[Aurornis]

Refreshing to see an honest and balanced take on AI coding. This is what real AI-assisted coding looks like once you get past the initial wow factor of having the AI write code that executes and does what you asked.

This experience is familiar to every serious software engineer who has used AI code gen and then reviewed the output:

> But when I reviewed the codebase in detail in late January, the downside was obvious: the codebase was complete spaghetti14. I didn’t understand large parts of the Python source extraction pipeline, functions were scattered in random files without a clear shape, and a few files had grown to several thousand lines. It was extremely fragile; it solved the immediate problem but it was never going to cope with my larger vision,

Some people never get to the part where they review the code. They go straight to their LinkedIn or blog and start writing (or having ChatGPT write) posts about how manual coding is dead and they’re done writing code by hand forever.

Some people review the code and declare it unusable garbage, then also go to their social media and post how AI coding is completely useless and they’re not going to use it for anything.

This blog post shows the journey that anyone not in one of those two vocal minorities is going through right now: A realization that AI coding tools can be a large accelerator but you need to learn how to use them correctly in your workflow and you need to remain involved in the code. It’s not as clickbaity as the extreme takes that get posted all the time. It’s a little disappointing to read the part where they said hard work was still required. It is a realistic and balanced take on the state of AI coding, though.

[yojo]

+1

I’ve been driving Claude as my primary coding interface the last three months at my job. Other than a different domain, I feel like I could have written this exact article.

The project I’m on started as a vibe-coded prototype that quickly got promoted to a production service we sell.

I’ve had to build the mental model after the fact, while refactoring and ripping out large chunks of nonsense or dead code.

But the product wouldn’t exist without that quick and dirty prototype, and I can use Claude as a goddamned chainsaw to clean up.

On Friday, I finally added a type checker pre-commit hook and fixed the 90 existing errors (properly, no type ignores) in ~2 hours. I tried full-agentic first, and it failed miserably, then I went through error by error with Claude, we tightened up some exiting types, fixed some clunky abstractions, and got a nice, clean result.

AI-assisted coding is amazing, but IMO for production code there’s no substitute for human review and guidance.

[figassis]

My process: start ideating and get the AI to poke holes in your reasoning, your vision, scalability, etc. do this for a few days while taking breaks. This is all contained in one Md file with mermaid diagrams and sections.

Then use ideation to architect, dive into details and tell the AI exactly what your choices are, how certain methods should be called, how logging and observability should be setup, what language to use, type checking, coding style (configure ruthless linting and formatting before you write a single line of code), what testing methodology, framework, unit, integration, e2e. Database, changes you will handle migrations, as much as possible so the AI is as confined as possible to how you would do it.

Then, create a plan file, have it manage it like a task list, and implement in parts, before starting it needs to present you a plan, in it you will notice it will make mistakes, misunderstand some things that you may me didn’t clarify before, or it will just forget. You add to AGENTS.md or whatever, make changes to the ai’s plan, tell it to update the plan.md and when satisfied, proceed.

After done, review the code. You will notice there is always something to fix. Hardcoded variables, a sql migration with seed data that should actually not be a migration, just generally crazy stuff.

The worst is that the AI is always very loose on requirements. You will notice all its fields are nullable, records have little to no validation, you report an error when testing and it tried to solve it with an brittle async solution, like LISTEN/NOTIFY or a callback instead of doing the architecturally correct solution. Things that at scale are hell to debug, especially if you did not write the code.

If you do this and iterate you will gradually end up with a solid harness and you will need to review less.

Then port it to other projects.

[ElFitz]

> After done, review the code. You will notice there is always something to fix. Hardcoded variables, a sql migration with seed data that should actually not be a migration, just generally crazy stuff. > > The worst is that the AI is always very loose on requirements. You will notice all its fields are nullable, records have little to no validation, you report an error when testing and it tried to solve it with an brittle async solution, like LISTEN/NOTIFY or a callback instead of doing the architecturally correct solution. Things that at scale are hell to debug, especially if you did not write the code.

For that I usually get it reviewed by LLMs first, before reviewing it myself.

Same model, but clean session, different models from different providers. And multiple (at least 2) automated rounds of review -> triage by the implementing session -> addressing + reasons for deferring / ignoring deferred / ignored feedbacks -> review -> triage by the implementing session -> …

Works wonders.

Committing the initial spec / plan also helps the reviewers compare the actual implementation to what was planned. Didn’t expect it, but it’s worked nicely.

[deadbabe]

LISTEN/NOTIFY is not brittle, we use it for millions of events per day.

[JoelJacobson]

I agree! It should be very stable, IMO. If not, then please send a bug report and we'll look into it. Also, now it scales well with the number of listening connections (given clients listen on unique channel names): https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit...

[deadbabe]

The LISTEN/NOTIFY feature really just doesn’t get enough PR. It is perfectly suitable for production workloads yet people still want to reach for more complicated solutions they don’t need.

[figassis]

It's not the feature itself, it's how/what the llm tries to use it for. It uses it to cross any and all architectural boundaries.

[irishcoffee]

I find it very interesting that you assume this method would branch out to other projects. I find it even more interesting that you assume all software codebases use a database, give a damn about async anything, and that these ideas percolate out to general software engineering.

Sounds like a solid way to make crud web apps though.

[klardotsh]

GP is clearly providing examples of categories of tasks. Sure, not all languages do “async fn foo()”, but almost all problem domains involve some sort of making sure the right things happen at the right times, which is in a similar ballpark.

Holier than thou “yeah well I work on stuff that doesn’t use databases, checkmate!” doesn’t really land - data still gets moved around somehow, and often over a network!

[irishcoffee]

Not trying to "land" anything.

[camdenreslink]

I’ve found that LLMs will frequently do extremely silly things that no person would do to make typescript code pass the typechecker.

[gck1]

I've noticed this too, but not necessarily type checkers, but more with linters. And can't really figure out if there's even a way to solve it.

If you set up restrictive linters and don't explicitly prohibit agents from adding inline allows, most LOC will be allow comments.

Based on this learning, I've decided to prohibit any inline allows. And then agents started doing very questionable things to satisfy clippy.

Recent example:

- Claude set up a test support module so that it could reuse things. Since this was not used in all tests, rust complained about dead_code. Instead of making it work, claude decided to remove test support module and just... blow up each test.

If you enable thinking summaries, you'll always see agent saying something like: "I need to be pragmatic", which is the right choice 50% of the time.

[9rx]

Yeah, I've found LLMs cannot write good Typescript code period. The good news is that they are excellent at some other languages.

[darkstarsys]

I can't agree here. https://pelorus-nav.com/ (one of my side projects) is 95-98% written by Claude Opus 4.6, all in very nice typescript which I carefully review and correct, and use good prompting and context hygiene to ensure it doesn't take shortcuts. It's taken a month or so but so worth it. And my packing list app packzen.org is also pretty decent typescript all through.

[9rx]

> which I carefully review and correct

So you do agree? If you are having to review and correct then it's not really the LLM writing it anymore. I have little doubt that you can write good Typescript, but that's not what I said. I said LLMs cannot write good Typescript and it seems you agree given your purported actions towards it. Which is quite unlike some other languages where LLMs write good code all the time — no hand holding necessary.

[darkstarsys]

I find correction is rarely necessary with Opus 4.6. Definitely not so much that "it's not really the LLM writing it anymore." More like it's the author and I'm the editor (in this limited case -- of course architecturally the ideas are all mine.) But I totally respect that my prompt style, the type of app I'm writing, and other factors could be influencing my success vs. others' lack of success.

[camdenreslink]

I think it can write working TypeScript code, and it can write good TypeScript code if it is guided by a knowledgable programmer. It requires actually reviewing all the code and giving pointed feedback though (which at that point is only slightly more efficient than just writing it yourself).

[9rx]

> It requires actually reviewing all the code and giving pointed feedback though

Exactly. You can write good Typescript, no doubt, but LLMs cannot. This is not like some other languages where LLM generated code is actually consistently good without needing to become the author.

[akdev1l]

You need to very specific and also question the output if it does something insane

[mexicocitinluez]

I've found it's less about specificity and more about removing the # of critical assumptions it needs to make. Being too specific can be a hindrance in it's own regard.

And that's also a decent barometer for what it's good at. The more amount of critical assumptions AI needs to make, the less likely it is to make good ones.

For instance, when building a heat map, I don't have to get specific at all because the amount of consequential assumptions it needs to make is slim. I don't care or can change the colors, or the label placement.

[justonceokay]

This decade’s version of “works on my box”

[dpkirchner]

I caught it using Parameters<typeof otherfn>[2] the other day. It wanted to avoid importing a type, so it did this nonsense. (I might have the syntax slightly wrong here, I'm writing from memory.)

