I have come to realize that code (and I think possibly productivity in general) being expensive was always a feature. I am sure that a few great ideas did get lost to obscurity due to lack of access to resources to build them out. However, we now have an absolute deluge of complete and utter shite.
Agreed, for the individual LLMs can be powerful to let less technical folks build and customize their software - at an org level I reckon we'll start seeing more sinking ships as that bottleneck was actually helpful at limiting the flow of lackluster features to prod.
We didn't need LLMs to come up with the genius idea of making every desktop app a web browser.
Software quality was in terminal decline already, the only hope is that LLMs get good enough to dig outselves out of the several miles deep hole that has been dug.
Won't there also be a point were you're shipping so fast that that in itself deteriorates UX? What if a page literally changes every time I reload? What if it changes mid-checkout process and the deal I agreed to 5 seconds ago does not exist anymore?!
First you take your Blendtech and "will it blend" your engineers, then upload the result to the cloud inside what is called an S3 bucket (don't forget to set access permissions on your buckets kids!) to be digested by the clankers, sit back and profit!
Dark humor aside I think disconnecting a bunch of problem solvers from their computing equipment could really enhance the world, putting that analytical power into the world in person could move a lot of cogs, rather then marshalling JSON.
Spent few minutes reading the infomercial -- regretted it. Engineering principles form the bedrock first, and AI-tools are made to fit in them, not the other way around as this infomercial propounds. Its linkedin vibe is a big turnoff too.
This post is funny to me, because I feel it falls well short of what a proper, forward-thinking "AI-native" engineering org would actually look like. That is, the author is presenting this as kind of a radical departure from normal engineering, but I just see it as normal engineering with more AI. I don't see that as AI-native.
To me, true "AI-native" engineering will be one where questions regarding how humans will do things like review code are irrelevant. You explicitly throw away any concept of typical software engineering and, instead, differ to the AI. Your job, as a human, is solely to do what the AI can't physically do. That's not the same as closing gaps between what AI is currently capable of doing and what you'd need it to be capable of doing. It's literally enforcing that anything an AI is able to do is treated as correct in itself, and you, as a human, only support it by being a human.
If that sounds outlandish, that's because it is. We don't have such capable AI systems yet. It's possible we never will. But that's beyond the point. The reality is trying to make an "AI-native" engineering org by just layering AI on top of existing processes and systems is futile. If your expectation is that AI will continue to improve in capabilities at an accelerating rate, then these stop-gaps are pointless. You might as well just ignore AI altogether until it is able to completely take over, because that's the inevitable goal, right?
If you're willing to buy that will be possible, then my guess is that it will occur in the form of small scale startups and actual mavericks rather than someone trying to run an existing business who will simply be too risk adverse to go all in when the time comes. Some guy in his basement is more likely to leverage AI "properly" to build an actual "AI-native" engineering org because that person won't have much to lose.
I think this is all fair, but somewhat just semantics.
Most engineers are working in "normal" engineering orgs, but can feel the ground underneath them shifting, and companies believe that if they are caught flat footed, they will be out competed in the marketplace, so they are all trying to make sure they are adopting it at least in a way that lets them keep pace if not accelerate revenue.
If you are not impacted by economic incentives, you can continue to not care about this transitional state, but most people do.
Are there any companies outside of the "AI shovels" business that make more money because of AI? Every time I ask someone why they went so hard on adopting AI, I hear the same story about the fear of losing the market share or becoming less competitive. Honest question, who is benefitting from all of this? The revenues at majority of companies seem flat at best. There is a growing concern about professionals getting deskilled, the job satisfaction is not improving, wages are stagnant. Mind-boggling that we are actively engaged and often push for this experiment that hurts our own profession. Cheering for our own demise.
I use AI compatibility as a metric when evaluating new software to add to my stack. If an AI agent isn’t able to do most of what you can do in the app by opening it, I prefer to look for other options.
Does not apply to everything though. E.G: I don’t care about AI support for my non work chats/email, since I’d rather not give it access.
Not keen on outing myself by providing evidence, but I think we do generate more revenue by using AI. We launched new products with a small team and also optimized our outcome-pricing based product using AI several times. We also reduced costs by self-hosting more software.
But we're a tiny baby startup, so things like "spin up a new product with 1 engineer and get to $1m in revenue on it" or "reduce our IaaS bill by 300k/yr" is a meaningful contribution for us.
We're also building new AI-enabled software that was not possible before.
The big breakout hits have been AI Infra, but that makes sense from a technological perspective, Cisco made a lot of money well before Google did, but Cisco is not where the money concentrated in the end.
We don't really know what the equivalent of Google as an application business will be in the AI era, but there's a pretty big chance it's not actual Google. But Google still has to do it's best to hold on.
Engineering’s job has always been to deal with hard technical challenges and apply new technologies.
Writing code was never the point. Predictably creating specific outcomes was. Wrangling AI in a way that multiplies productivity is the new job.
I won’t lie, it kind of sucks to be young right now, learn about punch cards and assembly in school, and then graduate into a market that’s moved on to Fortran. Sorry, I meant high level languages and AI. To say otherwise might imply the industry has seen a similar shift in the past where engineers made the exact same complaints practically verbatim.
Regardless, the reality is that college teaches very little about 90% of real engineering work anyway, and we still need to hire smart people for this new type of work.
Reminds me of a few things, like being a meat proxy, as well as books like Company of One or Million Dollar One Person Business, and these were published before AI so right now we will see companies with only one founder and hundreds to thousands of AI agents. There already was that drug delivery company with the one founder but apparently a lot of their revenue was fraudulent. Still, it proves the point that it is possible.
I was misremembering, they were sued for spam laws, not for their revenue being fraudulent so it seems it's legitimate, making a billion in revenue with one person (and later on his brother who was hired), the rest is all AI.
Deferring everything to AI is not forward thinking; it's digging your own grave unless you're the founder and CEO, 'coz everything else has been automated, right?
If you follow this logic, we get to the true "AI-native" engineer which is ecstatically floating in a bath of dopamine-stimulating liquid, while AI reads their brain pattern and instantly builds everything they didn't even form a full thought about.
"If that sounds outlandish, that's because it is. We don't have such capable AI systems yet."
IMO most modern engineering practices are cargo culture. I’m sure in 10 years we look back on today the same way we’d look back on the days before version control was common. We are in the emailing files around stage of development
The reality here is even more idiotic: someone criticizing a company for a terrible strategy they aren’t using that wouldn’t work if they did. According to the critic!
> I feel it falls well short of what a proper, forward-thinking "AI-native" engineering org would actually look like. That is, the author is presenting this as kind of a radical departure from normal engineering, but I just see it as normal engineering with more AI. I don't see that as AI-native.
A company which proclaims they are "AI-native" isn't actually interested in engineering, they are trying to ride the hype wave. Companies who care about engineering just... do engineering, and don't make a big deal out of whether they are chasing trends.
> If you're willing to buy that will be possible, then my guess is that it will occur in the form of small scale startups and actual mavericks rather than someone trying to run an existing business who will simply be too risk adverse to go all in when the time comes. Some guy in his basement is more likely to leverage AI "properly" to build an actual "AI-native" engineering org because that person won't have much to lose.
FWIW I think the company writing this post is one of those small scale startups. But that being said, you're not the only one who thinks this. A decent amount of VCs and funds think that only smaller, newer companies have the potential to be truly AI native because there's too much organizational inertia in an existing business in keeping its existing human processes and so only a newer company can achieve the true "scaling potential" or using AI to scale without human labor.
