I've spent 30 years seeing the junk many human developers deliver, so I've had 30 years to figure out how we build systems around teams to make broken output coalesce into something reliable.
A lot of people just don't realise how bad the output of the average developer is, nor how many teams successfully ship with developers below average.
To me, that's a large part of why I'm happy to use LLMs extensively. Some things need smart developers. A whole lot of things can be solved with ceremony and guardrails around developers who'd struggle to reliably solve fizzbuzz without help.
Did you also notice the evolution of average developers over time? I mean, if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
I assume that over time, the output improves because of the effort and time the developer invests in themselves. However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
Still, if you have 30 years of experience in the industry, you should be able to imagine what the real output might be.
> Did you also notice the evolution of average developers over time? I mean, if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
This makes little sense to me. Yes, individual developers gets better. I've seen little to no evidence that the average developer has gotten better.
> However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
It might reduce that effort to zero from the same people who have always invested the bare minimum of effort to hold down a job. Most of them don't advance today either, and most of them will deliver vastly better results if they lean heavily on LLMs. On the high end, what I see experienced developers do with LLMs involves a whole lot of learning, and will continue to involve a whole lot of learning for many years, just like with any other tool.
> However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
LLMs might help the new joiner produce code on the level of an average developer faster. But, at the same time, if LLMs are really trained on all open source repositories without any selection, that level might be limited.
It looks like the overwhelming majority of projects on Github, does not really follow stable growth tendencies. In all fairness, as these were the smaller projects, their developers might have never intended to demonstrate best practices, or make the project sustainable on the long-term.
This is all fine, experimentation and learning are very welcome in open source. But, with 83,9% of the projects (in my study) falling into this category, LLM might pick them up as demonstrating overwhelmingly popular best practices.
In the worst case, this might even lead to actual best practices being drowned out, over time.
> if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
really? it depends on the type of development, but ten years ago the coder profession had already long gone mainstream and massified, with a lot of people just attracted by a convenient career rather than vocation. mediocrity was already the baseline ("agile" mentality to at the very least cope with that mediocrity and turnover churn was already at its peak) and on the other extreme coder narcissism was already en vogue.
the tools, resources, environments have indoubtedly improved a lot, though at the cost of overhead, overcomplexity. higher abstraction levels help but promote detachment from the fundamentals.
so specific areas and high end teams have probably improved, but i'd say average code quality has actually diminished, and keeps doing so. if it weren't for qa, monitoring, auditing and mitigation processes it would by now be catastrophic. cue in agents and vibe coding ...
as an old school coder that nowadays only codes for fun i see llm tools as an incredibly interesting and game changing tool for the profane, but that a professional coder might cede control to an agent (as opposed to use it for prospection or menial work) makes me already cringe, and i'm unable to wrap my head around vibe coding.
You don't have to trust it. You can review its output. Sure, that takes more effort than vibe coding, but it can very often be significantly less effort than writing the code yourself.
Also consider that "writing code" is only one thing you can do with it. I use it to help me track down bugs, plan features, verify algorithms that I've written, etc.
Many of us are literally being forced to use it at work by people who haven't written a line of code in years (VPs, directors, etc) and decided to play around with it during a weekend and blew their minds.
I could say the same about every web app in the world... they fail every single day, in obvious, preventable ways. Don't look into the javascript console as you browse unless you want a horror show. Yet here we all are, using all these websites, depending on them in many cases for our livelihoods.
I don't trust it completely but I still use it. Trust but verify.
I've had some funny conversations -- Me:"Why did you choose to do X to solve the problem?" ... It:"Oh I should totally not have done that, I'll do Y instead".
But it's far from being so unreliable that it's not useful.
I find that if I ask an LLM to explain what its reasoning was, it comes up with some post-hoc justification that has nothing to do with what it was actually thinking. Most likely token predictor, etc etc.
As far as I understand, any reasoning tokens for previous answers are generally not kept in the context for follow-up questions, so the model can't even really introspect on its previous chain of thought.
I mostly find it useful for learning myself or for questioning a strange result. It usually works well for either of those. As you said, I'm probably not getting it's actual reasoning from any reasoning tokens but never thought that was happening anyway. It's just a way of interrogating the current situation in the current context.
It providing a different result is exactly because it's now looking at the existing solution and generating from there.
I guess I should have used ‘completely trust’ instead of ‘trust’ in my original comment. I was referring to the subset of developers who call themselves vibe coders.
I certainly wouldn't use a compiler that "screws up" 1% of the time; that's the perfect amount where it's extremely common where everything I use it for will have major issues but also so laborious to find amongst the 99% of correct output that I might as well not use it in the first place.