But it's not all bad news. TIL about Parameters<T>.

[theshrike79]

> On Friday...

This should be done on day one with a company-wide skill or project template that defines hard limits and processes for the Agent.

Strict linters, formatters and code quality checks are essential to de-slopify the code as much as possible.

That doesn't fix bad design though, that's still on humans.

[ffsm8]

Fwiw, the article mirrors my experience when I started out too, even exactly with the same first month of vibecoding, then the next project which I did exactly like he outlined too.

Personally, I think it's just the natural flow when you're starting out. If he keeps going, his opinion is going to change and as he gets to know it better, he'll likely go more and more towards vibecoding again.

It's hard to say why, but you get better at it. Even if it's really hard to really put into words why

[snovv_crash]

Given how addictive vibecoding is, I think it's very hard to be objective about the results if you are involved in the process.

[delusional]

It's a little like asking a cokehead how the addiction is going for him while he is high. Obviously he's going to say it's great because the consequences haven't hit him. Some percentage of addicts will never realize it was a problem at all.

Its not random that AI happens to be built by the very same people that turned internet forums into the most addictive communication technology ever.

[59nadir]

> he'll likely go more and more towards vibecoding again

I think "more and more" is doing some very heavy lifting here. On the surface it reads like "a lot" to many people, I think, which is why this is hard to read without cringing a bit. Read like that it comes off as "It's very addictive and eventually you get lulled into accepting nonsense again, except I haven't realized that's what's happening".

But the truth is that this comment really relies entirely on what "more and more" means here.

[devmor]

[flagged]

[ffsm8]

really?

have you ever learned a skill? Like carving, singing, playing guitar, playing a video game, anything?

It's easy to get better at it without understanding why you're better at it. As a matter of fact, very very few people master the discipline enough to be able to grasp the reason for why they're actually better

Most people just come up with random shit which may or may not be related. Which I just abstained from.

[SpicyLemonZest]

I've learned a number of skills, and for me none of them worked in the way you're describing. I didn't learn to cut good miter joints by randomly vibe-sawing wood until I unlocked miter joints in the skill tree. I carefully studied the errors I made, and adjusted in ways I thought might correct them, some of which helped some of which did not. Then eventually I understood the relationship between my actions and the underlying principles in enough detail to consistently hit 45 degrees.

[eszed]

Isn't that example pretty reductive, in that you have a directly-measurable output? I mean, the joint is either 45° (well, 90°) or it's not. Zoom out a bit, and the skill-set becomes much less definable: are my cabinets good - for some intersection of well-proportioned, elegantly-finished, and fit for purpose, with well-chosen wood and appropriate hardware.

Mind you, I don't think the process of improvement in those dimensions is fundamentally different, just much less direct and not easily (or perhaps even at all) articulable.

[devmor]

You can get better at something without understanding why, but you should be able to think about it and determine why fairly easily.

This is something everyone who cares about improving in a skill does regularly - examine their improvement, the reasons behind it, and how to add to them. That’s the basis of self-driven learning.

[danielmarkbruce]

This is an absurd statement. There are many complex undertakings in sport where even the very best get better with practice and can't tell you why. In fact, the ones who think they can tell you why are the one's to be most skeptical of.

You are just making stuff up or regurgitating material from a pop science book.

[ffsm8]

Not really. I can obviously say something, like you learn which features the models are able to actually implement, and you learn how to phrase and approach trickier features to get the model too do what you want.

And that's not really explainable without exploring specific examples. And now we're in thousands of words of explanation territory, hence my decision to say it's hard to put it into words.

[libraryofbabel]

Agree. This is such a good balanced article. The only things that still make the insights difficult to apply to professional software development are: this was greenfield work and it was a solo project. But that’s hardly the author’s fault. It would however be fantastic to see more articles like this about how to go all in on AI tools for brownfield projects involving more than one person.

One thing I will add: I actually don’t think it’s wrong to start out building a vibe coded spaghetti mess for a project like this… provided you see it as a prototype you’re going to learn from and then throw away. A throwaway prototype is immensely useful because it helps you figure out what you want to build in the first place, before you step down a level and focus on closely guiding the agent to actually build it.

The author’s mistake was that he thought the horrible prototype would evolve into the real thing. Of course it could not. But I suspect that the author’s final results when he did start afresh and build with closer attention to architecture were much better because he has learned more about the requirements for what he wanted to build from that first attempt.

[argee]

This wasn't even just greenfield work, it included the exact type of work where AI arguably excels: extracting working code from an extant codebase (SQLite) as a reusable library. (It also included the type of work AI is really bad at: designing APIs sensibly.)

[csallen]

I'll take the other side of this.

Professional software engineers like many of us have a big blind spot when it comes to AI coding, and that's a fixation on code quality.

It makes sense to focus on code quality. We're not wrong. After all, we've spent our entire careers in the code. Bad code quality slows us down and makes things slow/insecure/unreliable/etc for end users.

However, code quality is becoming less and less relevant in the age of AI coding, and to ignore that is to have our heads stuck in the sand. Just because we don't like it doesn't mean it's not true.

There are two forces contributing to this: (1) more people coding smaller apps, and (2) improvements in coding models and agentic tools.

We are increasingly moving toward a world where people who aren't sophisticated programmers are "building" their own apps with a user base of just one person. In many cases, these apps are simple and effective and come without the bloat that larger software suites have subjected users to for years. The code is simple, and even when it's not, nobody will ever have to maintain it, so it doesn't matter. Some apps will be unreliable, some will get hacked, some will be slow and inefficient, and it won't matter. This trend will continue to grow.

At the same time, technology is improving, and the AI is increasingly good at designing and architecting software. We are in the very earliest months of AI actually being somewhat competent at this. It's unlikely that it will plateau and stop improving. And even when it finally does, if such a point comes, there will still be many years of improvements in tooling, as humanity's ability to make effective use of a technology always lags far behind the invention of the technology itself.

So I'm right there with you in being annoyed by all the hype and exaggerated claims. But the "truth" about AI-assisted coding is changing every year, every quarter, every month. It's only trending in one direction. And it isn't going to stop.

[mjr00]

> However, code quality is becoming less and less relevant in the age of AI coding, and to ignore that is to have our heads stuck in the sand. Just because we don't like it doesn't mean it's not true.

Strongly disagree with this thesis, and in fact I'd go completely the opposite: code quality is more important than ever thanks to AI.

LLM-assisted coding is most successful in codebases with attributes strongly associated with high code quality: predictable patterns, well-named variables, use of a type system, no global mutable state, very low mutability in general, etc.

I'm using AI on a pretty shitty legacy area of a Python codebase right now (like, literally right now, Claude is running while I type this) and it's struggling for the same reason a human would struggle. What are the columns in this DataFrame? Who knows, because the dataframe is getting mutated depending on the function calls! Oh yeah and someone thought they could be "clever" and assemble function names via strings and dynamically call them to save a few lines of code, awesome! An LLM is going to struggle deciphering this disasterpiece, same as anyone.

Meanwhile for newer areas of the code with strict typing and a sensible architecture, Claude will usually just one-shot whatever I ask.

edit: I see most replies are saying basically the same thing here, which is an indicator.

[csallen]

> LLM-assisted coding is most successful in codebases with attributes strongly associated with high code quality: predictable patterns, well-named variables, use of a type system, no global mutable state, very low mutability in general, etc.

That's all very true, but what you're missing is that the proportion of codebases that need this is shrinking relative to the total number of codebases. There's an incredible proliferation of very small, bespoke, simple, AI-coded apps, that are nonetheless quite useful. Most are being created by people who have never written a line of code in their life, who will do no maintenance, and who will not give two craps how the code looks, any more than the average YouTuber cares about the aperture of their lens or the average forum commenter care about the style of their prose.

We don't see these apps because we're professional software engineers working on the other stuff. But we're rapidly approaching a world where more and more software is created by non-professionals.

[mjr00]

> That's all very true, but what you're missing is that the proportion of codebases that need this is shrinking relative to the total number of codebases. There's an incredible proliferation of very small, bespoke, simple, AI-coded apps, that are nonetheless quite useful. Most are being created by people who have never written a line of code in their life, who will do no maintenance, and who will not give two craps how the code looks, any more than the average YouTuber cares about the aperture of their lens or the average forum commenter care about the style of their prose.

I agree that there will be more small, single-use utilities, but you seem to believe that this will decrease the number or importance of traditional long-lived codebases, which doesn't make sense. The fact that Jane Q. Notadeveloper can vibe code an app for tracking household chores is great, but it does not change the fact that she needs to use her operating system (a massive codebase) to open Google Chrome (a massive codebase) and go to her bank's website (a massive codebase) to transfer money to her landlord for rent (a process which involves many massive software systems interacting with each other, hopefully none of which are vibe coded).

