The growing divide between AI hype and software engineering reality

that’s the thing, you can have the LLM study and make a skill to only code in the maintainers preferred style or readability.

Yeah, it's a bit absurd. There's so many empirically measured benchmarks where LLMs clearly exceed human capabilities and efficiencies!

How do you know your average AI PR is better than a human developer? Most of the teams that I see touting the benefits almost never review the code that's output, or they offload that process to another agent.

Like I see people say this, and yet the teams that are AI maxing produce worse code than ever. Software has rapidly gotten more unstable and unsustainable over the past three or so years than I've experienced in the past 20.

I agree, and I think what you’re describing is only scratching the surface of what’s possible today.

It’s even more powerful with large data and knowledge sources connected.

Takes a lot of work to set up effectively, but when connected to Slack _properly_ (not their MCP; but API which is more powerful), a database of your repo’s PRs/comments, data warehouses including analytics/telemetry and logs; and in a strong harness (including using multiple models simultaneously; like the OMP advisor pattern), what AI can achieve combined your domain expertise and human intelligence is just mind bogglingly crazy.

The larger your codebase / product / volume is; the more powerful it gets. AI has found many needles in haystacks that’s just impossible for a single person or team in large companies; because nobody has all the context.

I’ve embraced it too now. Initially I felt a bit disempowered and just somewhat uncomfortable.

Over time, I realised that I’m still doing serious and interesting engineering: just at a higher level of abstraction.

And for the craft and passion of software engineering, I have a couple of pet projects where I use ‘limited AI’. Good to still keep your wits sharp.

They are only good in the context of the engineer guiding them.

I really can’t imagine what would happen if I didn’t manually intervene sometimes and just kept prompting it for the new behavior I wanted.

I've been really struggling to get AI to write good quality c# code, or to be precise, what I see as good quality. I'm in two minds on if it matters or not.

On one hand I think, I want to be proud of it, I want to be able to explain it, if it breaks I want to be able to figure out why.

On the other hand, AI can do all of that with badly written code, so who cares.

Edit: however, it still feels like an amazing power tool, but it has taken me months to figure out how to use it.

I have the opposite experience of everyone else I follow online, I find it terrible at green field and great at brownfield. Green field it makes horrible choices as it has nothing to follow.

I'm in no way a very good programmer, or very smart, but the code I saw most of my co-workers writing was about the same quality as AI, not very good.

> ... you can be living in a golden era for software development.

Let's assume for a moment that you're correct. That AI is already better than most developers, for whatever definition of "better" you like, and they will very soon be better than any person. (I think this is a total fantasy and you've failed to recognise the limitations as the article points out, but I digress.)

In that case the end goal of these companies is to replace all software engineers. Do you not see that? They've not been hiding this fact. It's a good thing for you and I that these models don't work, because if they did the "golden age" is not coming for us, it's coming for people who own compute capacity and the rest of us will become labourers.

I kind of agree that the post is a bit too far away from the trenches to be able to claim it will reveal "software engineering reality".

From where I snipe, I see a big divide between those...

1) that try to surrender to AI, aiming to fully replace value-added intellectual effort and often also to augment enterprise value-mask slop busywork...

...they fail, and succeed, and the collective suffers.

2) those that ride AI to get more challenged, more feedback if any kind, to tread further but with attention to the right details

...they succeed

The problem is that skill at coding is not exactly the same thing as skill at developing and maintaining software, and AI can help there as well, but a swarm of cowboy coder agents will get you to a legacy codebase very very quickly.

And even if the AI is better than most humans, the speed means that you get more defects and issues! If a human developer has a change failure rate of say 10%, (1 in 10 changes causes a defect or issue), and AI is twice as good and only introduces bugs 5% of the time, but submits 10x as many changes, then you go from 1 bug per unit of time to 5 bugs per unit of time, so your velocity is up 10x but your defect rate is up 5x...

