All of this new capability has made me realize that the reason i love programming _isn't_ the same as the OP. I used to think (and tell others) that I loved understanding something deeply, wading through the details to figure out a tough problem. but actually, being able to will anything I can think of into existence is what I love about programming. I do feel for the people who were able to make careers out of falling in love w/ and getting good at picking problems & systems apart, breaking them down, and understanding them fully. I respect the discipline, curiosity, and intellect they have. but I also am elated w/ where things are at/going. this feels absurd to say, but I finally feel like I'm _good_ at programming, which is insane, because I literally haven't written a line of code myself in months, but having tools that can finally match the speed my ideas come to me is intoxicating
If there was a website called InfiniteAppStore, which contained every app imaginable, and where you could type in your search and it would return the code for that app, would you find that as satisfying to use as Claude Code?
On the surface this does not sound as satisfying, because it more resembles shopping than coding. But once Claude Code is finally tuned to do its job perfectly, you will essentially be using that infinite app store. You're actually using it right now, every time you use Claude Code — just an imperfect version of it.
If you enjoy using AI because it allows you to "will anything into existence", it's because the process is currently imperfect. Using Claude Code is closer to shopping than coding, but because the process is obfuscated, it feels like you're the one making the products in the shopping catalogue every time you place an order.
For folks who are not familiar, this is "The Library of Babel" by Borges. There is no creating, just selecting among characters sequences we already knew were possible.
the library of babel contain all possible books, but people are unable o find the good ones among the sea of random rubbish.
the LLM equivalent would be to prompt "give me an app", without specifying what that app does and then repeating that until you get the app you are looking for, each time, checking by hand if the app does what you want.
I agree. Thinking about it a little more, I've realized that people create things today even if unnecessary (e.g. grow their own food), a lot of it for the satisfaction of it.
So we would still build stuff, but it would not be out of necessity.
Trust me, the two are not the same, and are orders of magnitude different in terms of human satisfaction.
When I walk down a street, I get 10 people stopping me to ask "Where did you get that?". When I tell them I made it, their heads explode. I know which side of that interaction is more satisfying.
We also go all-out for Halloween, and at the big Halloween festival there is literally a line down the street of people waiting to take photos with us. We created something amazing.
In media there was a rule 1-9-90. One creates, 9 comment, 90 use or are silent/don’t care.
Richard Branson realized that a company starts to behave differently when it reaches more than stuff of 135 people that coincides with average number of people you can consider as personally known to you.
Context switching is a bitch. You cannot do it for a long time. Abundance brought by AI will somehow consolidate as people cannot digest everything created by it.
There are more than 45,000 models avail at HF (if I remember it right). Choose wisely :)
If there was an infinite App Store, we wouldn't have scarcity and I'd be doing literally anything else other than selling my time for money. I'd also be killed because there's no point to my owners/the world keeping me around anymore in that scenario, except, maybe for my winning personality/companionship.
I dunno, browsing McMaster-Carr feels like both shopping and creating at the same time.
Typing is just choosing from the latent space something special, too. Could just be random words, or, even fewer, random grammatically correct sentences.
I'd say, you are at the phase of this journey where you're feeling empowered.
It's just one step along the path of AI adoption to execute on an idea and see in near real-time the idea you had baked in your head come alive in front of you. Most of us get to this point and become the biggest evangelists of the tech. I see no reason you should feel guilty for the excitement you're feeling right now, and you should enjoy the journey. You're definitely paying for it in tokens, that's for sure.
However, there will come a point at which you will have successfully willed into existence a novel thing that you always wanted, and there it is, exactly as you dreamed, but by then, you'll be left with a weird empty feeling you won't really have the words for. Maybe it's a feeling of not earning the thing you built, or maybe it's just, your idea is finished and now you have to think of another idea. Certainly, this was your idea though, and it proves you were right, or at least on to something, and it is valuable, to you.