The average YouTuber not caring about the aperture of their lens is an apt comparison: the median YouTube video has 35 views[0]. These people likely do not care about their camera or audio setup, it's true. The question is, how is that relevant to the actual professional YouTubers, MrBeast et al, who actually do care about their AV setup?

[0] https://www.intotheminds.com/blog/en/research-youtube-stats/

[csallen]

This is where I get into much more speculative land, but I think people are underestimating the degree to which AI assistant apps are going to eat much of the traditional software industry. The same way smart phones ate so many individual tools, calculators, stop watches, iPods, etc.

It takes a long time for humanity to adjust to a new technology. First, the technology needs to improve for years. Then it needs to be adopted and reach near ubiquity. And then the slower-moving parts of society need to converge and rearrange around it. For example, the web was quite ready for apps like Airbnb in the mid 90s, but the adoption+culture+infra was not.

In 5, maybe 10, certainly 15 years, I don't think as many people are going to want to learn, browse, and click through a gazillion complex websites and apps and flows when they can easily just tell their assistant to do most of it. Google already correctly realizes this as an existential threat, as do many SaaS companies.

AI assistants are already good enough to create ephemeral applications on the fly in response to certain questions. And we're in the very, very early days of people building businesses and infra meant to be consumed by LLMs.

[mjr00]

> In 5, maybe 10, certainly 15 years, I don't think as many people are going to want to learn, browse, and click through a gazillion complex websites and apps and flows when they can easily just tell their assistant to do most of it.

And how do you think their assistant will interact with external systems? If I tell my AI assistant "pay my rent" or "book my flight" do you think it's going to ephemerally vibe code something on the banks' and airlines' servers to make this happen?

You're only thinking of the tip of the iceberg which is the last mile of client-facing software. 90%+ of software development is the rest of the iceberg, unseen beneath the surface.

I agree there will be more of this but again, that does not preclude the existence of more of the big backend systems existing.

[grey-area]

You are vastly overstating the capabilities of LLMs and the capacity and desire of non-technical individuals to use them to create applications.

[joe_the_user]

The thing, everything you describe may be easy for an average person in the future. But just having your single AI agent do all of that will be even easier and that seems like where things will go.

[datsci_est_2015]

Just like everyone has a 3D printer at home?

People want convenience, not a way to generate an application that creates convenience.

[HeyLaughingBoy]

And perhaps they'll get that convenience from an application that they don't even know came into existence because they asked their agent to do something.

[datsci_est_2015]

What, in practice, is the difference between AGI and what you’re suggesting will exist in terms of agent automation?

[59nadir]

I agree entirely with your statement that structure makes things easier for both LLMs and humans, but I'd gently push back on the mutation. Exactly as mutation is fine for humans it also seems to be fine for LLMs in that structured mutation (we know what we can change, where we can change it and to what) works just fine.

Your example with the dataframes is completely unstructured mutation typical of a dynamic language and its sensibilities.

I know from experience that none of the modern models (even cheap ones) have issues dealing with global or near-global state and mutating it, even navigating mutexes/mutices, conds, and so on.

[zozbot234]

However, code quality is becoming less and less relevant in the age of AI coding

It actually becomes more and more relevant. AI constantly needs to reread its own code and fit it into its limited context, in order to take it as a reference for writing out new stuff. This means that every single code smell, and every instance of needless code bloat, actually becomes a grievous hazard to further progress. Arguably, you should in fact be quite obsessed about refactoring and cleaning up what the AI has come up with, even more so than if you were coding purely for humans.

[bananamogul]

Even non-frontier models now offer a context window of 1 million tokens. That's 100K-300K LOCs. I would not call that a limited context.

[vlovich123]

> However, code quality is becoming less and less relevant in the age of AI coding, and to ignore that is to have our heads stuck in the sand. Just because we don't like it doesn't mean it's not true.

Strong disagree. I just watched a team spend weeks trying to make a piece of code work with AI because the vibe coded was spaghetti garbage that even the AI couldn’t tell what needed to be done and was basically playing ineffective whackamole - it would fix the bug you ask it by reintroducing an old bug or introducing a new bug because no one understood what was happening. And humans couldn’t even step in like normal because no one understood what’s going on.

[csallen]

Okay, so you observed one team that had an issue with AI code quality. What's your point?

In 1998, I'm sure there were newspaper companies who failed at transitioning online, didn't get any web traffic, had unreliable servers crashed, etc. This says very little about what life would be like for the newspaper industry in 1999, 2000, 2005, 2010, and beyond.

[vlovich123]

Im arguing that code quality very much still matters and will only continue to matter.

AI will get better at making good maintainable and explainable code because that’s what it takes to actually solve problems tractably. But saying “code quality doesn’t matter because AI” is definitely not true both experientially and as a prediction. Will AI do a better job in the future? Sure. But because their code quality improves not because it’s less important.

[csallen]

Well then sure, we can agree there, it's just a matter of phrasing then.

[vlovich123]

Then you may want to clarify what your phrasing meant because I couldn’t find a more charitable interpretation

[atomicnumber3]

There's almost no point in arguing about this anymore. Neither you nor the other person are going to be convinced. We just have to wait and see if a new crop of 100x productivity AI believer companies come along and unseat all the incumbents.

[layer8]

It seems that your opinion is based on expectations for the future then, which is notoriously difficult to predict.

[csallen]

It's not that hard to predict that obviously useful new technology is going to improve over time.

Guns, wheels, cars, ships, batteries, televisions, the internet, smartphones, airplanes, refrigeration, electric lighting, semiconductors, GPS, solar panels, antibiotics, printing presses, steam engines, radio, etc. The pattern is obvious, the forces are clear and well-studied.

If there is (1) a big gap between current capabilities and theoretical limits, (2) huge incentives for those who to improve things, (3) no alternative tech that will replace or outcompete it, (4) broad social acceptance and adoption, and (5) no chance of the tech being lost or forgotten, then technological improvement is basically a guarantee.

These are all obviously true of AI coding.

[ThrowawayR2]

That list cherry picks all the successful cases where the technology improved while ignoring the many, many others where it didn't and the technology improved no further. That's dishonest.

It isn't even a good job of cherry picking: we never got mainstream supersonic passenger aircraft after the Concorde because aerospace technology hasn't advanced far enough to make it economically viable and the decrease in progress and massively increasing costs in semiconductors for cutting edge processes is very well known.

[NoMoreNicksLeft]

The newspaper industry is the perfect analogy, because it is effectively dead. Wholesale dead. Here and there, the biggest, most world-renowned papers are still alive, on life-support... NYT, WSJ, etc. But they're all dead. Their death has caused the absolute destruction of an entire industry sector and has given gangrene to adjacent industries that they will soon succumb to. The point about 1998 wasn't that there was this transition that demanded careful attention and wise strategy, but that death was coming for it no matter what anyone did to stop it.

The death of newspapers is quite the spectacle too. No one seems to understand how bad it is... the youngest generation can't even seem to recognize that anything is missing. We've effectively amateurized journalism so that only grifters and talentless hacks want to attempt it, and only in tiny little soundbites on Twitter or other social media (and they're quickly finding out how it might be more lucrative to do propaganda for foreign governments or MLM charlatanism). When the death of the software industry is complete, it too will have been completely amateurized, the youngest generation will not even appreciate that people used to make it for a living, and the few amateurs doing it will start to comprehend how much more lucrative it will be to just make poorly disguised malware.

[mnsc]

But hindsight is 20/20 as they say. In 2020 people predicted that Facebook Horizon would only go one direction, always improve and become as pervasive as the internet. So when you predict that the design and architecture capabilities of models will continue to improve, thus making code quality irrelevant, you sound very confident. And if in five years you are right, you will brag about it here. If not, well I for one will not track you down and rub it in your face. Peace out.

[csallen]

You're confusing betting on a company/product vs betting on technological improvement in general.

It is absolutely the case that virtual reality technology will only get better over time. Maybe it'll take 5, or 10, or 20, or 40 years, but it's almost a certainty that we'll eventually see better AR/VR tech in the future than we have in the past.

Would you bet against that? You'd be crazy to imo.

[mnsc]

Well I wasn't talking about AR/VR tech. I was talking about a society where using VR like in the the visions the company Meta was drawing up. It hasn't manifested and since the company Meta is now downsizing their VR investments the progress of that AR/VR utopia is not _currently_ getting better, because people don't like it/use it. And I got a kid that was HOOKED on vr and spent so much time with his friends on VR, and now. They hang out on Discord and play CS2 on a very flat 2d screen. Will this change "In The Future(tm)"? I don't care but my point is that a statement like "code quality will be irrelevant" miiiight age poorly if in five years, taking into account model improvements, people still care about code quality and the agentic engineers still use extra effort to make certain the outputted code adhers to "good code" standards. I know I will but if ass code turns out to over time be objectively better than good code, I might change my mind or maybe start a new career in something tangible.