> human coders for the most part have been really awful at writing code.

They are better when copying and pasting expert code, even when they don't understand it.

It hasn’t climbed the complexity bar for hard software engineering yet, fable still can’t build a fully functioning C Compiler, I think in the long horizon eval it can sometimes build a C pre-processor (not deterministic) given all the tests and a spec. And given the tests is a big deal, humans actually write the tests on their own while developing btw. Anthropics marketing stunt C compiler doesn’t count (that one didn’t even type check).

Now the thing to claim “a better coder than humans”, is you can’t just stop at making a production grade C Compiler, you then also need to make the leap to make something new that is a definite improvement over everything that existed before it. This is an also a question of taste not just implementation chops. Think Zigs cross platform C Compiler, Rusts memory safety opinionated compiler and more.

The day AI can do both, implement a complex production grade project, and make a conceptual actual improvement upon SOTA is the day I’ll agree AI has become better than humans at coding. I’ve underestimated AI in the past, maybe with 10T of compute they’ll get there, maybe they won’t , we’ll know in the coming years

> AI is already better than most developers.

My experience, no its not. It just doesn't fight back as much when you tell it that its wrong.

My sister team is vibecoding the shit out of a couple of product PoCs. There is only one person on that team that appears to understand how to vibe code properly. the rest are just producing shite and breaking the service everytime they deploy. However, the code it creates is fine enough, just the architecture is bad, or the prompter is bad.

_however_ the problem with the post is that its using tangential metrics to prove the point. The opensource maintainer bit doesn't always mean that the output is bad, it means that either:

1) the maintainers hate AI

2) the shit they are getting is huge and takes too long to review

3) The shite they are getting solves a specific problem for one user at the expense of everyone else

4) the PR is nonsense.

only one of those options area signal for code quality from LLMs. the rest are about the skill of the creator, or attitude/time budget of the maintainer.

I generally agree with this. One of the strangest things about LLM driven engineering is holding two seemingly contradictory positions in your head: they’re both better than the median developer, and they’re also much worse at producing artifacts that are comprehensible to humans.

I often find myself throwing away large amounts of LLM driven code not because it’s bad, but because it doesn’t fit within my attention span. The code itself looks very reasonable, passes tests, benchmarks well, etc. But I throw it away because the models don’t yet “explain” their decisions in ways that elicit psychological safety. Humans are still very good at that, even when their engineering is worse.

The golden era that hasn't produced anything of note yet. More pro-AI advertisements from someone who needs AI crutches.

> AI is already better than most developers.

A tool can only be as good as the person who use it.

> Leverage your knowledge of systems, software engineering and product design and you can be living in a golden era for software development.

For a short while, maybe. If an LLM can keep track of a 500KSLoC codebase, it's gonna easily replace systems knowledge workers, software designers and product designers.

None of systems knowledge, software engineering and product design is a moat against this.

I think LLMs can be used productively, but I also think the average PR from an LLM is crap. They can be decent (or even excellent) at writing code, but they're mediocre at deciding what code to write, and terrible at deciding what not to write.

> AI is already better than most developers

By what measure? How do you even compare developer skill?

I think one problem with this whole conversation is that “coding” is not one thing, and skill at it can mean many different things depending on the context.

In my experience, the top models still generate tons of useless slop on any non-trivial implementation request that I do not essentially solve in the prompt beforehand (change this class, this function, etc). They also still make trivial errors that no human would make (although the inverse is also true). In this sense, they do suck at coding.

On the other hand, even weaker models can understand large sections of code, come up with correct implementations of changes, and catch non-trivial edge cases in many situations that is obviously better than most devs. In this sense, they are better than almost all human devs, especially when considering the time and cost.

Perhaps in the long term AI will help us distinguish better between different types of coding tasks and programming disciplines

This is a very misguided idea.

Humans have value judgement. AI doesn't. AI doesn't "know" what good code even is. For something to be good, there has to be a purpose. Good is the measure of how well that purpose is fulfilled.