It this point, a whole lot of teams have been leaning into AI-first, not-entirely-reviewed code since around March this year.
That means we are already 6-8 months in, and not far from having a full year of experience of what that actually looks like, albeit weirdly influenced by the increase in model capabilities during that period.
I'm looking forward to those retrospectives. Did this turn out to work OK for the teams doing it? What were the biggest failings and/or surprises? With hindsight, did this produce good quality software?
I think the biggest shift is in predictability. Will something be done today, next week, or next month - nobody knows. Will we converge on a bug free state? not sure.
So far AI works great at fast moving work which you will probably recode or throw away in a month or two anyway (e.g. a startup) but is weak at maintaining a large code base that you rely on. At least part of this is cultural, as the cost of misalignments between team members can be quickly translated into broken software.
Have been at it since Nov 23rd 2025 with a first commit with Opus 4.5 - it was rough at first but after about year well worth it. You can also tell where so many just get stuck in the mud due to lack of direct experience with all the engineering silos (from bare metal sys admin to QA eng silos outside of standard software engineering core) it takes to roll out a new kind of technology company while scaling a new kind of commercialization model, also managed by AI and AI native from the ground up.
It describes a team spending 30x payroll on tokens - $3,000,000 in token spend per month - building a multiplayer game where incidents and bug reports from users are passed directly to Fable 5/5.1 agents who then act on them and deploy the changes to production.
"We consider it an outage if we don't ship every hour"
It's worth reading because it's either a complete disaster or a glimpse of the future, or quite possibly both.
This works as we've been doing it since Opus 4.5 (Nov 2025) with every user request, feature and bug. It's the future without a doubt. The feedback loops evolve and get stronger depending on how well you fine-tune or train your system to optimize on its own.
This from that tweet stood out to me: "In general, we've seen that OpenAI's models game their own checks"
In the past when working on agentic stuff I've observed models gaming checks aggressively, to the point that when we were validating log files to see what the agent had done, the agent responded by editing the log files to pass validation. I can only imagine how bad that kind of behavior is at scale, and it sounds like they ran into it.
well, i did go check out the company spawn from the article. its certainly interesting how hands off their process is and how much they ship, but holy shit the games were fucking horrible. there was a direct WoW ripoff (right down to the assets) that was unplayable, a racing simulator where my controls stopped working 10 second in, and some sort of RPG that i started and just never loaded. so i will take what they are saying with the heaviest possible grain of salt.
Yes exactly this is my standard for everything now. You can spend an unbelievable amount of tokens doing all kinds of things that are interesting as processes in their own right.
This is amazing and somewhat insane. It's more like they are building an organism with an immune system than a code base. Interesting that they say only Fable works for them.
> A default that made Savi think longer on every message, landed at 10:22pm and reverted by 10:40pm: that's not right, undo it it's too slow and not jazz.
I giggled on that one. It feels like children playing having a job. If they pay that much for tokens they have to have at least 80k customers paying 50$ a month. Seems huge for something like that. Or they have a lot of investors. Anyway does not feel like something going anywhere.
This is a complete and utter disaster. They are making spam games. Like miniclips but for spam. A semi functional website to make what is basically youtube playables.
And it's devouring tens of millions. I know what tens of millions can make in the video game industry, it can keep a small team of good devs and designers and artists making something special that's _really_ enjoyed by tens of thousands of people.
We don't want more games, we want more great games. This will never, ever, make great games.
Look on ye mighty, and despair. I really don't care how this sausage was made because the only thing you need to know is that it shouldn't ever have been made.
As a (light) gamer for two decades who has been reading about the gaming industry for the past few months, I cannot understate how hard it is to create a good game, let alone a great game. So much money was spent/wasted on hopeless endeavors.
Oh it's Jacob - I used to work w/ him on his acquired startup, Pluto. He was very AI-pilled; I'm not surprised at the results. I remember wading through the AI-generated Python he had written. I think Pluto had something like 500k or 700k lines after 18mo. Everything was duplicated; there was no reuse of anything. Dozens of features, which mostly worked, not all did.
As a product that I would regularly use, Pluto missed the mark for me. As a SWE in 2023, I couldn't meet Jacob's mentality. Today, it's how a lot of us ship software.
I didn't love the product but I have to respect the process: he was able to sell his company. For some, what he did is success.
That’s the dumbest thing I’ve ever read. Spaffing millions per month on this slop is the kind of thing people suffering from AI psychosis do. There is no way you need “thousands of agents” to build any product.
The more agents you throw at something, the more they collide. Those collisions generate more slop, which requires further slop processing agents.
I don't get the obsession with more code. Whatever happened to good development practices? Many of which, if followed allow LLMs to work more efficiently ironically enough. I would rather hear that you've fixed bugs that have stumped your dev team for years, and have had next to no outages, to me that's more valuable than just slopping features out the door.
it really isn't a flex ppl think it is when they're burning tokens churning agents that are working for "hours" doing work
we don't need to read or write code anymore, but we do need to write (as humans) the instructions for agents.
having ADRs, product specs, acceptance criteria, etc. that are properly maintained leads to agents working for just a few minutes and pumping out reliable code.
the more vague the work for agents, the more randomness and inefficiency there will be. that leads to bugs, constantly re-writing code, etc.
imo ofc, i'm not yet running a billion dollar company so maybe i'm wrong.
Can you please point me to any project based around spec-driven development with agents which has worked well long-term, ideally one that isn't another agentic devleopment tool?
While I agree with your sentiment, very strongly actually, there has always been a tension between what I'll call "engineering teams" and "product teams". The engineering teams want the long-term platform stability, performance, etc. The product teams want to push that new feature out, quick! The overall business needs both (types of thinking and doing) to survive, of course, but not all leadership sees the world through the lens engineering team lens. I'd argue most actually lean the other way, which is understandable though unfortunate. I'd also posit that since these product teams are often "closer to the business", those people typically win favor with the real decision makers.
Features don’t usually come from product teams. They come from above: some Head Of, VP Of, and the like. Those people only ask, they know very little about execution. They want their wishes come true in a timely manner
Management/Product/Product Engineer - When you are responsible for getting the work done then you look for any and every option to speed it up.
Owner/Platform/Senior Engineer - When you are responsible for ensuring it works and can be maintained then you have to pay attention to how to build it, aka the trade offs
I'm lucky I guess, I feel like the product team is on "my side" with respect to building a resilient system. They understand that bad architecture shows up as a fragmented and friction-full UX.
The demand for new features come from sales and executive people who want to check more boxes on a customer's checklist.
Ultimately your paycheck exists through deals that involve those boxes on checklists. It doesn't simply materialize out of thin air. If there are no deals, it doesn't matter how robust and elegant the architecture is.
If you build your platform well, then you can execute fast, but also safe.
I push "money and data are sacred"; if we lose either of those, someone cries. Build the platform slow and fast. Governance, scaling etc sits here.
Provide reference APIs and let the product team one shot whatever they want and need, build fast and experimental, but your platform enforces constraints.
Best of both worlds (though feels like we're back in backend vs frontend development)
>If you build your platform well, then you can execute fast, but also safe.
this is extremely true, but it seems less and less like anyone wants to invest in a solid platform and just wants to jump to executing fast and unsafe. and then pretends that ai can definitely do both when the experience is quite a bit different.