See https://simonwillison.net/guides/agentic-engineering-pattern...

[slfnflctd]

There's a kid outside the window of the place I'm staying who's been in the yard playing and talking with people online through his VR headset for like 2+ hours. He's living in the future. Whatever happens, he and his friends are going to continue to be interested in more of this.

Whether what they're using in 20 years is produced by the company formerly known as Facebook or not is a whole different question.

[Philip-J-Fry]

I don't buy this at all. Code quality will always matter. Context is king with LLMs, and when you fill that context up with thousands of lines of spaghetti, the LLM will (and does) perform worse. Garbage in, garbage out, that's still the truth from my experience.

Spaghetti code is still spaghetti code. Something that should be a small change ends up touching multiple parts of the codebase. Not only does this increase costs, it just compounds the next time you need to change this feature.

I don't see why this would be a reality that anyone wants. Why would you want an agent going in circles, burning money and eventually finding the answer, if simpler code could get it there faster and cheaper?

Maybe one day it'll change. Maybe there will be a new AI technology which shakes up the whole way we do it. But if the architecture of LLMs stays as it is, I don't see why you wouldn't want to make efficient use of the context window.

[csallen]

I didn't say that you "want" spaghetti code or that spaghetti code is good.

I said that (a) apps are getting simpler and smaller in scope and so their code quality matters less, and (b) AI is getting better at writing good code.

[camdenreslink]

Apps are getting bigger and more ambitious in scope as developers try to take advantage of any boost in production LLMs provide them.

[csallen]

Every metric I've seen points to there being an explosion in (a) the number of apps that exist and (b) the number of people making applications.

[pessimizer]

What relevance do either of those claims have to the claim of the comment you are responding to?

Are you trying to imply that having more things means that each of them will be smaller? There are more people than there were 500 years ago - are they smaller, or larger?

Also, the printing press did lead to much longer works. There are many continuous book series that have run for decades, with dozens of volumes and millions of words. This is a direct result of the printing press. Just as there are television shows that have run with continuous plots for thousands of hours. This is a consequence of video recording and production technologies; you couldn't do that with stage plays.

You seem to be trying to slip "smaller in scope" into your statement without backing, even though I'd insist that applications individuals wrote being "smaller in scope" was a obvious consequence of the tooling available. I can't know everything, so I have to keep the languages and techniques limited to the ones that I do know, and I can't write fast enough to make things huge. The problems I choose to tackle are based on those restrictions.

Those are the exact things that LLMs are meant to change.

[leptons]

There's already been an explosion of apps - and most of them suck, are spam, or worse, will steal your data.

We don't need more slop apps, we already have that and have for years.

[theshrike79]

Yes, some people are pushing everything-apps.

But just as many are creating One More Habit Tracker or Todo App, so many that Apple had to change their review guidelines to block the surge of low-tier app slop.

Internally people are creating bespoke tools for themselves to fix issues in their daily workflows that would've either been a 100k€ software project that lasts for 6 months or required an expensive SaaS system with 420 extra features they didn't need - and the price to match.

[tadfisher]

The Jevons paradox says otherwise. As producing apps becomes cheaper, we will not be able to help ourselves: we will make them larger until they fill all available space and cost just as much to produce and maintain.

[csallen]

That's the incorrect application of the Jevons Paradox. We won't get bigger apps, we'll get more apps.

Think about what happened to writing when we went from scribes to the printing press, and from the printing press to the web. Books and essays didn't get bigger. We just got more people writing.

[Gigachad]

I’ve been told repeatedly now that if AI coding isn’t working for me it’s because my projects code quality is too poor so the agents can’t understand it.

Now I’m being told code quality doesn’t matter at all.

[vehementi]

Nothing you wrote seems to support what you said at the start there. Why is the importance of code quality decreasing?

[HeyLaughingBoy]

Controversy much :-)

I completely agree. Just going through the beginner & hobbyist forums, the change from "can you help me with code to do X" to "I used ChatGPT/Claude/Copilot to write code to do X" happened with absolutely startling speed, and it's not slowing down. There was clearly a pent-up demand here that wasn't being met otherwise.

People are using AI to get code written. They have no idea what code quality is and only care that what they built works.

AFAICT, every time technology has allowed non-technical people to do more, it's opened up new opportunities for programmers. I don't expect this to be any different, I just want to know where the opportunities are.

[lowsong]

> However, code quality is becoming less and less relevant in the age of AI coding, and to ignore that is to have our heads stuck in the sand. Just because we don't like it doesn't mean it's not true.

It's the opposite, code quality is becoming more and more relevant. Before now you could only neglect quality for so long before the time to implement any change became so long as to completely stall out a project.

That's still true, the only thing AI has changed is it's let you charge further and further into technical debt before you see the problems. But now instead of the problems being a gradual ramp up it's a cliff, the moment you hit the point where the current crop of models can't operate on it effectively any more you're completely lost.

> We are in the very earliest months of AI actually being somewhat competent at this. It's unlikely that it will plateau and stop improving.

We hit the plateau on model improvement a few years back. We've only continued to see any improvement at all because of the exponential increase of money poured into it.

> It's only trending in one direction. And it isn't going to stop.

Sure it can. When the bubble pops there will be a question: is using an agent cost effective? Even if you think it is at $200/month/user, we'll see how that holds up once the cost skyrockets after OpenAI and Anthropic run out of money to burn and their investors want some returns.

Think about it this way: If your job survived the popularity of offshoring to engineers paid 10% of your salary, why would AI tooling kill it?

[csallen]

> That's still true, the only thing AI has changed is it's let you charge further and further into technical debt before you see the problems. But now instead of the problems being a gradual ramp up it's a cliff, the moment you hit the point where the current crop of models can't operate on it effectively any more you're completely lost.

What you're missing is that fewer and fewer projects are going to need a ton of technical depth.

I have friends who'd never written a line of code in their lives who now use multiple simple vibe-coded apps at work daily.

> We hit the plateau on model improvement a few years back. We've only continued to see any improvement at all because of the exponential increase of money poured into it.

The genie is out of the bottle. Humanity is not going to stop pouring more and more money into AI.

> Sure it can. When the bubble pops there will be a question: is using an agent cost effective? Even if you think it is at $200/month/user, we'll see how that holds up once the cost skyrockets after OpenAI and Anthropic run out of money to burn and their investors want some returns.

The AI bubble isn't going to pop. This is like saying the internet bubble is going to pop in 1999. Maybe you will be right about short term economic trends, but the underlying technology is here to stay and will only trend in one direction: better, cheaper, faster, more available, more widely adopted, etc.

[lowsong]

> What you're missing is that fewer and fewer projects are going to need a ton of technical depth. > I have friends who'd never written a line of code in their lives who now use multiple simple vibe-coded apps at work daily.

Again it's the opposite. A landscape of vibe coded micro apps is a landscape of buggy, vulnerable, points of failure. When you buy a product, software or hardware, you do more than buy the functionality you buy the assurance it will work. AI does not change this. Vibe code an app to automate your lightbulbs all you like, but nobody is going to be paying millions of dollars a year on vibe coded slop apps and apps like that is what keeps the tech industry afloat.

> Humanity is not going to stop pouring more and more money into AI.

There's no more money to pour into it. Even if you did, we're out of GPU capacity and we're running low on the power and infrastructure to run these giant data centres, and it takes decades to bring new fabs or power plants online. It is physically impossible to continue this level of growth in AI investment. Every company that's invested into AI has done so on the promise of increased improvement, but the moment that stops being true everything shifts.

> The AI bubble isn't going to pop. This is like saying the internet bubble is going to pop in 1999.

The internet bubble did pop. What happened after is an assessment of how much the tech is actually worth, and the future we have now 26 years later bears little resemblance to the hype in 1999. What makes you think this will be different?

Once the hype fades, the long-term unsuitability for large projects becomes obvious, and token costs increase by ten or one hundred times, are businesses really going to pay thousands of dollars a month on agent subscriptions to vibe code little apps here and there?

[csallen]

> Again it's the opposite. A landscape of vibe coded micro apps is a landscape of buggy, vulnerable, points of failure. When you buy a product, software or hardware, you do more than buy the functionality you buy the assurance it will work. AI does not change this. Vibe code an app to automate your lightbulbs all you like, but nobody is going to be paying millions of dollars a year on vibe coded slop apps and apps like that is what keeps the tech industry afloat.

