If anything it seems wide deployment of LLMs would go against this. When nobody writes code by hand anymore, who will care about the ergonomics of programming languages? And even if a few do care, how would you get adoption? I expect everyone will just use whatever is already used most.
I agree, it seems like the current most popular languages and frameworks will become ossified, because they have the highest amount of training data. It's hard to see a future where Python and JavaScript aren't the most popular languages to use (assuming LLM-assisted development is the norm moving forward).
LLMs can be pretty conmpetent at languages that have zero training data, at least to the extent that those languages use features/ideas that are familiar. I wrote a toy language/compiler and AI can write code for it competently.
It seems that now more than ever, testing is important. But LLMs love to cheat the tests and make them superficially pass. If you're never reading the code, how do you know changes are reasonable?
I do review, if only whatever I do was the norm for everyone :)
Do you see lots of posts about new compilers and languages and language features on HN in the last year? Maybe I just missed them. I'd love to read more posts like that and fewer about agent frameworks.
Lots of people seem to think that you don't need to learn how to [scan a network], all you need to learn in this brave new world is how to prompt the agent to [scan a network].
The more time LLMs are a hyped thing now the more I realize how immensely important human expertise is. I recently stopped all usage of LLMs due to this. Skill degradation hits hard, learning effect is zero and the outcome is not really something a person without adequate expertise can properly judge. I fear we will loose a lot of human expertise due to this marketing stunt of a technology.
People often claim learning is actually supercharged with LLMs but to me it's the opposite. I didn't learn anything within the past year.
The irony here that if you ever do any kind of practical woodworking lessons or general hands on craft work, metal working, or any 3D, you will be encouraged to use hand-tools over bandsaws, etc. The reasoning being so you know the fundamentals of what you're trying to achieve with the more complex tools later on.
It's always held true: You'll never get the most out of advanced tools unless you can 'do it by hand' so to speak
I studied computing at AS level in the UK (16-17 years old). I learned about: computer components (disks, memory, cpu), binary, ASCII, assembly and machine code. We programmed in Turbo Pascal. I then spent ten years doing non-computer things until I came back to a masters. I was one of the top students in my masters because i didn't need help with fundamentals. The other top student had previously made contributions to the linux kernel (even though he was a philosophy grad...).
The argument for having autonomous LLMs/Agents often ends up as "none of us need to know about assembly, why do i need to know about the code?".
> Sorry, but to me an LLM is nothing but a tool. It is not a replacement for my expertise and it is definitely not something to outsource my thinking to.
Great on you, that's indeed how LLMs should be used, proper. But if anything, the article demonstrates someone is trying to outsource thinking to an AI agent.
The weird thing is that this is the utopia that the AI companies are chasing - this is the best case scenario where AI doesn’t kill us all. We become happy sheep relying on the AI to think and provide for us.
"It is well that we are so foolish, or what little freedom we have would be wasted on us. It is for this that Book of Cold Rain says one must never take the shortest path between two points."
To be honest lots of developers think they don’t need to learn machine code. They just need to learn a language which once compiled will produce machine code.
I wonder if a probabilistic compiler would be fine for the people arguing this. One that sometimes produces machine code that does something else, and sometimes produces machine code that is just broken and does nothing useful. From the same source code.
What if your compiler could be fooled by some other developers into spending thousands of dollars, and still not produce the desired machine code in the end?
Understanding assembly/machine code is optional but helpful. The programming language semantics are enough to reason about what the program is doing. Other tools also help, but are optional for learning how to program.
Using an AI, there is no semantic model that can be used to reason through. You're left without any mental model of the proglblem at all.
I've been arguing for years that is isn't optional and treating it like it is is how we ended up with Electron and 400MB JavaScript websites.
When you have no mental model of the machine running your code or what the physical implications of code mean, you fundamentally lack the ability to reason or care about performance. "Works on my machine" is the original vibecoding.
I mean I don't disagree, but there's still a difference in the kind of disconnect you get. The disconnect is harmful in the high-level language case, but it's dangerous and irresponsible with vibe coding/LLMs.
Also, I would argue that a good enough understanding of computer architecture and a mental model of a process' memory layout gets you there, without knowing how to write assembly. That's still a mental model.