I have seen at least one example develop in real time. You typically spent years building before you had a platform, then lack the enthusiasm from senior leadership to invest the next 12-18 months with no new features and hard to quantify - maybe no - returns. Then you get displaced by newcomers who are "platform native"; what this really means is their engineering misteps haven't been discovered yet, or even if they guessed correctly the world has turned and made their previously correct solution now a failing one. And now we have something called "AI-native" that is going to solve this once and for all with some sort of magic, and you can't lead these companies unless you truly believe in the magic.
“ You typically spent years building before you had a platform, then lack the enthusiasm from senior leadership to invest the next 12-18 months with no new features and hard to quantify - maybe no - returns.” —> this is failure from the team and especially people who should do product management job on that team.
This tension is why I refer to myself as a product engineer. Teams where non-technical product managers (ie. your "product team") become feature factories that eventually drown in their own tech debt. Teams where navel-gazing engineering managers (ie. your "engineering team") have too much power end up with premature platformization, and beautiful architecture diagrams while user needs go unmet.
The key is to understand that computers exist to serve human needs, and the less code / UI / hoops to solve a problem the better, and to think end-to-end. If you are able to do that, most systems built by committee have a lot of low-hanging fruit that can be improved without much sacrifice. In practice, political realities and operational concerns may come in the way, but I firmly believe this is the only way to successfully operate as an engineer, and it will only become more important in the age of AI.
And I feel that stuff like agile is now even more important than before. Now it’s role should be more about protecting customers from bad changes and following whole processes through where you actually measure the impact. It’s just too easy to do those 100k lines changes to products because it’s some vice presidents pet project.
One thing I've spotted several times throughout this year: the larger volume of code leads to exactly the sort of problems it always has. It just happens real fast now, with fewer people. Problems that used to take years to erupt now manifest before an MVP ships, but people just sweep it all under the rug in the name of moving fast.
The rate at which software is produced has never been higher, nor has the rate at which it is thrown away for being broken and useless. It’s not at all obvious to me that if you control for both of those rate changes that the amount of useful software with a lifespan measured in years created per developer (ie, the software that actually has long term value) has actually changed all that much.
I've spent most of the past two weeks trying to get my AI to stop writing so goddamned much code. It's great that I can, say, completely switch between two databases, but I wish the AIs would develop a concept of energy spend or something and spend maybe a moment checking whether something is already implemented in the code base before blasting out 2000 new lines defining a new database access layer, and also rewriting random code it shouldn't be touching for some task hundreds of lines at a time just because it can. I don't care how easy it is to write some tests that sort of kind of cover it hopefully maybe... no new code is as tested as the stuff that has been doing it in the field for years already.
Just because it has the power doesn't mean it should be used.
I'm not asking for everything to be some sort of beautiful code whose concision would lead Knuth to tears. I'm just asking that you not slather dozens of existing functions with three new parameters and dozens of lines of code each that basically do nothing, to cover a use case that I accidentally vaguely alluded to, if you read my prompt a certain way, but isn't really what I was interested in.
Right. There IS a way to convince ai to write less code.. but it obviously spends 10x tokens, whether it’s LLMs as judge and automated review or just write 10 solutions and keep 1. Partly ai companies like it this way but partly it’s unintentional consequences that happen to work in their favor.
Training for good taste in architecture actually causes premature optimization at high effort allowance, but at the same time, it is combined with an inability to even recognize / exploit that later if it should ever become actually useful. Dial the effort down, and it skips the reasonable abstraction and nothing is dry, factoring is insane.
Goldilocks for simple stuff barely works with frontier models after they are out of their comfort zone for topic or line limits.. you kind of just have to decide whether it’s worth it anyway. In practice.. constant supervision for high quality code, or such high quality system design that the code quality is less of a down side.
We used to understand that code was harder to read than it is to write. It follows, directly, that better engineering discipline means shipping LESS code. Less to support, less to understand, means a product that is easier to maintain and extend.
Now, token calculators spew out code at a pace no human can match, which completely removes the barrier of effort - which was one of the largest natural counters to shipping massive amounts of slop.
I'll be impressed by a coding model when it writes less code than a human, and spends more time refactoring than it does just adding new layers. Until then, this vibecoding is just madness.
I drastically improved the reliability of an internal IoT device so it can tolerate all kinds of abuse (abrupt power loss during update, unreliable SD card, bootstrapping over network when the SD card is missing/damaged, fail-safe updates, recovery in a network isolated environment). This is the first release that I really leaned into AI, having been pretty skeptical before.
I think AI has been a net positive and has been used responsibly at my work. It can be used to make existing products better and more secure. You just won't naturally hear about that. There's some challenges like emerging social mores but overall good.
> It can be used to make existing products better and more secure. You just won't naturally hear about that.
Why? I keep asking for examples of LLM being used to make code more simple and elegant (which I would say is adjacent to making software better, if not more secure), and never get a reply, not a single one. I'm not claiming it doesn't exist, I know it must exist. If only via a lots of careful massaging of system prompts and harnesses, even if it takes too much effort to be worth it, I would like to see it.
Of course people can't share internal examples, but this is all over the world for many months now, where are the open source examples? Not "something new someone couldn't have done before", but someone making their precious even neater (while also adding things to it, but not primarily). Put differently, can LLM delete code, can they curate it well, can they not write weird comments nobody wants or needs, that sound like echoes of the user prompts and responses to them, but just explain tricky parts of the code, like a human would?
Also, IMO a VERY useful thing to learn about a tool or a chemical or whatever is, "what happens if I keep applying it to the same small thing over and over?" -- because that's the level of scientist I never evolved past, the kind of stuff you do as a kid -- , whereas a lot of this seems to be more about how it feels to apply it here and there until it looks good, and then move on and never look back. Which really isn't much at all, especially given we're such a short time in. I mean, how useful were mugs made of lead? Are people aware of the (in hindsight) insane things that were done with x-rays as those were invented, before the potential for harm was known? I bet they had a great time playing with that stuff, for a while.
What if in 5 years it turns out that a few years ago, LLM got into this habit of implementing certain things in a certain way because it seemed the best to "them" (the training, whatever), but there's a security issue with that -- what do you do? You can only let more agents loose, and hope they don't miss anything, because you cannot even do something like "patch PHP" (which is not my thought, Casey Muratori mentioned that in on of those podcast things).
Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though. It just does, like suggesting we go to Mars, because everything is better there, and to do that, we have to blow up Earth. Or saying to magically be able to fly from now on, we need to saw off the branch we're sitting on. Even if I thought life on Mars was the future or that we could fly, if we just thought of it the right way, this isn't a way forward IMO.
You want them to make code more simple and elegant by themselves, no other direction? "Make this code simple and elegant, no mistakes, no hallucinations"? I don't think that's realistic at the moment.
But with suitable direction, they can definitely improve codebases - especially a typical enterprise codebase, which, if you don't like LLM code, you would hate with a passion. (I can only assume you've never seen such code otherwise your perspective would be different.)
> Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though.
I essentially agree, but there's a huge spectrum before you get to that point, and lots of ways to use it effectively that doesn't create tech debt.
> You want them to make code more simple and elegant by themselves, no other direction?
No, he wants a project where AI is used as a major help, but the result tend towards good code, i.e readable and well abstracted. Even if the cost is high, just an example where you can extract the best practices of using AI coding.