Humans can write better or worse code, but AI is not even in the category of things that can write better or worse code. A human needs to be there to tell bad code from good code.

* * *

Also, in my personal experience with AI code: I'm yet to see good code (but I haven't worked with people who are good at directing AI towards their goals). All code I've seen generated by AI so far ranged from "absolute garbage" to "passable". Which, most likely, reflects the ability of those who managed the tool: before they did that, their code was also atrocious. It was easier to deal with, because the velocity at which these people produced garbage didn't cause a deluge in the same way they do it with AI help.

* * *

A note on what I believe to be good code and its distribution. First of all, I agree with you on that the vast majority of code produced to date is very bad. There are many reasons for it: until few years ago the demand for programmers was smaller than supply and the industry was on course to create conditions for very bad programmers to succeed anyhow (help the losers lose less, tee-hee!). It still didn't recover from all the "paradigms" it created to support bad programmers.

Unlike in well-established fields, where you'd expect normal distribution in terms of how skillful the workers are (i.e. you'd expect very few to be very bad and very few to be very good, but most would be good enough), the distribution in programming is exponential: overwhelming majority are at the proverbial bottom of the barrel, only a few are OK, and you probably will never meet a truly good one. This defies intuition and leads us to assume that the barely palatable is the best it can possibly be. And that's, roughly, where AI is at at the moment.

The best point Otto makes is how much time LLMs take off coding a fundamental starting point, but finding and removing edge cases still 100% requires humans to fix and find them.

Exactly. I envision this future too. But we'll come back to a divide in what we call software engineering vs. software development as a whole lot becomes more trades level work outside of a few specialized areas. Frankly, it sounds appealing to be a clanker whisperer, part-time in my retirement doing the kinda work you mention. I started my career building those small business automation and loved it.

I think that technologies will continue to commoditize and arrive at the global mean (median?), so the need for accountants to have the vocabulary just disappear. They will say what they want and it will be coded, deployed, with CDNs and firewalls and whatnot, the domains will be bought. We are not that far from this state already.

So, I don't buy this Jevons paradox idea for software engineering. I think these explanations that as the software development process becomes more efficient, the need for software developers will increase is incorrect in the context of LLM adoption. Instead, I think it should be phrased as the LLMs become more efficient and widespread, the need for LLMs will increase. Reduction in developer demand will be tangential.

And I am saying this wishing this wasn't true being a developer myself.

Certainly this is the impression true believers have had for at least a year. Nobody seems to have been left in the dust yet though. How odd.

I've heard it matters less now, but I also don't like being impolite to inanimate objects.

Not being polite just further nourished our basest animal instincts, which the internet has already enflamed. I’ve watched people slide into severe impatience and antisocial knee jerks as a result of too much time online, including myself. Driving and synthetic (online/ai) social interaction make many of us a little more assholeish. And of course, there’s a negative feedback loop, as this further polarized online discussion angering people even more. It’s rather depressing, and it seems no online realm is safe (including HN)

"this stuff should've been automated years ago in frameworks and in libs, or through sane programming langs that dealt with memory and logic flow better."

70 years of working on the 'how do I reuse code?'. And the solution just takes all the electricity in the world.

I'm biased, being a software technical writer and not a dev, but at least from my side of the fence I think LLMs are no better at generating docs than they are at generating code, and might actually be way worse :)

My devs keep throwing Claude-generated writeups at me that look okay at first glance but fall apart when you actually try to follow the instructions they lay out (which makes them useless for anyone who's not already familiar with the product or feature they're describing), and/or have major structural and logical gaps, and/or gloss over messy details in a way that makes the product or feature sound better but doesn't reflect the reality of what we actually built.

