenses progress updates with payment vendor API in ~30 minutes
* https://repo.autonoma.ca/repo/treetrek/tree/HEAD/git - real-time, cache-free raw Git reader implementation with cloning in ~5 days
* https://repo.autonoma.ca/repo/notanexus - PDFjs integration in ~3 days
However, these are likely not the "hard" problems you've mentioned. I feel like I can architect solutions at a higher-level now, without having to be completely caught up in many technical nuances. I'd rather not learn the extensive PDFjs API, for example, because it would take weeks of effort to understand.
Why reinvent the wheel? Syntax highlighting, git. I'm pretty sure there are PHP libraries to do that.
Your syntax highlighting is very basic as well. Just ask LLMs to provide tests where it would fail to render correctly.
The first thing that comes to mind after looking at it: print("# not a comment")
I'm not paying someone to dig by hand if a machine makes the job quicker.
This is like reading an article "I Don't Drive Cars" that goes on like
- They're too expensive
- My buddy's 1995 Accord breaks down a lot
- Walking is healthier, plus you can stop and smell the roses
- I enjoy caring for my horse
- Sometimes you can get stuck in traffic
Fine if that's the way you want and can afford to live your life. But it is an exotic luxury belief. For those of us who are participating in the economy for real, the preference to not drive cars is not realistic.
You're going to get picked apart by people who live within walking distance or public transport distance of their office and don't understand why everyone else uses cars.
If you can walk to your office and the temperature is always between 50 and 70 degrees F you would probably think cars are crazy, too.
Which, funnily enough, proves the point even further. Some people get so comfortable in their bubble that they become unable to even comprehend why other people make other choices in other situations.
Checked all five except "caring for my horse" is "tinkering with my bicycle".
Yes everyone that lives in a major city that doesn't use a car is... not participating in the real economy.
Is this bait? What are you talking about? I just use public transport to go to work. Basically, all of those points about cars are correct, except for the last one because here you almost always get stuck in traffic during rush hours. Often buses get to a destination faster than cars because of Bus Rapid Transit.
EDIT: Oh, you are talking just about the US. Then your comparison doesn't make any sense because LLMs are available worldwide.
People write "i dont" when they mean "i cant"
Tbh. Those are all good reasons not to drive. I my self would add:
- They dangerous both to me as a driver, my passengers, and other road users, including pedestrians and bicyclists.
- They ruin cities which constantly have to accommodate ever increasing number of cars by destroying previously walkable neighborhoods to make room for roads and parking.
- They destroy our climate
- They are loud.
- Busses are nicer and I can read a book while riding the bus.
You're welcome to feel that way but it's a luxury belief. In reality, outside of a few (one?) major city in the US with public transportation infrastructure, you need a car. 92% of people own a car, higher if you exclude the dense urban areas I'm talking about.
People only need cars because people have cars and cars make cities worse for everyone outside of one. If nobody owned cars everyone would get by just fine. It's a race to the bottom.
Car ownership is lowest in the lowest income brackets, and public transit ridership is highest among the lower income brackets. I really don‘t understand how you can reach your conclusion that not driving is a luxury. Data would suggest the exact opposite.
EDIT: To clarify on the public transit usage. The data is by-modal. Lower income levels are by far more likely to use road based public transit (such as busses), but high earners are more likely to live near a rail station and use rail based transit: https://cepr.org/voxeu/columns/public-transit-access-and-inc...
> However, the process was far more important than the product (again!). Not every whimsy needs to become a reality.
I mean, I get it, there's different kinds of people out there with different motivations, goals, spare time, etc.
But there's also a process of product design that I think the author is overlooking.
Lately I've been working and iterating on a number of DSLs, projects that might be a total waste of my time because they end up being poorly conceived or not very useful compared to a general purpose language!
I'm also working on a video game that is basically Magic: The Gathering meets StarCraft with Civilization style hex-grid conflict. It could be a total bust and entirely no fun to play (it's hard to tell if it's fun by itself because I enjoy working on the game while testing out the play patterns). It would suck to spend a couple of years on this if it's no good.
I very much enjoy the process of trying to figure out the best syntax and semantics for a new DSL or the process of iterating on gameplay elements when working on a game. The destination is also less important. I don't really expect anyone to use my DSLs or play my video games. I'm ultimately doing it for my own enjoyment.
Saying this, I am interested in the overall architecture and I've definitely learned from my mistakes, especially with creating DSLs. Like, having a TypeScript language server with a Rust runtime has some issues. It's kind of better to build the language server into the runtime so you're not maintaining multiple parsers, and depending on the language features, an additional pseudo-runtime in the language server.
It's a really interesting PoV, and one I'm in polar opposition to.
Context engineering is allowing me to do things I've always wanted to do but don't have the time/energy. I'm writing in C++, assembly, Rust, Go. I'm fucking with boot loaders and all kinds of things.
It's brought me a far greater understanding of how cryptography, GPUs, CUDA, Apple Metal - all topics I have a vague interest in but have no time to work on.
The current raft of LLM models are genius children. It's like that 15 year old at college. But I have 30 years of experience and a genius child is pure power in my hands.
And it's a genius child that never gets tired. For a few hundred bucks a month I can have 3 geniuses working on my ideas through the night. Last night they wrote 20 different research theses on a topic and benchmarked them all. Then combined them into a best of breed algorithm better than anything that has been done before. It's an amazing world we live in.
I don't write this to throw mud at OP - they are entitled to their opinion. Merely to point out the contrast.
I don't agree with the overall conclusion of avoiding AI tooling but this was really wonderfully written
>but this was really wonderfully written
That's because AI wrote it to deter other AI from taking it's job
I taught myself linux/coding/servers because there was a long period of time where all I had was a chromebook for school, but I still wanted to explore this thing called "pure data" that i'd heard about, and thought I could make art with it. I distinctly remember being continually amazed at how you could get so many things for free, if you know where to look. And yeah.. once I found emacs it was all over. To this day I am definitely going to always go "the hard way" where I can instead of pay any SaaS even $5 a month. In my head its like: "I am a mechanic, or at least, I can get by as one, why would I take my car to the shop and pay money??"
I know its not rational, but it would be pretty darn terrible in my brain to pay for an IDE. Even more unimaginable to me to pay $100 a month for something...
All to say, "cheapskate"-ness from TFA really resonated with me, I don't see the sentiment around a lot.
To experienced devs. Why are you enjoying vibecoding? It is soulless and the job is really becoming unbearable having to discuss with an agent that alternates between “good at” and totally consensual and low iq.it feels miserable to have a few turns then seeing the tool Became so bad and so low iq that you stuck in doing things garder than if you did it by yourself
I get the conversational aspect and value of it I just dont get people saying “I dont code anymore I manage agents” - besides obviously people selling AI
programming is just procrastination that gets in the way of implementing your ideas.
"painting is just procrastination that gets in the way of implementing your ideas."
"woodwork is just procrastination that gets in the way of implementing your ideas."
We can find plenty of others, but my main point is that industrializing a process doesn't make it "procrastinating". There are plenty of jobs that are done by machines but are still practiced by humans for multiple reasons. If we think of coding as a means to create, then we have plenty of examples of good reasons to have both the industrialized process and the 'handmade' one.
Where does this evolution really lead?
"Thinking is just procrastination that gets in the way of your opinions"? ;-)
> As someone who grew up in a city on the East Coast
Since this blogsite has a .is domain I must assume they mean Egilsstaðir a lovely city with a population of around 2500 people.
I'm vegan. I only watch PBS and the Criterion Channel. I'm atheist. Now it's "I don't vibe code."
Wait what's wrong with the Criterion Channel??