You are responding to someone that just today generated thousands of lines of code, claims to have reviewed it all, thought it was good and only wanted one minor change. Surely they have an example of the good code it produces.
The code in question was split into modules, the largest of which was about 500 lines. Overall, the quality was higher than a lot of unaided human code that I've reviewed.
That code is greenfield code, so doesn't fit what was being requested above. But here's an example that illustrates the point I mentioned about functional pipelines:
This particular fragment is parsing input using the Chumsky parser combinator library. That imposes a structure that has to be followed. It's all heavily type-driven, which means that it's naturally structured as type cases, where each case handler is pretty small. The longest one in this code is around 20 lines, but most are more like 5 lines or so.
As a result, the modules, functions, and case handlers naturally follow the single responsibility principle. This makes it easy to review. Again, this goes to the points I made in my other comment - if you give a model a good type schema, have it use good libraries in a good language, so that it has a well-structured framework in which to operate, you're likely to get good results.
Perhaps a simpler way to describe it is the old saying, "garbage in, garbage out". If you're vibe coding, say, PHP you're much less likely to get the same quality results.
> LLM being used to make code more simple and elegant
Simple and elegant generally doesn't come from the LLM. It comes from me saying no to the LLM. I've discarded many branches that didn't feel like they were going the right way. Hell, I aggressively do that with my own code also. I rarely commit the first thing that works.
> where are the open source examples?
My general impression of open source is that it is, in part, a market driven by good software engineering. There's certainly below average code, but that tends to get mocked out of existence before it grows too much. Proprietary code that doesn't have a strong forcing function used to be able to hide poor engineering principles.
I think AI generated code is a regression to the mean, and the mean can be an improvement sometimes. I inherited this project. It was not originally written with AI. A lot of hard work and good engineering went into the hardware/firmware. The IoT software connecting it to our intranet, less so. Some examples that I'm fixing/fixed: ignoring HTTPS certificates, RCE by design, in-place file updating JSON files, a hand-rolled (but ineffective) fair mutex, busy waiting for a device to appear, and worst of all, no tests. None of these are hard to avoid, and even the small AI models would have come up with a better implementation.
This doesn't seem unique to my project either. I think a lot of software is just silently getting closer to the average of all open source code upon which the models were trained. I don't think I want things like SQLite to get closer to the average.
> Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though.
I think you might be reading too much into what I said. When I say "fully lean into", it's probably less than you're thinking of. I still feel that I understand what was written and can stake my reputation/career on it.
> I think AI has been a net positive and has been used responsibly at my work. It can be used to make existing products better and more secure. You just won't naturally hear about that. There's some challenges like emerging social mores but overall good.
It always works best when layering on top of good human code. The thing is, you start to run out of that as you lean in. Tricky.
> The thing is, you start to run out of that as you lean in. Tricky.
I think it depends how you lean in. I generated a few thousand lines of Rust code today. It was actually pretty high quality. On my initial review, I only identified one change I wanted to make.
Most functions were pretty short and well factored. I wonder if using Rust as a target helps, because (1) the training data doesn't include all the terrible Javascript and Python etc. found on the internet, and (2) Rust and many of its libraries encourage good architecture - code factored into traits, functional pipelines, a powerful type system, etc.
LLMs trained on bad code for mediocre languages naturally write corresponding quality code.
A big part of it still boils down to prompting - what you're asking it to do and how much freedom you give them. If you let them make all the architectural decisions, you're likely to end up with issues.
Heh, you should look at the reply I left for your sibling comment. I think it is just a regression to the mean of all open source software upon which the models were trained. Sometimes the mean is an improvement.
Hell, if the Dunning–Kruger effect is to be believed, it would be bold me to assume I am capable of good human code. Maybe the average is the best I'll ever get.
1. The issue is that most people and organizations do not care about maintenance. Maintenance doesn’t get you the promotion, accolades, or immediate quarterly revenue because great maintenance tends to be invisible.
2. This is exacerbated by the lack of loyalty people have towards their organizations because their orgs don’t value or reward loyalty. That’s because leadership doesnt care about the long term view because of item #1. Hence, everyone is only doing short 1 - 4 year stints in order to get meaningful raises
3. The exceptions in the private sector are businesses that not publicly traded.
4. Even then, very few people care about quality that no one else can see
As we all know, LOC as a metric has been around for ages, usually pushed by managers who don't understand development wanting some indicator that you are working hard.
It's no surprise that the same people are now using the same metric against LLMs except this time the LLM isn't telling them it's a daft measurement.
I think the HN crowd overestimates the quality of software. There is a (very) long tail of truly abysmal software that people are forced to use all the time. The reason it gets to be abysmal is because it’s often back-office admin software that helps people file forms for, say, logistics paperwork or school district expense tracking. AI-native engineering teams can create dramatic improvements for that long tail because the people running that software are either incompetent or checked out, and a pull towards average quality by AIs would yield great improvement.
> There is a (very) long tail of truly abysmal software that people are forced to use all the time.
We generally call it “enterprise software,” and it’s usually abysmal because the people buying/funding it are VP-level executives who care about compliance/reporting/visibility and who never have to actually use the software.
This actually comes up on HN pretty regularly. Or used to; like many topics it’s taken a back seat to AI.
...and now with AI much more of that dreadful software can be built with all the bullshit featuritis that said managers who don't use it think they want.
Right. All the boosters crowing about how amazing and so much better LLMs are than us are just doing marketing. Our jobs will be taken or ruined and people and companies will just be forced to get used to an even lower standard of quality as they've been doing already.
I've gone through a few recruiter screens lately and the number of people who mention "number of deploys per day" as a metric they are proud of causes my eyes to roll.
What can you possibly be doing as a product that justifies you releasing 60 times in a working day?
It's certainly better than the old models of releasing on a quarterly cadence with the test team and all that, but it feels like the metric has become the goal when you are releasing that often.
This was the case at a previous job. Someone read some "state of devops report" or similar BS where they wrote that good teams ship often. They took from that it was shipping often that made good teams...
And as a result we had some contrived deploy process on Slack with buttons and emojis and what not to deploy.
Not a single customer saw any value out of this of course, because shipping something is not the same as shipping something valuable.
So I guess releasing 60 times in a working day proves that you're part of a good team /s
That's why I'm sceptical about the value of ai in software development. Much more can now be done but I don't see costumers paying more for it. The only way it can work is by laying off software engineers and saving money on their salaries.
Tend to agree. AI has failed to produce more business outcome. The only thing left is cost efficiency by reducing headcount. Thus 5x more productivity means needing just 1/5th your current staffing.
and IME the #1 rule for us is work in a profit center, not a cost center. When you're cutting there's a law of diminishing returns, but the floor is so incredibly low you don't want to be near it just to clear the blade.
since when does an engineering org care about revenue or customer satisfaction? Most software devs have no idea how the business they work for operates and think their direct deposit every two weeks is a fundamental law of nature. Also, many software devs are anti-customer and think customers are wrong even when the customer is talking to them one-on-one describing their needs in plain english.
You're thinking about this at the wrong level. This org has made the decision to be AI-native. They aren't A/B testing being AI-native vs not being AI-native. That's the kind of thing "the market" does; if a company's markup is higher than another's it can attract more investment or its equity can trade for higher pricing on public markets.
I don't think it makes sense to A/B test "AI-native" vs other regimes of development unless you are a large, decentralized company like an F5 company or a Big Tech. How will a team of 25 (the size of the company if you read the thread) have enough output to even A/B test the difference?