Yet, you didn't go on the journey to get there. You didn't bump up against limitations of the programming language or system and think about workarounds while you were showering or commuting to the office. You basically bought the finished product from the dynamic template marketplace of Anthropic (or whereever), and that's cool that it does what you need. It just isn't really programming, or being a software engineer in the traditional sense.
What used to be something you could potentially leave your day job for to go create a startup with a cofounder over, or maybe sell off to a buyer, or just open source and share with the world, isn't going to have the same meaning. It's a black box of code that you'll need a coding agent to continue working on, keeping that money flowing to Anthropic or whereever.
Anyway, I think the Slot Machine question is where a lot of early adopters are now at in this journey, and once more of us are there, then we can start asking the hard questions. Right now too many of us are where you're at, and it's impossible to know where things will end up in a year or so.
> Going to McDonalds made me realize that the reason I love cooking isn't the actual cooking itself. Being able to order a food at McDonalds and getting it without doing anything myself is the best part about cooking! Now that I only eat McDonalds, I feel like I'm _good_ at cooking.
You do not like and have never liked programming. You wanted to be a manager. They are completely different things.
One size never fits all. I am old enough to remember what a game changer Spreadsheets (VisiCalc) where. They made the personal computer into a SwissArmy knife for many people that could not justify investing large sums of money into software to solve a niche problem. Until that time PCs simply were not a big thing.
I believe AI will do something similar for programming. The level of complexity in modern apps is high and requires the use of many technologies that most of us cannot remotely claim to be expert in. Getting an idea and getting a prototype will definitely be easier. Production Code is another beast. Dealing with legacy systems etc will still require experts at least for the near future IMHO.
That's a lot of words just to say you never liked programming.
You could just as easily make claims about carpentry or cooking because you discovered Ikea or microwave meals. They serve a purpose and technically satisfy the needs of anyone, yet they aren't a good enough solution for anything important. That's where we're at with this tech.
Fair assessment, but you seem to love "creating" rather than "programming", not that there's anything wrong with that! Pondering the merits of AI has made me realize the opposite -- I love the process and challenge of creating (the programming) even more than the final product. AI is undoubtedly helpful, but when it solves my problem for me I'm not nearly as satisfied? as if I'd solved it myself. It's like copy-pasting an answer from StackOverflow, but for a whole program. I doubt my employer will share my feelings, and I'll have to use increasingly more AI to keep up the productivity.
For me the joy comes from the understanding that the answer to "Is xyz possible?" is always, always "yes". It might be difficult, expensive, or take a long time, but my stance as an engineer is that anything is possible.
Hyperbole, yes, many things are in fact, not possible. But most people have the size of the two categories confused. The number of things that are categorically impossible is less than a rounding error compared to how many things are possible.
The joy and wonder of being an engineer is in taking problems deemed "impossible" and creating possibilities. It's in extracting a solution from infinite possibilities and redefining what possible even is.
I heavily use AI for coding, but you cannot skip the understanding part. At some point it falls apart and then you need someone to wade through the results. If you understand the architecture, server and service configuration and how they interact, you can use AI to be quite productive. But you still need the deep level understanding.
Exactly this for me as well. When I was a SWE I thought what I loved was problem solving. So after many years of doing that I decided to move upsteam and took Product roles so that I can identify and address big business problems. It was only after I switched that I realized that I was not in love with problem solving. I was in love with art. Programming was art of me.
I kept at it on the side as a hobby. But stacks evolved and I was left behind. Now with AI it's back on.
I've felt this exact same way until very recently. But in the end, it's slop that never quite does what it's supposed to. Anthropic is proud of themselves that they brute-forced the world's crappiest C compiler into existence. Guess what, nobody will use it.
> but I finally feel like I'm _good_ at programming, which is insane
Yes, it is insane. You couldn't torture this confession out of me. But that's the drug they're selling you, isn't it? You don't even write code, but you're getting a self-inflated sense of worth. It must be addicting! Of course, whether or not the programs you prompt are actually good surely has no relation to whether you feel they're good, since you're not the one writing them, and apparently were not capable of writing them before so are not qualified to review them very much.