This is what everyone says when technology democratizes something that was previously reserved for a small number of experts.

When the printing press was invented, scribes complained that it would lead to a flood of poorly written, untrustworthy information. And you know what? It did. And nobody cares.

When the web was new, the news media complained about the same thing. A landscape of poorly researched error-ridden microblogs with spelling mistakes and inaccurate information. And you know what? They were right. That's exactly what the internet led to. And now that's the world we live in, and 90% of those news media companies are dead or irrelevant.

And here you are continuing the tradition of discussing a new landscape of buggy, vulnerable products. And the same thing will happen and already is happening. People don't care. When you democratize technology and you give people the ability to do something useful they never could do before without having to spend years becoming an expert, they do it en masse, and they accept the tradeoffs. This has happened time and time again.

> The internet bubble did pop... the future we have now 26 years later bears little resemblance to the hype in 1999. What makes you think this will be different?

You cut out the part where I said it only popped economically, but the technology continued to improve. And the situation we have now is even better than the hype in 1999:

They predicted video on demand over the internet. They predicted the expansion of broadband. They predicted the dominance of e-commerce. They predicted incumbents being disrupted. All of this happened. Look at the most valuable companies on earth right now.

If anything, their predictions were understated. They didn't predict mobile, or social media. They thought that people would never trust SaaS because it's insecure. They didn't predict Netflix dominating Hollywood. The internet ate MORE than they thought it would.

[lowsong]

> This is what everyone says when technology democratizes something that was previously reserved for a small number of experts.

What part of renting your ability to do your job is "democratizing"? The current state of AI is the literal opposite. Same for local models that require thousands of dollars of GPUs to run.

Over the past 20 years software engineering has become something that just about anyone can do with little more than a shitty laptop, the time and effort, and an internet connection. How is a world where that ability is rented out to only those that can pay "democratic"?

> When the printing press was invented, scribes complained that it would lead to a flood of poorly written, untrustworthy information. And you know what? It did. And nobody cares.

A bad book is just a bad book. If a novel is $10 at the airport and it's complete garbage then I'm out $10 and a couple of hours. As you say, who cares. A bad vibe coded app and you've leaked your email inbox and bank account and you're out way more than $10. The risk profile from AI is way higher.

Same is even more true for businesses. The cost of a cyberattack or a outage is measured in the millions of dollars. It's a simple maths, the cost of the risk of compromise far oughtweights the cost of cheaper upfront software.

> You cut out the part where I said it only popped economically, but the technology continued to improve.

The improvement in AI models requires billions of dollars a year in hardware, infrastructure, end energy. Do you think that investors will continue to pour that level of investment into improving AI models for a payout that might only come ten to fifteen years down the road? Once the economic bubble pops, the models we have are the end of the road.

[2ccg]

Your whole argument is based on 'the technology improves'.

Ok, so another fundamental proposition is monetary resources are needed to fund said technology improvement.

Whats wrong with LLMs? They require immense monetary resources.

Is that a problem for now? No because lots of private money is flowing in and Google et al have the blessing of their shareholders to pump up the amount of cash flows going into LLM based projects.

Could all this stop? Absolutely, many are already fearing the returns will not come. What happens then? No more huge technology leaps.

[subhobroto]

> nobody will ever have to maintain it, so it doesn't matter

I'm curious about software that's actively used but nobody maintains it. If it's a personal anecdote, that's fine as well

[csallen]

I mean I've written some scripts and cron jobs for websites that I manage that have continued trucking for years with no changes or monitoring on my end. I suppose it's a bit easier on the web.

[wiether]

  > However, code quality is becoming less and less relevant in the age of AI coding, and to ignore that is to have our heads stuck in the sand. Just because we don't like it doesn't mean it's not true.

  > [...]

  > We are increasingly moving toward a world where people who aren't sophisticated programmers are "building" their own apps with a user base of just one person. In many cases, these apps are simple and effective and come without the bloat that larger software suites have subjected users to for years. The code is simple, and even when it's not, nobody will ever have to maintain it, so it doesn't matter. Some apps will be unreliable, some will get hacked, some will be slow and inefficient, and it won't matter. This trend will continue to grow.

I do agree with the fact that more and more people are going to take advantage of agentic coding to write their own tools/apps to maker their life easier. And I genuinely see it as a good thing: computers were always supposed to make our lives easier.

But I don't see how it can be used as an argument for "code quality is becoming less and less relevant".

If AI is producing 10 times more lines that are necessary to achieve the goal, that's more resources used. With the prices of RAM and SSD skyrocketing, I don't see it as a positive for regular users. If they need to buy a new computer to run their vibecoded app, are they really reaping the benefits?

But what's more concerning to me is: where do we draw the line?

Let's say it's fine to have a garbage vibecoded app running only on its "creator" computer. Even if it gobbles gigabytes of RAM and is absolutely not secured. Good.

But then, if "code quality is becoming less and less relevant", does this also applies to public/professional apps?

In our modern societies we HAVE to use dozens of software everyday, whether we want it or not, whether we actually directly interact with them or not.

Are you okay with your power company cutting power because their vibecoded monitoring software mistakenly thought you didn't paid your bills?

Are you okay with an autonomous car driving over your kid because its vibecoded software didn't saw them?

Are you okay with cops coming to your door at 5AM because a vibecoded tool reported you as a terrorist?

Personally, I'm not.

People can produce all the trash they want on their own hardware. But I don't want my life to be ruled by software that were not given the required quality controls they must have had.

[csallen]

> If AI is producing 10 times more lines that are necessary to achieve the goal, that's more resources used. With the prices of RAM and SSD skyrocketing, I don't see it as a positive for regular users. If they need to buy a new computer to run their vibecoded app, are they really reaping the benefits?

I mean, I agree, but you could say this at any point in time throughout history. An engineer from the 1960s engineer could scoff at the web and the explosion in the number of progress and the decline in efficiency of the average program.

An artist from the 1700s would scoff at the lack of training and precision of the average artist/designer from today, because the explosion in numbers has certain translated to a decline in the average quality of art.

A film producer from the 1940s would scoff at the lack of quality of the average YouTuber's videography skills. But we still have millions of YouTubers and they're racking up trillions of views.

Etc.

To me, the chief lesson is that when we democratize technology and put it in the hands of more people, the tradeoff in quality is something that society is ready to accept. Whether this is depressing (bc less quality) or empowering (bc more people) is a matter of perspective.

We're entering a world where FAR more people will be able to casually create and edit the software they want to see. It's going to be a messier world for sure. And that bothers us as engineers. But just because something bothers us doesn't mean it bothers the rest of the world.

> But then, if "code quality is becoming less and less relevant", does this also applies to public/professional apps?

No, I think these will always have a higher bar for reliability and security. But even in our pre-vibe coded era, how many massive brandname companies have had outages and hacks and shitty UIs? Our tolerance for these things is quite high.

Of course the bigger more visible and important applications will be the slowest to adopt risky tech and will have more guardrails up. That's a good thing.

But it's still just a matter of time, especially as the tools improve and get better at writing code that's less wasteful, more secure, etc. And as our skills improve, and we get better at using AI.

[hokkos]

If strongly typed languages are preferred for AI coding, maybe the fixation on code quality make LLM produce better code.

[danielmarkbruce]

Maybe, but how exactly are you defining "code quality" ?

[hbarka]

> Some people never get to the part where they review the code. They go straight to their LinkedIn or blog and start writing (or having ChatGPT write) posts about how manual coding is dead and they’re done writing code by hand forever. Some people review the code and declare it unusable garbage, then also go to their social media and post how AI coding is completely useless and they’re not going to use it for anything. This blog post shows the journey that anyone not in one of those two vocal minorities is going through right now.

What’s really happening is that you’re all of those people in the beginning. Those people are you as you go through the experience. You’re excited after seeing it do the impossible and in later instances you’re critical of the imperfections. It’s like the stages of grief, a sort of Kübler-Ross model for AI.

[atomicnumber3]

I'm deeply convinced that there's 2 reasons we don't see real takes like this: 1) is because these people are quietly appreciating the 2-50% uplift you get from sanely using LLMs instead of constantly posting sycophantic or doomer shit for clout and/or VC financing. 2) is because the real version of LLM coding is boring and unsexy. It either involves generating slop in one shot to POC, then restarting from scratch for the real thing or doing extensive remediation costing far more than the initial vibe effort cost; or it involves generally doing the same thing we've been doing since the assembler was created except now I don't need to remember off-hand how to rig up boilerplate for a table test harness in ${current_language}, or if I wrote a snippet with string ops and if statements and I wish it were using regexes and named capture groups, it's now easy to mostly-accurately convert it to the other form instead of just sighing and moving on.