Perhaps it shows that it does not matter how good your engineering is, or if you have sped up feature development 10x, if the shop is not providing value then who cares?
For the argument lets say that this approach works and results in high quality apps. But will be users happy that app is updated 3 times a week and all updates add major changes? Because code generation is so cheap and fast it means we should even more thing about what to build to not overwhelm our users and actually solve their problems.
I was just looking at some user-facing error messages Claude generated for me which contained unnecessary/irrelevant technical details while failed to provide clear instructions or fix.
Earlier, I reviewed code that does way more than specified scope, changes public API and introduces new behavior. I had to almost redo the whole thing.
I thought to myself, no way I am going to ship the code as written without actually reading through it (or as some people put it, only looking at the "intent"). I'll get more complaints from users while having absolutely no idea what's going on with the code or actual behavior.
It's a puzzle to me how these orgs can pull it off.
It really depends on the kind of product you're working on. A lot of developers (and managers and business leaders) assume that their workflows will apply to other kinds of products; and are often very wrong.
For example: A few days ago I saw a quote that over 90% of current Y-Combinator startups vibecode their products. The problem is the author misunderstands context: Startups sacrifice quality for time to market. In other cases, if you're building something that isn't technically challenging, (because it's 80% similar to many other products out there,) you can probably vibecode it.
In contrast, if you're doing something technically challenging, it's to your benefit to be a lot more hands-on. I recently started getting excellent reviews from copilot of my hand-written code. (Or, I should say, the hand-written parts of an AI-assisted pull request.)
I think it also depends on how well defined requirements are. I can have Claude nearly one shot a Terraform provider but it's just taking 2 API contracts and combining them together (the provider contract and the API you're automating)
On the other hand, some things are incredibly product intensive and poorly defined and it seems LLMs will latch on to an arbitrary direction with much lower success rate.
It is also worse in "brown field" where there's lots of tribal knowledge and technical debt. Two systems may both exist that look very similar but oftentimes there's the one on life support that almost no one uses or cares about and the LLM doesn't know it should largely ignore that until it's thoroughly documented (which can be a significant undertaking)
Here we are again, thirty years after I was taught the "waterfall" paradigm at business school.
When asked about "customer satisfaction" we were told, awkwardly, that became "political"
The paradigm did not survive its encounter with reality, and I do not think this one will either
The "only" 175% increase in productivity is very impressive, and seems realistic to me, when you remove the chores of writing code (thank you to coding agents)
What you build is still very dependant on what you need, and you do not know that until you build it
It is a paradox only for the "waterfall" paradigm. We rejected it, in the 1990s for a reason
I see a lot of builders (myself included) falling into the trap of focusing on the wrong things. Development velocity doesn't matter per se, what matters are things like growth in profit or traction. It's really easy to conflate automation/systems/process with actual business results. Movement ≠ Progress.
> None of this was free. Through the summer, much of our engineering effort went into tests and tooling, and customer-facing changes per engineer stayed between 17 and 30 a month
This is the reality I think for a lot of orgs and is absorbing a lot of the productivity gains. The gap between vibe coding a green field app from nothing which is inherently "AI native" and implementing AI tooling into complex orgs with large amounts of legacy infrastructure, integrations, ingrained practices etc is enormous. For us, it has been a big effort to enable agentic coding over a significant footprint of our codebase. And all this is happening while the plane keeps flying, with near zero tolerance for defects in critical systems. There is a lot more to it than you will understand if you just look at twitter or Hacker News.
Can we ban twitter links? I have to use a hack to even read it and it’s always just slop. If you can’t be bothered to write an actual article, why should we bother to read it.
Working at an "AI native" company and these questions and stats are far too hand-wavvy for me.
What works:
- Empowering engineers. Giving engineers more trust, ownership and product decision-making leads to more engaged engineers vs. micromanaged tickets. Engineers who are treated like owners tend to notice cross-cutting problems and push to get them cleaned up.
- Hire for diversity. Not race or gender, but diversity of thought. Different ages, backgrounds, approaches to AI, focus on frontend/backend, etc. Race/gender diversity tends to come along for free. This is a huge edge because every LLM is spinning up the same next token prediction, so approaching problems from different perspectives gives more robust coverage across your codebase.
- Flat org structure, low ego. Interns and 20 year vets work side-by-side and teach each other things - hire for openmindedness.
- Communicate about product. What should it do? How do we want a feature to work, and how to handle certain edge cases? If the product is well understood, the code follows. In-person/hybrid is valuable.
- Architecture matters more than ever, but it is easier than ever to fix. Listen when engineers mention tech debt. Notice when a simple change touches 27 files. Senior engineers shine for this, because they tend to have a better nose for code smell.
- Reviewing still matters. Anthropic may throw tokens at reviewing, but it is a great way to share ambient product/code knowledge across the team. 200 engineers throwing code against the wall is chaos and leads to YOLO codebases. You can move fast AND keep a rough mental model of the codebase intact.
Been moving our 17-person engineering team to adopt ai and this comment summarizes all of my findings perfectly.
This specifically summarizes a huge gap I think some people have around ai:
> Architecture matters more than ever, but it is easier than ever to fix.
You can prompt away to your heart’s content, but if you’re not pushing it in the right direction architecturally, you’re bound to face frustration eventually.
The most successful way I’ve found to convert those leaning anti-AI or AI-skeptical on my team is just showing them how much tech debt I can clean up with AI. They get excited to pitch in, and they see that it does actually benefit them in some meaningful ways. That set of endpoints that’s been neglected for years? Let’s stop complaining about them and DO something about them, today. I’ve actually seen life be blown into some devs who were coasting for a while. It’s an interesting time.
Yes. All of this sounds wise to me. Developers must be allowed and encouraged to expand their scope of responsibility in relation to how AI expands their code typing speed.
Blindly crushing jira tickets at 4x the speed will lead to crap, but investing the gained time into being more strategical will lead to higher productivity AND for many people greater job satisfaction.
We shipped more code!
We merged 5x faster!
We spent more tokens!
>> Every time we sped up one step, work piled up at the next... we started going through the entire process of shipping software, one step at a time...
I feel like I'm being gaslit here. You can become CTO with this lack of business fundamentals, and a basic misunderstanding of systems engineering?
I remember optimizing a huge build that took days. We optimised it to only hours on a cluster - it took years to get this right. We realised at the end of this that the packaging system (handled by another team) was taking about 2x longer than the build because there was one particularly huge zipfile that sat there compressing for ever and ever and ever while the rest of the cluster was idle.
As in this story we blew enormous effort optimizing something that was very difficult and because of our blinkers (and our management's blinkers) we missed that it was only able to achieve a limited result. We didn't look at the whole system.
I know many (big) places that are already back-paddling.
From token leadership boards (more = better) to now saving on AI cost, because the benefit was less than expected. As if this wasn't obvious. Sigh.
Sure MS, Meta, etc, are still laying off engineers to have money for data centers. But I am 99.9% sure that they will thoroughly regret that move in less than 2 years.
> None of this was free. Through the summer, much of our engineering effort went into tests and tooling, and customer-facing changes per engineer stayed between 17 and 30 a month.
What it cost you is that you helped the AI labs become better engineers. At a certain point the Big Flip will happen, and the AI labs will stop their offerings and instead start competing with the engineers.