Which turns into an ironic ouroboros where I then have to punch my own queries into an LLM and ask it to read our codebase, compare those details against the original writeup, try to decipher what the hell it was trying to say, etc. And even that turns into an extended back-and-forth where my LLM is like "The original writeup is inaccurate; it should say X" and I'm like "Are you sure? That contradicts what I know about related concept Y", and then the LLM is like "Good point, I dug into it more and the real answer is Z." (And even then, god only knows if Z is correct. I still have to get real developer eyeballs on anything before it goes live.)

> Is half of the industry under AI psychosis right now ?

A bad coder sees bot code as an inprovement. A good coder sees bot code as deterioration.

They are both correct.

Yes, it appears so, as you can see from your downvotes and the simplistic cheerleading further up this thread.

> I don’t think it’s widely accepted financial markets are in an AI bubble or there is actually any evidence to support this

It's widely reported on and discussed. You'll find plenty of people saying it isn't one, but I'm sure you can find an economist willing to take any position you like if you look hard enough. Not to mention everyone who's financially incentivised to continue to claim that there isn't a bubble.

> Even the most skeptical investors to bubbles like Buffet and Burry, have large stakes in Google and Microsoft, front line bets on AI.

Burry has been warning about an AI bubble for years.

> There is essentially nothing magical about being human. Our primitive brains were trained on logic, reasoning and processes. An LLM is simply this on less efficient hardware, but, improving at a speed faster than human evolution.

There is no basis for this claim. There is no evidence that human brains and the process of evolution that led to modern humans is at all similar to how LLMs function. If you're going to evaluate an LLM then evaluate an LLM, you can't say "Humans can do X, LLMs are like humans, therefore LLMs can/will do X" because there is no evidence to connect them.

You can usually safely dismiss sentences that start with “It’s widely accepted that…” because if it were actually true, they wouldn’t need to hedge like that. The usual reason to start a sentence like that is when it isn’t as widely accepted as they claim, but they would like the reader to believe that it is. When something is widely accepted, you can just say it without the weasel words.

https://en.wikipedia.org/wiki/Weasel_word

For me to believe this is not a bubble, I'd want to see that revenues exceed expenses by a large enough factor to sustain the business (often a 10% or greater profit margin). Right now, every one of these companies is following the Uber business model: give the product away at below market prices to hopefully capture the market and force their competitors to go bankrupt first. They're also speed running the bubble with massive data center builds that will increase their debt and future interest payments on that debt.

The question for me isn't "is this a bubble", it's "how many of these companies will be left after it pops". The few companies that remain are likely worth their current inflated value. But I'd want to see the back of the envelope math showing that all of the companies together will be able to earn the necessary profit to justify their valuations, how much revenue would that require, and how does that compare to the current tech purchasing today.

> stop saying “please” to an LLM. It does not have any feelings.

> Yes, but I still prefer a nice tone. Like why should I change my manners just because it has no feelings? If anything the statistic predicts a friendlier answer when I say "please".

It's a probabilistic generator. If you set the tone of the conversation it will follow it.

Try inserting a few jokes, puns etc into a conversation and you'll see that it responds kn kind.

Just like if you ask highly specific technical questions, it responds using highly technical language. If you ask questions in legalese it responds using precise legal terms.

That's what happens when a token predictor has a conversation: it can't have any tone other than what you give it.

So continue saying please, and you'll have more pleasant conversations.

> Yes, but I still prefer a nice tone. Like why should I change my manners just because it has no feelings? If anything the statistic predicts a friendlier answer when I say "please".

Like you I generally prefer polite phrasings over rude ones, and I'm certainly not going to tell you how you should communicate to LLM models, however it's interesting to note that being somewhat rude and to the point seems to have some objective advantages, see for example:

Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)

https://arxiv.org/abs/2510.04950

Understanding Tone-Dependent Inference Cost in Large Language Models

https://arxiv.org/abs/2607.23915

I would hate for this style of communication to leak through to daily communications with humans (e.g. colleagues) though, so even just for that it can make sense to hold on to a polite form of communication :-).