> having tools that can finally match the speed my ideas come to me
Anyone can be an "ideas guy". We laughed at those people, because having ideas is not the hard part. The hard part was in all of the hundreds and thousands of little details that go into building the ideas into something actually worthwhile, and that hasn't changed. LLMs can build an idea into a prototype in a weekend. I am still waiting to see LLMs build an idea into something other people use at scale, once, ever, other than LLM wrappers. Either every person who is all-in on vibes only has ideas that consist of making .md files and publishing them as a "meta agent framework", or LLMs are not actually doing a great job of translating ideas into tangibly useful software.
I think this article makes a valid point. However, if AI coding is considered gambling, then being a project manager overseeing multiple developers could also be seen as a form of gambling to a certain degree. In reality, there isn't much difference between the two. AI models are non-deterministic, and humans are also non-deterministic. You could assign the same task to two different developers and end up with entirely different results.
I'd emphasize that prompting LLMs to generate code isn't just metaphorical gambling in the sense of "taking a risk", the scary part is the more-literal gambling involving addictive behaviors and how those affect the way the user interacts with the machine and the world.
Heck, this technology also offers a parasocial relationship at the same time! Plopping tokens into a slot-machine which also projects a holographic "best friend" that gives you "encouragement" would fit fine in any cyberpunk dystopia.
In my corner of the world, average software developers at Tokyo companies, not that many people are actually using Claude Code for their day-to-day work yet. Their employers have rolled it out and actively encourage adoption, but nobody wants to change how they work.
This probably won't surprise anyone familiar with Japanese corporate culture: external pressure to boost productivity just doesn't land the same way here. People nod, and then keep doing what they've always done.
It's a strange scene to witness, but honestly, I'm grateful for it. I've also been watching plenty of developers elsewhere get their spirits genuinely crushed by coding agents, burning out chasing the slot machine the author describes. So for now, I'm thankful I still get to see this pastoral little landscape where people just... write their own code.
It’s variable rewards and even with large models the same question can lead to dramatically different answers. Possibly because they route your request through different models. Possibly because the model has more time to dig through the problem. Nonetheless we have some illusion of control over the output (you we wouldn’t be playing it) but it is just the quality of the model itself that leads to better outcomes - not your input. If you can’t let go of the feeling thought, it’s definitely addictive. And as I look back, it’s a fast iteration on the building cycle we had before AI. But the brain really likes low latency - it is addicted to the fast reward for its actions. So AI, if it gets fast enough (sub 400ms) it will likely become irreversibly addictive to humans in general, as the brain will see is at part of itself. Hope it has our interest at heart by then.
The gambling metaphor often applied to vibecoding implies that the outcome cannot be fully controlled or influenced, such as a slot machine. Opus 4.5 and beyond show that it not only can be very much can be influenced, but also it can give better results more consistently with the proper checks and balances.
Fascinating how HN is torn about vibe coding still. Everybody pretty much agrees that it works for some use cases, yet there is a flamewar (I mean, cultured, HN-type one) every time. People seem to be more comfortable in a binary mindset.
I think "gambling" is a bit too strong, but there is a real shift in how we evaluate correctness. With traditional coding, you reason step by step and with AI-assisted code, you're often validating outputs after the fact.
The risk isn't randomness per se it's over trusting something that looks correct. The skill ceiling is moving from "can you write it" to "can you reliably verify it"
I disagree. I have a successful software product that I vibe coded using claude code starting last June. It does something novel and useful that wasn't yet offered on the App Store or any app on Android.
I am not going to say what it is because all of the AI haters will immediately flock to leave it bad reviews and overwhelm my support systems with bad faith requests (something that has already happened).
I've been writing software for 25 years, I know what I am doing. Every bug I shipped was my fault either because I didn't test well enough or I did not possess enough platform knowledge to know myself the right way to do things. "Unknown unknowns"
But I have also learned better ways to do things and fixed every bug using AI tools. I don't read the code. I may scan it to gain context and then tweak a single value myself, but beyond that I don't write or read code anymore.