This assumes that it’s more profitable for these labs to compete with their own customers, rather than increasing the productivity for their customers and - assuming this increase justifies it - increasing their profits.
158 comments
[ 1.5 ms ] story [ 38.0 ms ] threadIf that's the benchmark, developers are incentivized to produce over-engineered and bloated code.
Software quality was in terminal decline already, the only hope is that LLMs get good enough to dig outselves out of the several miles deep hole that has been dug.
First you take your Blendtech and "will it blend" your engineers, then upload the result to the cloud inside what is called an S3 bucket (don't forget to set access permissions on your buckets kids!) to be digested by the clankers, sit back and profit!
Dark humor aside I think disconnecting a bunch of problem solvers from their computing equipment could really enhance the world, putting that analytical power into the world in person could move a lot of cogs, rather then marshalling JSON.
To me, true "AI-native" engineering will be one where questions regarding how humans will do things like review code are irrelevant. You explicitly throw away any concept of typical software engineering and, instead, differ to the AI. Your job, as a human, is solely to do what the AI can't physically do. That's not the same as closing gaps between what AI is currently capable of doing and what you'd need it to be capable of doing. It's literally enforcing that anything an AI is able to do is treated as correct in itself, and you, as a human, only support it by being a human.
If that sounds outlandish, that's because it is. We don't have such capable AI systems yet. It's possible we never will. But that's beyond the point. The reality is trying to make an "AI-native" engineering org by just layering AI on top of existing processes and systems is futile. If your expectation is that AI will continue to improve in capabilities at an accelerating rate, then these stop-gaps are pointless. You might as well just ignore AI altogether until it is able to completely take over, because that's the inevitable goal, right?
If you're willing to buy that will be possible, then my guess is that it will occur in the form of small scale startups and actual mavericks rather than someone trying to run an existing business who will simply be too risk adverse to go all in when the time comes. Some guy in his basement is more likely to leverage AI "properly" to build an actual "AI-native" engineering org because that person won't have much to lose.
Most engineers are working in "normal" engineering orgs, but can feel the ground underneath them shifting, and companies believe that if they are caught flat footed, they will be out competed in the marketplace, so they are all trying to make sure they are adopting it at least in a way that lets them keep pace if not accelerate revenue.
If you are not impacted by economic incentives, you can continue to not care about this transitional state, but most people do.
Does not apply to everything though. E.G: I don’t care about AI support for my non work chats/email, since I’d rather not give it access.
But we're a tiny baby startup, so things like "spin up a new product with 1 engineer and get to $1m in revenue on it" or "reduce our IaaS bill by 300k/yr" is a meaningful contribution for us.
We're also building new AI-enabled software that was not possible before.
The big breakout hits have been AI Infra, but that makes sense from a technological perspective, Cisco made a lot of money well before Google did, but Cisco is not where the money concentrated in the end.
We don't really know what the equivalent of Google as an application business will be in the AI era, but there's a pretty big chance it's not actual Google. But Google still has to do it's best to hold on.
Engineering’s job has always been to deal with hard technical challenges and apply new technologies.
Writing code was never the point. Predictably creating specific outcomes was. Wrangling AI in a way that multiplies productivity is the new job.
I won’t lie, it kind of sucks to be young right now, learn about punch cards and assembly in school, and then graduate into a market that’s moved on to Fortran. Sorry, I meant high level languages and AI. To say otherwise might imply the industry has seen a similar shift in the past where engineers made the exact same complaints practically verbatim.
Regardless, the reality is that college teaches very little about 90% of real engineering work anyway, and we still need to hire smart people for this new type of work.
https://www.nytimes.com/2026/04/02/technology/ai-billion-dol...
https://www.businessinsider.com/medvi-ai-weight-loss-million...
"If that sounds outlandish, that's because it is. We don't have such capable AI systems yet."
defer to the AI
A company which proclaims they are "AI-native" isn't actually interested in engineering, they are trying to ride the hype wave. Companies who care about engineering just... do engineering, and don't make a big deal out of whether they are chasing trends.
FWIW I think the company writing this post is one of those small scale startups. But that being said, you're not the only one who thinks this. A decent amount of VCs and funds think that only smaller, newer companies have the potential to be truly AI native because there's too much organizational inertia in an existing business in keeping its existing human processes and so only a newer company can achieve the true "scaling potential" or using AI to scale without human labor.
That means we are already 6-8 months in, and not far from having a full year of experience of what that actually looks like, albeit weirdly influenced by the increase in model capabilities during that period.
I'm looking forward to those retrospectives. Did this turn out to work OK for the teams doing it? What were the biggest failings and/or surprises? With hindsight, did this produce good quality software?
So far AI works great at fast moving work which you will probably recode or throw away in a month or two anyway (e.g. a startup) but is weak at maintaining a large code base that you rely on. At least part of this is cultural, as the cost of misalignments between team members can be quickly translated into broken software.
It describes a team spending 30x payroll on tokens - $3,000,000 in token spend per month - building a multiplayer game where incidents and bug reports from users are passed directly to Fable 5/5.1 agents who then act on them and deploy the changes to production.
"We consider it an outage if we don't ship every hour"
It's worth reading because it's either a complete disaster or a glimpse of the future, or quite possibly both.
In the past when working on agentic stuff I've observed models gaming checks aggressively, to the point that when we were validating log files to see what the agent had done, the agent responded by editing the log files to pass validation. I can only imagine how bad that kind of behavior is at scale, and it sounds like they ran into it.
But is the outcome good? Is the game fun?
In the instances where they were able to detect it. How much do you think they pour over individual traces nowadays to search for these things?
I looked at some of the games and it just looks like a Roblox clone
I giggled on that one. It feels like children playing having a job. If they pay that much for tokens they have to have at least 80k customers paying 50$ a month. Seems huge for something like that. Or they have a lot of investors. Anyway does not feel like something going anywhere.
And it's devouring tens of millions. I know what tens of millions can make in the video game industry, it can keep a small team of good devs and designers and artists making something special that's _really_ enjoyed by tens of thousands of people.
We don't want more games, we want more great games. This will never, ever, make great games.
https://www.spawn.co
Look on ye mighty, and despair. I really don't care how this sausage was made because the only thing you need to know is that it shouldn't ever have been made.
These people have no idea what good games mean.
As a product that I would regularly use, Pluto missed the mark for me. As a SWE in 2023, I couldn't meet Jacob's mentality. Today, it's how a lot of us ship software.
I didn't love the product but I have to respect the process: he was able to sell his company. For some, what he did is success.
Do players like it?
Will the history of gaming remember this game?
Presumable a handful do, in the short term at least.
No.
The more agents you throw at something, the more they collide. Those collisions generate more slop, which requires further slop processing agents.
Only three metrics went up: LOC, token spend and presumably release speed/frequency.
What's the markup (profit/COGS)? is it up?
Customer satisfaction? Is NPS moving one way or another?
it really isn't a flex ppl think it is when they're burning tokens churning agents that are working for "hours" doing work
we don't need to read or write code anymore, but we do need to write (as humans) the instructions for agents.
having ADRs, product specs, acceptance criteria, etc. that are properly maintained leads to agents working for just a few minutes and pumping out reliable code.
the more vague the work for agents, the more randomness and inefficiency there will be. that leads to bugs, constantly re-writing code, etc.
imo ofc, i'm not yet running a billion dollar company so maybe i'm wrong.