But that's boring nerd shit and LLMs didn't change who thinks boring nerd shit is boring or cool.

[zozbot234]

> because the real version of LLM coding is boring and unsexy

Some people do find it unfun, saying it deprives them of the happy "flow" of banging out code. Reaching "flow" when prompting LLMs arguably requires a somewhat deeper understanding of them as a proper technical tool, as opposed to a complete black box, or worse, a crystal ball.

[devmor]

There’s also just the negative association factor.

I use LLMs in my every day work. I’m also a strong critic of LLMs and absolutely loathe the hype cycle around them.

I have done some really cool things with copilot and Claude and I keep sharing them to within my working circle because I simply don’t want to interact that much with people who aren’t grounded on the subject.

[cossray]

I would be interested to hear your take on Copilot vs Claude. I have used Copilot (trial) in VS Code and I found it to mostly meet my needs. It could generate some plans and code, which I could review on the go. I found this very natural to me as I never felt 'left behind' in whatever code the AI was generating. However, most of the posts I see here are on Claude (I haven't tried it) and very few mentions of Copilot. What is your impression about them and the use cases each is strong in?

[cassidy_co]

(Context: I'm a different person, but have thoughts on this)

I started using Copilot at work because that's what the company policy was. It's a pretty strict environment, but it's perfectly serviceable and gets a lot of fresh, vetted updates. IDE integration with vs code was a huge plus for me.

Claude code is definitely a messier, buggier frontend for the LLM. It's clunkier to navigate and it has much more primitive context management tools. IDE integration is clunky with vs code, too.

However, if you want to take advantage of the Anthropic subscription services, I've found Claude Code is the way to go... Simply because Anthropic works hard to lock you into their ecosystem if you want the sweet discounts. I'm greedy, so I bit the bullet for all of the LLM coding stuff I do in my personal life.

[devmor]

Copilot isn’t really a competing product to Claude - in fact I use Claude through copilot.

I have found in general that for the type of work I do (senior to staff level engineering, 90-10 research to programming) that Claude Opus is the only model really worth my time - but I just really like the Copilot CLI tooling.

[avadodin]

So, are you using it for the 10%?

I do use LLMs to learn about new subjects but we already only bill 10% for "coding" and that's inflating it to cover other parts.

I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?

[devmor]

I would say I'm using it for about half of the "10%" and and a quarter of the "90%".

> I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?

Absolutely, that's a real concern. The only time I will let it loose on something is a throwaway project to test something, or a small tool that I know I can write deterministic tests for.

On codebases of any significant size, I'm using it more like a custom domain Stackoverflow search engine.

[marhee]

Software engineering is only about 20% writing code (the famous 40-20-40 split). Most people use it only for the first 40%, and very succesfully (im in that camp). If you use it to write your code you can theorettically maybe get 20% time improvement initially, but you loose a lot of time later redoing it or unraveling. Not worth bothering.

[bdangubic]

20% is one of those cool lies SWEs have been able to push through (like “our jobs are oh so very special we can’t really estimate it, we’ll create an entire sub-industries with our industry to make sure everyone knows we can’t estimate”).

SWEs spend 20% of the time writing code for exactly the same reason brick-layers spend 20% of their time laying bricks

[skydhash]

The other 80% is spent on the following:

- A lot of research. Libraries documentation, best practice, sample solutions, code history,... That could be easily 60% of the time. Even when you're familiar with the project, you're always checking other parts of the codebase and your notes.

- Communication. Most projects involve a team and there's a dependency graph between your work. There may be also a project manager dictating things and support that wants your input on some cases.

- Thinking. Code is just the written version of a solution. The latter needs to exists first. So you spend a lot of time wrangling with the problem and trying to balance tradeoffs. It also involves a lot of the other points.

Coding is a breeze compared to the others. And if you have setup a good environment, it's even enjoyable.

[megous]

It can be any number of things. From spending hour or two just writing requirements, to giving an example of existing curated code from another project you wrote and would like to emulate, or rewriting existing apps in a different language/architecture (sort of like translating), to serving as a QA agent or reviewer for the LLM agent, or vice versa.

I kinda like how you can just use it for anything you like. I have bazillion personal projects, I can now get help with, polish up, simplify, or build UI for, and it's nice. Anything from reverse engineering, to data extraction, to playing with FPGAs, is just so much less tedious and I can focus on the fun parts.

[te_chris]

Without wanting to sound rude: I think the mistake people make with AI prototypes is keeping the code at all.

The AI’s are more than capable of producing a mountain of docs from which to rebuild, sanely. They’re really not that capable - without a lot of human pain - of making a shit codebase good.

[bmitc]

> This blog post shows the journey that anyone not in one of those two vocal minorities is going through right now: A realization that AI coding tools can be a large accelerator but you need to learn how to use them correctly in your workflow and you need to remain involved in the code. It’s not as clickbaity as the extreme takes that get posted all the time. It’s a little disappointing to read the part where they said hard work was still required. It is a realistic and balanced take on the state of AI coding, though.

I appreciate the balanced takes and also the notion that one can use these AI tools to build software with principled use.

However, what I am still failing to see is concrete evidence that this is all faster and cheaper than just a human learning and doing everything themself or with a small team. The cat is out of the bag, so to speak, but I think it's still correct to question these things. I am putting in a _lot_ of work to reach a principled status quo with these tools, and it is still quite unclear whether it's actually improvement versus just a side quest to wrangle tools that everyone else is abusing.

[zahlman]

I feel like recently HN has been seeing more takes like this one and at least slightly less of the extremist clickbaity stuff. Maybe it's a sign of maturity. (Or maybe it's just fatigue with the cycle of hyping the absolute-latest model?)

[senko]

It takes time for people to go through these experiences (three months, in OP's case), and LLMs have only been reasonably good for a few months (since circa Nov'25).

Previously, takes were necessarily shallower or not as insightful ("worked with caveats for me, ymmv") - there just wasn't enough data - although a few have posted fairly balanced takes (@mitsuhiko for example).

I don't think we've seen the last of hypers and doomers though.

[deaux]

> LLMs have only been reasonably good for a few months (since circa Nov'25).

Ironically this itself is one of the hyper/doomer takes.

[senko]

But is it a hyper or a doomer take?

There seems to be a concencus among people I follow/read, that somewhere around that time was an inflexion point in coding LLMs, and this matches my personal experience.

(My comment was in the context of LLMs being used to generate non-throwaway code, not general GenAI use - apologies if that was unclear.)

[deaux]

> There seems to be a concencus among people I follow/read, that somewhere around that time was an inflexion point in coding LLMs, and this matches my personal experience.

LLMs have been a very useful tool to generate non-throwaway code for at least 2 years. It's a question of Overton Window, of mainstream acceptance, that has made you and the people you're talking about come to a "consensus" that there was an agentic LLM coding step change around that time. There was indeed an inflection point, but it was a social one: a window shift, where it became socially acceptable among mainstream SWEs to hold this sentiment. It had already been the case for a long time, but for those who understood this, expressing that was still not deemed acceptable. Doing so would brand one as a hyper, at least in the particular circles you were in.

You were in reality part of the doomers, just as much as the current doomers are still doomers.

[senko]

> LLMs have been a very useful tool to generate non-throwaway code for at least 2 years.

I was in YC W24 (exactly two years ago) with an AI coding startup ("agentic" and "vibe" buzzwords weren't invented yet). LLMs were useful as smarter autocomplete, but were struggling (and us with them!) on anything nontrivial.

Comparing that state to the past few months and saying it's just a social change is a bit of a stretch :)

[tipiirai]

Can you point to one other post like this? Curious. Thanks

[sharperguy]

It's actually common for human-written projects to go through an initial R&D phase where the first prototypes turn into spaghetti code and require a full rewrite. I haven't been through this myself with LLMs, but I wonder to what extent they could analyse the codebase, propose and then implement a better architecture based on the initial version.

[Deukhoofd]

Let's be real, a lot of organizations never actually finish that R&D phase, and just continue iterating on their prototypes, and try to untangle the spaghetti for years.

I recently had to rewrite a part of such a prototype that had 15 years of development on it, which was a massive headache. One of the most useful things I used LLMs for was asking it to compare the rewritten functionality with the old one, and find potential differences. While I was busy refactoring and redesigning the underlying architecture, I then sometimes was pinged by the LLM to investigate a potential difference. It sometimes included false positives, but it did help me spot small details that otherwise would have taken quite a while of debugging.