Its not a magical few shot prompt then reap profits machine. I just feel like a solopreneur ditch digger who just got a lease on a new CAT excavator. I can get work done faster I can also do damage faster if I am not careful.
I do not think "AI coding" - as distinct from the human who drives it - is gambling. More like a delayed footgun for the uneducated. I don't mean that disparagingly, but I do mean it literally.
I’ve certainly been spending more time coding. But is it because it’s making me more efficient and smarter or is it because I’m just gambling on what I want to see?
Is this really a difficult question to answer for oneself? If you can't tell if you're learning anything, or getting more confident describing what you want, I would suggest that you cannot be thinking that deeply about the code you're producing.
Am I just pulling the lever until I reach jackpot?
And even then, will you know you've won?
At the very least, a gambler knows when they have hit jackpot. Here, you start off assuming you've won the jackpot every time, and maybe there'll be an unpleasant surprise down the line. Maybe that's still gambling, but it's pretty backwards.
Obviously the following isn't a completely original take, but it's worth stating that AI coding is just a fundamentally different job than "traditional" or "manual" coding. The previous job was to spec something out to a comfortable degree without spending all of your time on a spec when there are so many unknowns that will come up during the engineering stage. Then, the job was to engineer at a snail's pace (compared to today) and adjust the spec.
Now, the job is to nail the spec and test HARD against that spec. Let the AI develop it and question it along the way to make sure it's not repeating itself all over the place (even this I'm sure is super necessary anymore...). Find a process that helps you feel comfortable doing this and you can get the engineering part done at lightning speed.
Both jobs are scary in different ways. I find this way more fun, however.
I hear it a lot but this gambling analogy breaks when you look at actual outcomes. If you went to Vegas and after a few pulls on a one-armed bandit could _reliably_ walk away with the jackpot we wouldn’t even call it gambling anymore.
Assigning work to an intern is gambling: they're inherently non-deterministic and it's a roll of the dice whether the work they do will be good enough or you'll have to give them feedback in order to get to what you need.
For me, the feedback loop accelerating the way that AI now permits is so addictive in my day-to-day flows. I've had a really hard time stepping away from work at a reasonable hour because I get dopamine hits seeing Claude build things so fast.
Addiction and recovery is part of my story, so I've done quite a bit of work around that part of my life. I don't gamble, but I can confidently say that using LLMs has been an incredible boost in my productivity while completely destroying my good habits around setting boundaries, not working until 2AM, etc.
Bespoke suits are still a thing. Meaning where the highest quality is desired or valued, things still get handmade, and the rest of the time it happens on a factory line.
I suppose what's happening with software development is we're exploring where the line between the two is going to land. It's pretty clear that something like a simple and generic website can be reliably vibecoded, but on the other extreme I wouldn't expect the software for something like a space shuttle to be vibe coded due to the stringent safety requirements.
431 comments
On the surface this does not sound as satisfying, because it more resembles shopping than coding. But once Claude Code is finally tuned to do its job perfectly, you will essentially be using that infinite app store. You're actually using it right now, every time you use Claude Code — just an imperfect version of it.
If you enjoy using AI because it allows you to "will anything into existence", it's because the process is currently imperfect. Using Claude Code is closer to shopping than coding, but because the process is obfuscated, it feels like you're the one making the products in the shopping catalogue every time you place an order.
the LLM equivalent would be to prompt "give me an app", without specifying what that app does and then repeating that until you get the app you are looking for, each time, checking by hand if the app does what you want.
>
In that scenario the 'joy of creation' would just shift to the 'joy of discovery'. Both of which are innate to humans.They may be innate, but that doesn't mean they are related or that one is a good substitute for the other.
So we would still build stuff, but it would not be out of necessity.