LLMs these days seem to have no problem using language semantics to conceptualize what’s happening in a program. This is my favorite use of an LLM, “why is this library doing x” and then it digs through the library itself in my venv to find an answer.
What I've done is ask the LLM a question like "How do I configure EF Core in this particular way?", then when it tells me the answer, I go and look up that function in the EF Core docs and learn by reading the docs. (Which also tells me whether it's correct or hallucinating; one time the LLM told me "You can do X like this" and the documentation said "We don't yet support doing X, but in a future version you'll be able to do it like this"). Here, I'm using the LLM to compensate for the fact that MSDN search is awful and the bits of info you need are scattered across three different articles, none of which link directly to each other.
You internalize the inner workings of all the libraries in your venv? Impressive! My current project’s uv.lock has ~60 packages in it already, reading and comprehending those tens to hundreds of thousands of lines of code must be time consuming.
You’re also just confidently wrong about the model reading the code. It quotes file paths and line numbers and I open and read those files at those line numbers. For me, hallucinations are much more frequent when it references the docs rather than code because docs are more subjective than code.
This is a normal thing I’ve been doing since at least December.
I have to ask — do you actually use LLM coding tools? Your knowledge on this topic seems really out-of-date.
The fundamental architecture of LLMs has not changed, so knowledge on that cannot be out of date.
Do I internalize the inner workings of all the libraries? Not unless it's necessary. Sometimes it is. If I want to read the source code of the function I'm calling, I can just do that, my IDE pulls up the file with one key combination.
I'm perfectly capable of reading source code myself, I don't need a non-deterministic filter in between.
Compilers are deterministic and, luckily, not agentic.
But yes, it's not obvious (or perhaps even likely) that it just happens that current high-level languages are the "correct" optimal level of abstraction at which you can ignore the sausage-making details at the lower levels. Ultimately, of course, it depends on the use case. Something like Python is so far removed from machine instructions that knowing assembly hardly gives the programmer any additional value.
(Also, obligatory reminder that assembly and even numeric machine code are also abstractions, an "API" provided by the CPU. Instructions get split or fused into micro-ops, named registers are a backwards-compatible abstraction over a much larger register file, instructions get reordered and executed in parallel depending on their data dependencies, a large fraction of the total transistor budget is spent on multi-level caches and cache logic to maintain the illusion of fast access to a single, uniform memory space...)
The catch is just that if you lack the capacity to estimate how much computing power [task in brackets] might need, and your agent can autonomously create AWS instances, that might have bad consequences for you (or your bank account).
If it's a one off and needs no or minimal maintenance work afterwords, sure.
If it's intended to be actively maintained, then you probably should understand how things work, unless you want to wipe everything and start from scratch when the LLM creates such a mess that it can't be sorted out.
It's interesting user43928 that you only created your account here 19 days ago and that every one of your comments is pro AI. You don't comment on anything else. Also interesting that you promote Fable by name here (it was only released 2 days ago).
(Don't worry, I know I'm rowing against the tide with this comment. The AI people have decided to destroy the commons for a few more millions on top of the billions they have already been given. It's a shame.)
What's crazy is the prompt must be something like "pro-AI but still believable and measured", since its "fixed my iOS app albeit with back and forth". Interesting, they know the HN crowd for sure.
Is that surprising, considering I'm using AI a lot?
I have not hand written a single line of code in months on my side projects.
Obviously I am also interested in discussing the latest model. Your claim that I promote anything or otherwise don't engage here in good faith is both misplaced and against the site rules.
Since it couldn't reproduce the issue in the iOS simulator, I had to run it on the device, reproduce the issue, and provide the logs.
This went on for many rounds, during which I tried to steer it toward what I thought was the source of the bug, while the model mostly kept adding instrumentation and logs.
In the end the cause was not what I suspected, but reasonably close to it via another mechanism.
If you look into large fully-vibecoded projects getting styling changes to work is a nightmare. The problem with agents is using them on large projects without manual review for consistency, guidelines and taste. Doesn't really matter the type of project.
Agents can't look at a large system holistically, guidelines on .md files only go so far.
This line of thinking is like suggesting people who would like to become structural engineers should learn to Google plans and copy them since in the future, all plans will be out there more or less, or something that insane.
I suggest people who need some structural engineering done may use an AI tool to do it, in the hypothetical scenario that it was within the AI's capabilities.