[zozbot234]

If you write that first prototype in Rust, with the idiomatic style of "Rust exploratory code" (lots of defensive .clone()ing to avoid borrowck trouble; pervasive interior mutability; gratuitous use of Rc<> or Arc<> to simplify handling of the objects' lifecycle) that can often be incrementally refactored into a proper implementation. Very hard to do in other languages where you have no fixed boilerplate marking "this is the sloppy part".

[klabb3]

Rust is a language for fast prototyping? That’s the one thing Rust is absolutely terrible at imo, and I really like the production/quality/safety aspects of Rust.

[zozbot234]

It's not specialized to fast prototyping for sure, but you can use for that with the right boilerplate.

[nickstinemates]

There is a lot you can do to shape the end result to not have these faults. In the end, the engineering mind and rigor still needs to apply, so the hard work doesn't go away.

But, the errors that are described - no architecture adhesion, lack of comprehension, random files, etc. are a matter of not leveling up the sophistication of use further, not a gap in those tools.

As an example. Very clearly laying out your architecture principles, guidance, how code should look on disk, theory on imports, etc. And then - objectively analyzing any proposed change against those principles, converges toward sane and understandable.

We've been calling it adversarial testing across a number of dimensions - architecture, security, accessibility, among other things. Every pr gets automatically reviewed and scored based on these perspectives. If an adversary doesn't OK the PR, it doesn't get merged.

[moron4hire]

Someone used Claude Code to generate a very simple staffing management app. The sort of thing that really wouldn't take that long to make, but why pay for any software when you can just ignore the problem, amiright? Anyway, the code that got generated was full of SQL injection issues for the most absurd sorts of things. It would have 80% of the database queries implemented through the ORM, but then the leftover stuff was raw string concat junk, for no good reason because it wasn't even doing any dynamic query or anything that the ORM couldn't do.

[prpl]

I find the people who end up with spaghetti code did so because they didn’t translate their normal processes over.

Being completely methodical about development really helps. obra/superpowers, for example, gets close but I think it overindexes on testing and doesn’t go far enough with design document templates, planning, code style guides, code reviews, and more.

Being methodical about it takes more time, but prevents a good bit of the tech debt.

Planning modes help, but they are similarly not methodical enough.

[ianhorn]

That works until you make a plan/tests/etc, set the thing loose, and then when it has trouble it decides "actually the pragmatic thing would be [diverge from the plan/change the tests/etc]" and goes off the rails. I'm so frustrated by these things right now.

[prpl]

I have honestly not had that problem much. Being specific, concise, and strong with your prompts helps out a lot.

[socalgal2]

Unfortunately there is a ton of pressure not to review code. AI enthusiasts see themselves in a race against others and code review = going slower. I recently attended a company wide "let's all use AI" conference and several talks were about how they were not reviewing much code anymore because the PRs were coming in 10x to 50x more and they just couldn't keep up.

Scary AF

[joe_the_user]

This blog post shows the journey that anyone not in one of those two vocal minorities is going through right now

Is there evidence these groups are a minority? I mean, the OP sounds like they are taking the right approach but I suspect it requires both skill/experience and an open mind to take their approach.

Just because an approach has good use-cases doesn't mean those are going predominate.

[throwatdem12311]

For me it’s just a matter of “does this actually save me time at all?”

If it generates the slop version in a week but it takes me 3 more weeks to clean it up, could I have I just done it right the first time myself in 4 weeks instead? How much money have I wasted in tokens?

[sunaurus]

I've been arguing that it's POSSIBLE to get a small (but meaningful) uplift in productivity on average if you are careful with how you use LLMs, but at the same time, it's also extremely easy to actually negatively impact your productivity.

In both cases, you feel super productive all the time, because you are constantly putting in instructions and getting massive amounts of output, and this feels like constant & fast progress. It's scary how easy it is to waste time on LLMs while not even realizing you are wasting time.

[0xbadcafebee]

A car saves you time in getting to and from the store. But if you don't learn to drive, and just hop in the car and press things, you're going to crash, and that definitely won't save you time. Cars are also more expensive than walking or a bike, yet people still buy them.

[throwatdem12311]

I already know how to drive stick (trad coding), I don’t feel like I’m gaining much by switching to automatic transmission.

[0xbadcafebee]

Yeah that's not the difference, lol. With AI coding you can get the same work done in an order of magnitude less time, without even knowing how to program.

The only comparison I can come up with is 3D printers, but even that's not as ridiculously fast and easy as AI coding. An average person can ask an agent to write a program, in any popular language, and it'll do it, and it'll work. We still need people intelligent enough to steer the agent, but you do not need to edit a single line of code anymore.

[skydhash]

Most people that don't know how to program have no real desire in coding with AI (unless to pose as a SWE and get that sweet money). Most of them don't even like computers. Yes they do some tasks on it, but they're not that attached to the tool and its capabilities.

[zephen]

> does this actually save me time at all?

Soooooo....

As one who hasn't taken the plunge yet -- I'm basically retired, but have a couple of projects I might want to use AI for -- "time" is not always fungible with, or a good proxy for, either "effort" or "motivation"

> How much money have I wasted in tokens?

This, of course, may be a legitimate concern.

> If it generates the slop version in a week but it takes me 3 more weeks to clean it up, could I have I just done it right the first time myself in 4 weeks instead?

This likewise may be a legitimate concern, but sometimes the motivation for cleaning up a basically working piece of code is easier to find that the motivation for staring at a blank screen and trying to write that first function.

[throwatdem12311]

Well for me, the amount of time/effort as a function my of my motivation has acted as a natural gatekeeper to bad ideas. Just because I can do something with AI now doesn’t necessarily mean that I should. I am also weary of trading time and effort for outright money right out of my own pocket to find out, especially when I find the people I’d be giving money to so reprehensible. I don’t live somewhere where developers make a lot of money. I’m not poor in any stretch but not rich enough that I can waste money on slop for funsies. But I can spend a month on validating a side project because I find coding as a hobby enjoyable in and of itself, and I don’t care if I throw out a few thousand lines of code after a little while and realize I’m wasting my time.

Cleaning up agent slop code by hand is also a miserable experience and makes me hate my job. I do it already because at $DAYJOB because my boss thinks “investing” in third worlders for pennies on the dollar and just giving them a Claude subscription will be better than investing in technical excellence and leadership. The ROI on this strategy is questionable at best, at least at my current job. Code Review by humans is still the bottleneck and delivering proper working features has not accelerated because they require much more iteration because of slop.

Would much rather spend the time making my own artisanal tradslop instead if it’s gonna take me the same amount of time anyway - at least it’s more enjoyable.

[zephen]

Your position makes an immense amount of sense for your described situation.

As I said, I'm retired, and so I've never had to clean up AI slop at $DAYJOB.

Since the whole AI thing would be a learning experience for me, it would include trying to toilet train the AI itself, as others have intimated can be done in some cases, rather than dealing with a bunch of already-checked-into-the-repo-slop.

And that may be a losing proposition. I don't know; haven't tried it yet.

> Would much rather spend the time making my own artisanal tradslop instead if it’s gonna take me the same amount of time anyway - at least it’s more enjoyable.

Although I haven't had the AI experience you describe, I have had a similar experience with coworkers who moved fast and broke all kinds of shit. That was similarly no fun. It's like trying to work on your wife's minivan, but she won't pull over and let you properly fix it.

Given sufficient time, I enjoy polishing/perfecting/refactoring code. My final output often looks radically different from my prototype. It is clear to me that I would hate the situation you describe. It is not clear to me that starting with prompted slop and wrangling it into submission would be much less enjoyable to me than writing my own slop and then wrangling it into submission.

> especially when I find the people I’d be giving money to so reprehensible.

This is a bit of a concern, but I'm pretty sure that, at the moment, every token you burn costs them more than you.

[throwatdem12311]

The biggest thing that has changed in my experience (at least in a professions setting) is now that people have AI agents they don’t really have any motivation to improve. If you tell them something that needs to be changed they just reprompt the agent until it’s good enough - but the most sinister thing is they keep making the same mistakes over and over again. There is no growth, no shared understanding that disseminates through review - just re-prompting. They often just directly use my review comments as prompts! People don’t understand code they generated themselves just a few days later. But not in a “oh just let me reread this again real quick” kind of way but a “I have absolutely no clue wtf I am even looking at” way.

I’ve been sounding the alarm in my own circles about the lack of junior roles now because of AI - which will lead to a shortage of seniors in just a few years - but there is something even more sinister: juniors no longer improve enough to be intermediates and seniors, and worse…seniors and intermediates have regressed to juniors through laziness and cognitive offloading.

Like if I’m just sending code review to a middle man prompter - why not just skip the middle man? I’m already wrangling a handful of AI agents myself every day, so what is even the point of this extra person anyway? I don’t want to replace people with AI but if the person is so lazy that even I would probably prefer just doing the prompting myself then why shouldn’t I replace them with AI?