When I walk down a street, I get 10 people stopping me to ask "Where did you get that?". When I tell them I made it, their heads explode. I know which side of that interaction is more satisfying.
We also go all-out for Halloween, and at the big Halloween festival there is literally a line down the street of people waiting to take photos with us. We created something amazing.
People aren't going to line up for slop.
Richard Branson realized that a company starts to behave differently when it reaches more than stuff of 135 people that coincides with average number of people you can consider as personally known to you.
Context switching is a bitch. You cannot do it for a long time. Abundance brought by AI will somehow consolidate as people cannot digest everything created by it.
There are more than 45,000 models avail at HF (if I remember it right). Choose wisely :)
>But once Claude Code is finally tuned to do its job perfectly, you will essentially be using that infinite app store
You really believe that? What has lead you to the conclusion that LLMs will ever be capable of that?
Typing is just choosing from the latent space something special, too. Could just be random words, or, even fewer, random grammatically correct sentences.
It's just one step along the path of AI adoption to execute on an idea and see in near real-time the idea you had baked in your head come alive in front of you. Most of us get to this point and become the biggest evangelists of the tech. I see no reason you should feel guilty for the excitement you're feeling right now, and you should enjoy the journey. You're definitely paying for it in tokens, that's for sure.
However, there will come a point at which you will have successfully willed into existence a novel thing that you always wanted, and there it is, exactly as you dreamed, but by then, you'll be left with a weird empty feeling you won't really have the words for. Maybe it's a feeling of not earning the thing you built, or maybe it's just, your idea is finished and now you have to think of another idea. Certainly, this was your idea though, and it proves you were right, or at least on to something, and it is valuable, to you.
Yet, you didn't go on the journey to get there. You didn't bump up against limitations of the programming language or system and think about workarounds while you were showering or commuting to the office. You basically bought the finished product from the dynamic template marketplace of Anthropic (or whereever), and that's cool that it does what you need. It just isn't really programming, or being a software engineer in the traditional sense.
What used to be something you could potentially leave your day job for to go create a startup with a cofounder over, or maybe sell off to a buyer, or just open source and share with the world, isn't going to have the same meaning. It's a black box of code that you'll need a coding agent to continue working on, keeping that money flowing to Anthropic or whereever.
Anyway, I think the Slot Machine question is where a lot of early adopters are now at in this journey, and once more of us are there, then we can start asking the hard questions. Right now too many of us are where you're at, and it's impossible to know where things will end up in a year or so.
> Going to McDonalds made me realize that the reason I love cooking isn't the actual cooking itself. Being able to order a food at McDonalds and getting it without doing anything myself is the best part about cooking! Now that I only eat McDonalds, I feel like I'm _good_ at cooking.
You do not like and have never liked programming. You wanted to be a manager. They are completely different things.
I believe AI will do something similar for programming. The level of complexity in modern apps is high and requires the use of many technologies that most of us cannot remotely claim to be expert in. Getting an idea and getting a prototype will definitely be easier. Production Code is another beast. Dealing with legacy systems etc will still require experts at least for the near future IMHO.
You could just as easily make claims about carpentry or cooking because you discovered Ikea or microwave meals. They serve a purpose and technically satisfy the needs of anyone, yet they aren't a good enough solution for anything important. That's where we're at with this tech.
> but I finally feel like I'm _good_ at programming, which is insane, because I literally haven't written a line of code myself in months
This is exactly the sort of mentality that makes me hate this technology
You finally feel good at programming despite admitting that you aren't actually doing it
Please explain why anyone should take this seriously?
Hyperbole, yes, many things are in fact, not possible. But most people have the size of the two categories confused. The number of things that are categorically impossible is less than a rounding error compared to how many things are possible.
The joy and wonder of being an engineer is in taking problems deemed "impossible" and creating possibilities. It's in extracting a solution from infinite possibilities and redefining what possible even is.
I kept at it on the side as a hobby. But stacks evolved and I was left behind. Now with AI it's back on.