These new tools only exacerbate this issue.
Management/Product/Product Engineer - When you are responsible for getting the work done then you look for any and every option to speed it up.
Owner/Platform/Senior Engineer - When you are responsible for ensuring it works and can be maintained then you have to pay attention to how to build it, aka the trade offs
The demand for new features come from sales and executive people who want to check more boxes on a customer's checklist.
I push "money and data are sacred"; if we lose either of those, someone cries. Build the platform slow and fast. Governance, scaling etc sits here.
Provide reference APIs and let the product team one shot whatever they want and need, build fast and experimental, but your platform enforces constraints.
Best of both worlds (though feels like we're back in backend vs frontend development)
this is extremely true, but it seems less and less like anyone wants to invest in a solid platform and just wants to jump to executing fast and unsafe. and then pretends that ai can definitely do both when the experience is quite a bit different.
The key is to understand that computers exist to serve human needs, and the less code / UI / hoops to solve a problem the better, and to think end-to-end. If you are able to do that, most systems built by committee have a lot of low-hanging fruit that can be improved without much sacrifice. In practice, political realities and operational concerns may come in the way, but I firmly believe this is the only way to successfully operate as an engineer, and it will only become more important in the age of AI.
Just because it has the power doesn't mean it should be used.
I'm not asking for everything to be some sort of beautiful code whose concision would lead Knuth to tears. I'm just asking that you not slather dozens of existing functions with three new parameters and dozens of lines of code each that basically do nothing, to cover a use case that I accidentally vaguely alluded to, if you read my prompt a certain way, but isn't really what I was interested in.
Training for good taste in architecture actually causes premature optimization at high effort allowance, but at the same time, it is combined with an inability to even recognize / exploit that later if it should ever become actually useful. Dial the effort down, and it skips the reasonable abstraction and nothing is dry, factoring is insane.
Goldilocks for simple stuff barely works with frontier models after they are out of their comfort zone for topic or line limits.. you kind of just have to decide whether it’s worth it anyway. In practice.. constant supervision for high quality code, or such high quality system design that the code quality is less of a down side.
Now, token calculators spew out code at a pace no human can match, which completely removes the barrier of effort - which was one of the largest natural counters to shipping massive amounts of slop.
I'll be impressed by a coding model when it writes less code than a human, and spends more time refactoring than it does just adding new layers. Until then, this vibecoding is just madness.
I think AI has been a net positive and has been used responsibly at my work. It can be used to make existing products better and more secure. You just won't naturally hear about that. There's some challenges like emerging social mores but overall good.
Why? I keep asking for examples of LLM being used to make code more simple and elegant (which I would say is adjacent to making software better, if not more secure), and never get a reply, not a single one. I'm not claiming it doesn't exist, I know it must exist. If only via a lots of careful massaging of system prompts and harnesses, even if it takes too much effort to be worth it, I would like to see it.
Of course people can't share internal examples, but this is all over the world for many months now, where are the open source examples? Not "something new someone couldn't have done before", but someone making their precious even neater (while also adding things to it, but not primarily). Put differently, can LLM delete code, can they curate it well, can they not write weird comments nobody wants or needs, that sound like echoes of the user prompts and responses to them, but just explain tricky parts of the code, like a human would?
Also, IMO a VERY useful thing to learn about a tool or a chemical or whatever is, "what happens if I keep applying it to the same small thing over and over?" -- because that's the level of scientist I never evolved past, the kind of stuff you do as a kid -- , whereas a lot of this seems to be more about how it feels to apply it here and there until it looks good, and then move on and never look back. Which really isn't much at all, especially given we're such a short time in. I mean, how useful were mugs made of lead? Are people aware of the (in hindsight) insane things that were done with x-rays as those were invented, before the potential for harm was known? I bet they had a great time playing with that stuff, for a while.
What if in 5 years it turns out that a few years ago, LLM got into this habit of implementing certain things in a certain way because it seemed the best to "them" (the training, whatever), but there's a security issue with that -- what do you do? You can only let more agents loose, and hope they don't miss anything, because you cannot even do something like "patch PHP" (which is not my thought, Casey Muratori mentioned that in on of those podcast things).
Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though. It just does, like suggesting we go to Mars, because everything is better there, and to do that, we have to blow up Earth. Or saying to magically be able to fly from now on, we need to saw off the branch we're sitting on. Even if I thought life on Mars was the future or that we could fly, if we just thought of it the right way, this isn't a way forward IMO.
But with suitable direction, they can definitely improve codebases - especially a typical enterprise codebase, which, if you don't like LLM code, you would hate with a passion. (I can only assume you've never seen such code otherwise your perspective would be different.)
> Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though.
I essentially agree, but there's a huge spectrum before you get to that point, and lots of ways to use it effectively that doesn't create tech debt.
No, he wants a project where AI is used as a major help, but the result tend towards good code, i.e readable and well abstracted. Even if the cost is high, just an example where you can extract the best practices of using AI coding.
I specifically wrote an "initial review".
The code in question was split into modules, the largest of which was about 500 lines. Overall, the quality was higher than a lot of unaided human code that I've reviewed.
That code is greenfield code, so doesn't fit what was being requested above. But here's an example that illustrates the point I mentioned about functional pipelines:
This particular fragment is parsing input using the Chumsky parser combinator library. That imposes a structure that has to be followed. It's all heavily type-driven, which means that it's naturally structured as type cases, where each case handler is pretty small. The longest one in this code is around 20 lines, but most are more like 5 lines or so.As a result, the modules, functions, and case handlers naturally follow the single responsibility principle. This makes it easy to review. Again, this goes to the points I made in my other comment - if you give a model a good type schema, have it use good libraries in a good language, so that it has a well-structured framework in which to operate, you're likely to get good results.
Perhaps a simpler way to describe it is the old saying, "garbage in, garbage out". If you're vibe coding, say, PHP you're much less likely to get the same quality results.
Simple and elegant generally doesn't come from the LLM. It comes from me saying no to the LLM. I've discarded many branches that didn't feel like they were going the right way. Hell, I aggressively do that with my own code also. I rarely commit the first thing that works.
> where are the open source examples?
My general impression of open source is that it is, in part, a market driven by good software engineering. There's certainly below average code, but that tends to get mocked out of existence before it grows too much. Proprietary code that doesn't have a strong forcing function used to be able to hide poor engineering principles.
I think AI generated code is a regression to the mean, and the mean can be an improvement sometimes. I inherited this project. It was not originally written with AI. A lot of hard work and good engineering went into the hardware/firmware. The IoT software connecting it to our intranet, less so. Some examples that I'm fixing/fixed: ignoring HTTPS certificates, RCE by design, in-place file updating JSON files, a hand-rolled (but ineffective) fair mutex, busy waiting for a device to appear, and worst of all, no tests. None of these are hard to avoid, and even the small AI models would have come up with a better implementation.
This doesn't seem unique to my project either. I think a lot of software is just silently getting closer to the average of all open source code upon which the models were trained. I don't think I want things like SQLite to get closer to the average.
> Fully leaning into LLM doing as much of the coding and understanding as can be handed off to them seems insane to me, I don't mean this to offend though.
I think you might be reading too much into what I said. When I say "fully lean into", it's probably less than you're thinking of. I still feel that I understand what was written and can stake my reputation/career on it.
It always works best when layering on top of good human code. The thing is, you start to run out of that as you lean in. Tricky.