[zephen]

That does sound like an intractable problem.

My problem, if and when I get started, would be tangential to this. It is clear that communication with LLMs is changing so rapidly that there may not be any universal long-lived lessons to be learned from optimizing your interactions with a particular model.

I know that one-shotting things is probably not best, but determining how far to take it and when to cut over and finish it myself is something that I want to learn, but perhaps not too well.

My skills are an eclectic mix of high- and low- level. I know exactly what, for example, a frequency analyzer can do for me, but controlling the $400K frequency analyzer is often best left to the guy who lives and breathes it.

Likewise, my debugging skills are exceptional, but I am not as proficient with any particular debugger as are people who live in the debugger daily because they write terrible code. My debugging skills are mostly predicated on a big part of your daily life -- reading code.

(To be fair, I have known a very few people who live in the debugger because they are dealing with intractable problems caused by other people, but those are the rarities. I, myself, used to live in the debugger a lot when I was writing graphics drivers for the mostly undocumented Windows 3.1.)

Which brings us to your reports and/or co-workers. These people have always existed. They pride themselves on and partly base their value on and derive their value from the tools they think they know inside-out.

In truth, they don't know the tools, but they are intimately familiar with the controls of the tool, like a child who knows how to make a smartphone do exactly what their parent needs it to do.

So, as long as it's a tool you need, but it's too painful for you to control directly, these people are useful. In your case, you already have cause to use the LLM directly on a regular basis, so, as you point out, the value of these people is diminishing and maybe already negative.

> why shouldn’t I replace them with AI?

You probably should. Or, at a minimum, if possible, you should restructure things so that the people who are doing things that you are already proficient at are doing them for someone else who isn't as proficient at the tools, and you can get out of that loop.

One reason I am not yet completely insane is that I realized about 40 years ago that the place I hated most being was inside someone else's debug loop. Because most people are objectively stupid, and this goes double for people who need you in that loop. So I always work to structure my responsibilities and work setup to avoid this. If I find a bug in an internal supplier's code, I create an MVCE and hand it over to them. If an internal customer claims to find a bug in my code and doesn't provide an MVCE, I figure out what they are attempting to do, create my own MVCE for their function, and either fix it if it was really my problem, or hand it back to them, and ask them to expand on it until it breaks and get back to me.

Reflecting on this, I realize that I am probably not too likely to succumb to interminable prompting loops, because that wouldn't feel much different to what I nave avoided most of my life. On the few occasions over the last four decades where being involved in someone else's debug loop was completely unavoidable, the most useful thing I brought to the table when they were out of ideas and ready to throw a lot of effort at trying random things was a series of questions like "What are you going to learn from that? What will your decision points be?"

And I'm not much of a gambler, so I won't be spending too many tokens hoping "the next time, for sure!"

[theshrike79]

1. Make it work

2. Make it pretty

3. Make it fast.

If you have something that's pretty and fast but doesn't work, is that useful?

But if you have something that works, but is ugly and slow - you can still use it and fix it while you dogfood it. Maybe figure out other ways to improve it beyond making the code look pretty.

[airstrike]

It's a very accurate and relatable post. I think one corollary that's important to note to the anti-AI crowd is that this project, even if somewhat spaghettified, will likely take orders of magnitude less time to perfect than it would for someone to create the whole thing from scratch without AI.

I often see criticism towards projects that are AI-driven that assumes that codebase is crystalized in time, when in fact humans can keep iterating with AI on it until it is better. We don't expect an AI-less project to be perfect in 0.1.0, so why expect that from AI? I know the answer is that the marketing and Twitter/LinkedIn slop makes those claims, but it's more useful to see past the hype and investigate how to use these tools which are invariably here to stay

[kaoD]

> this project, even if somewhat spaghettified, will likely take orders of magnitude less time to perfect than it would for someone to create the whole thing from scratch without AI

That's a big leap of faith and... kinda contradicts the article as I understood it.

My experience is entirely opposite (and matches my understanding of the article): vibing from the start makes you take orders of magnitude more time to perfect. AI is a multiplier as an assistant, but a divisor as an engineer.

[airstrike]

vibing is different from... steering AI as it goes so it doesn't make fundamentally bad decisions

[0xbadcafebee]

Both of these are not really the right way to use AI to code with. There are two basic ways to code with AI that work:

1. Autocomplete. Pretty simple; you only accept auto-completes you actually want, as you manually write code.

2. Software engineering design and implementation workflow. The AI makes a plan, with tasks. It commits those plans to files. It starts sub-agents to tackle the tasks. The subagents create tests to validate the code, then writes code to pass the tests. The subagents finish their tasks, and the AI agent does a review of the work to see if it's accurate. Multiple passes find more bugs and fix them in a loop, until there is nothing left to fix.

I'm amazed that nobody thinks the latter is a real thing that works, when Claude fucking Code has been produced this way for like 6 months. There's tens of thousands of people using this completely vibe-coded software. It's not a hoax.

[airstrike]

#2 does not negate my steering suggestion, so I'm not sure how you can conclude nobody thinks it's a real thing that works

also Claude Code is notoriously poorly built, so I wouldn't tout it as SOTA

[0xbadcafebee]

I have worked at companies from startups to fortune 500. They all have garbage code. Who cares? It works anyway. The world is held together with duct tape, and it's unreasonably effective. I don't believe "code quality" can be measured by how it looks. The only meaningful measure of its quality is whether it runs and solves a user's problem.

Get the best programmer in the world. Have them write the most perfect source code in the world. In 10 years, it has to be completely rewritten. Why? The designer chose some advanced design that is conceptually superior, but did not survive the normal and constant churn of advancing technology. Compare that to some junior sysadmin writing a solution in Perl 5.x. It works 30 years later. Everyone would say the Perl solution was of inferior quality, yet it provides 3x more value.

[zozbot234]

> when Claude fucking Code has been produced this way for like 6 months

And people can look at the results (illegally) because that whole bunch of code has been leaked. Let's just say it's not looking good. These are the folks who actually made and trained Claude to begin with, they know the model more than anyone else, and the code is still absolute garbage tier by sensible human-written code quality standards.

[0xbadcafebee]

Yet it works anyway. What does that say about human code quality standards?

[cush]

Good code will stand the test of time. No matter how great a project is, there’s no world in which I adopt anything written over a few months and just released, for maintenance reasons alone.

[wolttam]

> you need to learn how to use them correctly in your workflow and you need to remain involved in the code

I completely agree that this is the case right now, but I do wonder how long it will remain the case.

[vasco]

Those extreme takes are taken mostly for clicks or are exaggerated second hand so the "other side's" opinion is dumber than it is to "slam the naysayers". Most people are meh about everything, not on the extremes, so to pander to them you mock the extremes and make them seem more likely. It's just online populism.

[beepbooptheory]

I'm sorry, who is this for? Aren't you maybe a little tired of talking about this, if not totally <expletive> bored??

There is something at this point kind of surreal in the fact that you know everyday there will be this exact blog post and these exact comments.

Like, its been literal years and years and yall are still talking about the thing thats supposed to do other things. What are we even doing anymore? Is this dead internet? It boggles the mind we are still at this level of discourse frankly.

Love 'em hate 'em I don't care yall need to freaking get a grip! Like for the love god read a book, paint a picture! Do something else! This blog is just a journey to snooze town and we all must at some level know that. This feels like literal brain virus.

[order-matters]

i feel like it's worth noting that for a long time prior to AI, I heard a ton of anecdotes about codebases at big companies being very shitty spaghetti more often than not, and if one of the maintainers left it was often a nightmare of managing, refactoring, or in some cases re-writing whenever issues popped up with new integrations

If AI needs to re-write everything from scratch everytime you make a design change, that may have some obvious inefficiencies and limitations to it but if it can also do that in a few hours or a week, is it really that bad comapred to months of stalling and excuses from devs trying to understand the work of someone before them who wasnt given enough time to make well documented clean code to begin with?

Like it is undoubtedly worse for hobby projects to rely on the AI output 100%, but im actually not so sure for commercial products. It'll be the same type of spagetti garbage everywhere. There will be patterns in its nonsense that over years people will start to get accustomed to. Youll have people specialize in cleaning up AI generated code, and itll more or less be a relatively consistent process compared to picking up random developer spaghetti

maybe this is a hot take though

[iamandoni]

This is exactly why I built https://github.com/andonimichael/arxitect . I’ve found that agents by default produce tactical but brittle software. But if you teach agents to prioritize software architecture and design patterns, their code structure becomes much much better. Additionally, better structured code becomes more token efficient, requires less context to make changes, and coding agents become more accurate.