> but I finally feel like I'm _good_ at programming, which is insane
Yes, it is insane. You couldn't torture this confession out of me. But that's the drug they're selling you, isn't it? You don't even write code, but you're getting a self-inflated sense of worth. It must be addicting! Of course, whether or not the programs you prompt are actually good surely has no relation to whether you feel they're good, since you're not the one writing them, and apparently were not capable of writing them before so are not qualified to review them very much.
> having tools that can finally match the speed my ideas come to me
Anyone can be an "ideas guy". We laughed at those people, because having ideas is not the hard part. The hard part was in all of the hundreds and thousands of little details that go into building the ideas into something actually worthwhile, and that hasn't changed. LLMs can build an idea into a prototype in a weekend. I am still waiting to see LLMs build an idea into something other people use at scale, once, ever, other than LLM wrappers. Either every person who is all-in on vibes only has ideas that consist of making .md files and publishing them as a "meta agent framework", or LLMs are not actually doing a great job of translating ideas into tangibly useful software.
Heck, this technology also offers a parasocial relationship at the same time! Plopping tokens into a slot-machine which also projects a holographic "best friend" that gives you "encouragement" would fit fine in any cyberpunk dystopia.
This probably won't surprise anyone familiar with Japanese corporate culture: external pressure to boost productivity just doesn't land the same way here. People nod, and then keep doing what they've always done.
It's a strange scene to witness, but honestly, I'm grateful for it. I've also been watching plenty of developers elsewhere get their spirits genuinely crushed by coding agents, burning out chasing the slot machine the author describes. So for now, I'm thankful I still get to see this pastoral little landscape where people just... write their own code.
Know when to Re-prompt,
Know when to Clear the Context,
And know when to RLHF.
You never trust the Output,
When you’re staring at the diff view,
There’ll (not) be time enough for Fixing,
When the Tokens are all spent.
The risk isn't randomness per se it's over trusting something that looks correct. The skill ceiling is moving from "can you write it" to "can you reliably verify it"
I am not going to say what it is because all of the AI haters will immediately flock to leave it bad reviews and overwhelm my support systems with bad faith requests (something that has already happened).
I've been writing software for 25 years, I know what I am doing. Every bug I shipped was my fault either because I didn't test well enough or I did not possess enough platform knowledge to know myself the right way to do things. "Unknown unknowns"
But I have also learned better ways to do things and fixed every bug using AI tools. I don't read the code. I may scan it to gain context and then tweak a single value myself, but beyond that I don't write or read code anymore.
Its not a magical few shot prompt then reap profits machine. I just feel like a solopreneur ditch digger who just got a lease on a new CAT excavator. I can get work done faster I can also do damage faster if I am not careful.
Beyond this concern,
At the very least, a gambler knows when they have hit jackpot. Here, you start off assuming you've won the jackpot every time, and maybe there'll be an unpleasant surprise down the line. Maybe that's still gambling, but it's pretty backwards.
Overall I’m a fan, but yes there are things to watch for. It doesn’t replace skilled humans but it does help skilled humans work faster if used right.
The labor replacement story is bullshit mostly, but that doesn’t mean it’s all bad.
Now, the job is to nail the spec and test HARD against that spec. Let the AI develop it and question it along the way to make sure it's not repeating itself all over the place (even this I'm sure is super necessary anymore...). Find a process that helps you feel comfortable doing this and you can get the engineering part done at lightning speed.
Both jobs are scary in different ways. I find this way more fun, however.
Addiction and recovery is part of my story, so I've done quite a bit of work around that part of my life. I don't gamble, but I can confidently say that using LLMs has been an incredible boost in my productivity while completely destroying my good habits around setting boundaries, not working until 2AM, etc.
In that sense, it feels very much like gambling.
I suppose what's happening with software development is we're exploring where the line between the two is going to land. It's pretty clear that something like a simple and generic website can be reliably vibecoded, but on the other extreme I wouldn't expect the software for something like a space shuttle to be vibe coded due to the stringent safety requirements.