I think it depends how you lean in. I generated a few thousand lines of Rust code today. It was actually pretty high quality. On my initial review, I only identified one change I wanted to make.
Most functions were pretty short and well factored. I wonder if using Rust as a target helps, because (1) the training data doesn't include all the terrible Javascript and Python etc. found on the internet, and (2) Rust and many of its libraries encourage good architecture - code factored into traits, functional pipelines, a powerful type system, etc.
LLMs trained on bad code for mediocre languages naturally write corresponding quality code.
A big part of it still boils down to prompting - what you're asking it to do and how much freedom you give them. If you let them make all the architectural decisions, you're likely to end up with issues.
Hell, if the Dunning–Kruger effect is to be believed, it would be bold me to assume I am capable of good human code. Maybe the average is the best I'll ever get.
2. This is exacerbated by the lack of loyalty people have towards their organizations because their orgs don’t value or reward loyalty. That’s because leadership doesnt care about the long term view because of item #1. Hence, everyone is only doing short 1 - 4 year stints in order to get meaningful raises
3. The exceptions in the private sector are businesses that not publicly traded.
4. Even then, very few people care about quality that no one else can see
Shipping lots of good code by necessity means you ship lots of code.
Shipping lots of bad code, too.
But if you only know that you are shipping lots of code, which of the two is it?
IOW: by increasing number of shipped LOC, you will not magically make it better.
It's no surprise that the same people are now using the same metric against LLMs except this time the LLM isn't telling them it's a daft measurement.
We generally call it “enterprise software,” and it’s usually abysmal because the people buying/funding it are VP-level executives who care about compliance/reporting/visibility and who never have to actually use the software.
This actually comes up on HN pretty regularly. Or used to; like many topics it’s taken a back seat to AI.
What can you possibly be doing as a product that justifies you releasing 60 times in a working day?
It's certainly better than the old models of releasing on a quarterly cadence with the test team and all that, but it feels like the metric has become the goal when you are releasing that often.
So I guess releasing 60 times in a working day proves that you're part of a good team /s
I don't think it makes sense to A/B test "AI-native" vs other regimes of development unless you are a large, decentralized company like an F5 company or a Big Tech. How will a team of 25 (the size of the company if you read the thread) have enough output to even A/B test the difference?
Earlier, I reviewed code that does way more than specified scope, changes public API and introduces new behavior. I had to almost redo the whole thing.
I thought to myself, no way I am going to ship the code as written without actually reading through it (or as some people put it, only looking at the "intent"). I'll get more complaints from users while having absolutely no idea what's going on with the code or actual behavior.
It's a puzzle to me how these orgs can pull it off.
For example: A few days ago I saw a quote that over 90% of current Y-Combinator startups vibecode their products. The problem is the author misunderstands context: Startups sacrifice quality for time to market. In other cases, if you're building something that isn't technically challenging, (because it's 80% similar to many other products out there,) you can probably vibecode it.
In contrast, if you're doing something technically challenging, it's to your benefit to be a lot more hands-on. I recently started getting excellent reviews from copilot of my hand-written code. (Or, I should say, the hand-written parts of an AI-assisted pull request.)
On the other hand, some things are incredibly product intensive and poorly defined and it seems LLMs will latch on to an arbitrary direction with much lower success rate.
It is also worse in "brown field" where there's lots of tribal knowledge and technical debt. Two systems may both exist that look very similar but oftentimes there's the one on life support that almost no one uses or cares about and the LLM doesn't know it should largely ignore that until it's thoroughly documented (which can be a significant undertaking)
When asked about "customer satisfaction" we were told, awkwardly, that became "political"
The paradigm did not survive its encounter with reality, and I do not think this one will either
The "only" 175% increase in productivity is very impressive, and seems realistic to me, when you remove the chores of writing code (thank you to coding agents)
What you build is still very dependant on what you need, and you do not know that until you build it
It is a paradox only for the "waterfall" paradigm. We rejected it, in the 1990s for a reason
It did not work
This is the reality I think for a lot of orgs and is absorbing a lot of the productivity gains. The gap between vibe coding a green field app from nothing which is inherently "AI native" and implementing AI tooling into complex orgs with large amounts of legacy infrastructure, integrations, ingrained practices etc is enormous. For us, it has been a big effort to enable agentic coding over a significant footprint of our codebase. And all this is happening while the plane keeps flying, with near zero tolerance for defects in critical systems. There is a lot more to it than you will understand if you just look at twitter or Hacker News.
What works: - Empowering engineers. Giving engineers more trust, ownership and product decision-making leads to more engaged engineers vs. micromanaged tickets. Engineers who are treated like owners tend to notice cross-cutting problems and push to get them cleaned up. - Hire for diversity. Not race or gender, but diversity of thought. Different ages, backgrounds, approaches to AI, focus on frontend/backend, etc. Race/gender diversity tends to come along for free. This is a huge edge because every LLM is spinning up the same next token prediction, so approaching problems from different perspectives gives more robust coverage across your codebase. - Flat org structure, low ego. Interns and 20 year vets work side-by-side and teach each other things - hire for openmindedness. - Communicate about product. What should it do? How do we want a feature to work, and how to handle certain edge cases? If the product is well understood, the code follows. In-person/hybrid is valuable. - Architecture matters more than ever, but it is easier than ever to fix. Listen when engineers mention tech debt. Notice when a simple change touches 27 files. Senior engineers shine for this, because they tend to have a better nose for code smell. - Reviewing still matters. Anthropic may throw tokens at reviewing, but it is a great way to share ambient product/code knowledge across the team. 200 engineers throwing code against the wall is chaos and leads to YOLO codebases. You can move fast AND keep a rough mental model of the codebase intact.
This specifically summarizes a huge gap I think some people have around ai:
> Architecture matters more than ever, but it is easier than ever to fix.
You can prompt away to your heart’s content, but if you’re not pushing it in the right direction architecturally, you’re bound to face frustration eventually.
The most successful way I’ve found to convert those leaning anti-AI or AI-skeptical on my team is just showing them how much tech debt I can clean up with AI. They get excited to pitch in, and they see that it does actually benefit them in some meaningful ways. That set of endpoints that’s been neglected for years? Let’s stop complaining about them and DO something about them, today. I’ve actually seen life be blown into some devs who were coasting for a while. It’s an interesting time.
Blindly crushing jira tickets at 4x the speed will lead to crap, but investing the gained time into being more strategical will lead to higher productivity AND for many people greater job satisfaction.
>> Every time we sped up one step, work piled up at the next... we started going through the entire process of shipping software, one step at a time...
I feel like I'm being gaslit here. You can become CTO with this lack of business fundamentals, and a basic misunderstanding of systems engineering?
(in fact it may be a requisite ...)
As in this story we blew enormous effort optimizing something that was very difficult and because of our blinkers (and our management's blinkers) we missed that it was only able to achieve a limited result. We didn't look at the whole system.
Sure MS, Meta, etc, are still laying off engineers to have money for data centers. But I am 99.9% sure that they will thoroughly regret that move in less than 2 years.
> None of this was free. Through the summer, much of our engineering effort went into tests and tooling, and customer-facing changes per engineer stayed between 17 and 30 a month.
What it cost you is that you helped the AI labs become better engineers. At a certain point the Big Flip will happen, and the AI labs will stop their offerings and instead start competing with the engineers.
I don’t think it will ever reach such a point.