That's hardly insane. Not everyone is interested in learning something they want done.
If you do the thing yourself, you know your knowledge limits, you know where the thing lacks. With LLMs, you don't. Maybe it works, maybe it doesn't. You have no idea.
CSS keeps improving and models still train on legacy. So yes, knowing what’s possible and how is very much needed if you want to do something scalable and maintainable.
Random blog or landing page, not so much.
If the other people in the org are using LLMs to a similar degree, any question to which an LLM can provide a good answer to will never get sent. How useful are the draft replies then?
But seriously: It's a game. If that kind of "productivity" is seen as a positive measure of their worth, then in this game they're rewarded for optimizing it.
And the game is simply fucked up.
And that's not new. Ye olde corpo rat race has always often revolved not around maximizing the things that are useful, but instead around maximizing the things that the boss-man perceives to be valuable.
Here in 2026, if the boss-man is himself boss-maxxing by using a bot to evaluate performance, this kind of automated charade would probably work very well. Champagne would fall from the heavens. Doors would open. Velvet ropes would part.
This game is quite clearly not sustainable and must ultimately collapse, but it's still a game with winners and losers. Historically, lots of unsustainable games have left winners standing around when the the games ultimately collapses.
(And, to be frank: It's perfectly OK to hate the game. It's also OK to hate the players and the mediators.)
I guess the point might not be to be useful, but to pingpong responsibility back to somebody else. "There, sent a response, not it's their problem again."
> After news broke out of Volkswagen cheating on diesel emissions, multiple other vehicle manufacturers got caught falsifying emissions data, as well as exceeding legal emission limits. This uncovered a greater industry-wide issue that goes far beyond only Volkswagen Group.
It starts with some things that minimize the lawsuit area, but over time it transforms into a habit of lying. It's company policy, you know? Don't question, just execute.
No, but there are a lot of them, and principal and staff engineers, and solo folks who would get to set the culture if they ever succeed.
A lot of people's taste making comes from reading the online discussions of the engineering literati so I think we need old folks yelling at clouds to keep us grounded.
"It's a big club and you ain't in it". Obviously the problem is the club is too small, that's why for most of the people it is true that they are not part of it.
"Half the population is stupider than how stupid the average person is". As if somehow there's not a single person exactly on the median. In fact there is probably a huge number of people there, and within a margin of error of it.
How do you figure? I don't have a problem with Carlin, but with people who quote him as a source of wisdom.
The commenter who quoted him here in the thread meant to make a joke and I didn't get it? I thought he quoted him as a point against the law we are discussing.
> "Selling is legal, and fucking is legal; but selling fucking is not legal."
I don't get it. The literal interpretation is a clear joke, as you say. So what's the point that it is making?
To be clear, I think the law discussed is stupid. I also think the argument that if both parts are legal they should also be legal together is wrong. What am I avoiding?
I am quite acquainted with Carlin. If there's anyone that can have their absurd logic repeated back to them, it would be a comedian. And That Right Soon.
If you are not an insider with special info and special access, no matter what you do in the market, you eventually lose to the insiders. So, if you blur the details a bit, you're just giving your money to these people.
The rational move would be to just not participate in a market where insider trading happens. I don't really understand why people aren't avoiding these markets like the plague.
I find it very hard to understand why so many people and institutions are still participating in markets that are obviously full of insider trading. It's basically just giving money away to the insiders. Why do people do this?
You're a fund manager. What's the alternative? Throw your hands up and tell your customers to take all their money back, you don't want to get paid anymore?
Exactly. Barter is super insanely expensive in comparison with the most manipulated paper markets; thus, if you closed the current markets, the participants would be very highly incentivized to create a new one, which would likely be worse on all accounts.
It's their job and if they're good at it, they still win / earn money. Someone who's staying eyes glued to the price charts on 12 stacked monitors will be the first to see a trend and buy/sell immediately after the action of the insider trader.
Institutions do not stake their own money and are somewhat averse to the direction of the market. As for common people, they're generally not known to do the most rational thing.
If anything it seems wide deployment of LLMs would go against this. When nobody writes code by hand anymore, who will care about the ergonomics of programming languages? And even if a few do care, how would you get adoption? I expect everyone will just use whatever is already used most.
reply