Which is ironically, the exact case those of us who don't find LLM-assisted coding "worth it" make.
LLMs screw up far more than 1% of the time. They screw up routinely, far more than a professionally trained human would, and in ways that would have said human declared mentally ill.
> enabling programmers around the world to be far more productive
I know a lot of us feel this way, but why isn't there more evidence of it than our feelings? Where's the explosion of FOSS projects and businesses? And why do studies keep coming out showing decreased productivity? Why aren't there oodles of studies showing increases of productivity?
I like kicking back and letting claude do my job but I've yet to see evidence of this increased productivity. Objectively speaking, "I" seem to be "writing" the same amount of code as I was before, just with less cognitive effort.
It's like everyone forgot that "lines of code" as a productivity metric was a running joke for a decade-plus. The real bottleneck in our work isn't producing boilerplate code, it's producing more or less the right kind of code for the problem at hand, and LLMs, having no real underlying ability to reason, are just not very good at it.
I haven’t done web development since 2002 except for some copy and paste work. My development is purely back end and AWS IAC. I have completely vibe coded three internal web admin sites that had about 10 pages of functionality and authentication with Amazon Cognito. I didn’t look at a line of code. I just told it what I wanted and the changes based on the UX I wanted
not questioning the cost of adopting new tech is so foolish it boggles my mind that so many nominally intelligent people just close their eyes and take a bite without wondering whether that's really fudge on their sundae or something fecal.
Pure ideology, as a certain sniffing slav would say
FTFY: “There’s this incredible new technology that allows evil megacorporations to get richer and control the world while destroying the beauty of the Web.”
I've spent 30 years seeing the junk many human developers deliver, so I've had 30 years to figure out how we build systems around teams to make broken output coalesce into something reliable.
A lot of people just don't realise how bad the output of the average developer is, nor how many teams successfully ship with developers below average.
To me, that's a large part of why I'm happy to use LLMs extensively. Some things need smart developers. A whole lot of things can be solved with ceremony and guardrails around developers who'd struggle to reliably solve fizzbuzz without help.
Did you also notice the evolution of average developers over time? I mean, if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
I assume that over time, the output improves because of the effort and time the developer invests in themselves. However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
Still, if you have 30 years of experience in the industry, you should be able to imagine what the real output might be.
> Did you also notice the evolution of average developers over time? I mean, if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
This makes little sense to me. Yes, individual developers gets better. I've seen little to no evidence that the average developer has gotten better.
> However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
It might reduce that effort to zero from the same people who have always invested the bare minimum of effort to hold down a job. Most of them don't advance today either, and most of them will deliver vastly better results if they lean heavily on LLMs. On the high end, what I see experienced developers do with LLMs involves a whole lot of learning, and will continue to involve a whole lot of learning for many years, just like with any other tool.
4 replies →
> However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLMs now.
LLMs might help the new joiner produce code on the level of an average developer faster. But, at the same time, if LLMs are really trained on all open source repositories without any selection, that level might be limited.
I have recently published a potentially related article: https://link.springer.com/article/10.1007/s44427-025-00019-y
It looks like the overwhelming majority of projects on Github, does not really follow stable growth tendencies. In all fairness, as these were the smaller projects, their developers might have never intended to demonstrate best practices, or make the project sustainable on the long-term.
This is all fine, experimentation and learning are very welcome in open source. But, with 83,9% of the projects (in my study) falling into this category, LLM might pick them up as demonstrating overwhelmingly popular best practices. In the worst case, this might even lead to actual best practices being drowned out, over time.
> if you take code from a developer ten years ago and compare it with their output now, you can see improvement.
really? it depends on the type of development, but ten years ago the coder profession had already long gone mainstream and massified, with a lot of people just attracted by a convenient career rather than vocation. mediocrity was already the baseline ("agile" mentality to at the very least cope with that mediocrity and turnover churn was already at its peak) and on the other extreme coder narcissism was already en vogue.
the tools, resources, environments have indoubtedly improved a lot, though at the cost of overhead, overcomplexity. higher abstraction levels help but promote detachment from the fundamentals.
so specific areas and high end teams have probably improved, but i'd say average code quality has actually diminished, and keeps doing so. if it weren't for qa, monitoring, auditing and mitigation processes it would by now be catastrophic. cue in agents and vibe coding ...
as an old school coder that nowadays only codes for fun i see llm tools as an incredibly interesting and game changing tool for the profane, but that a professional coder might cede control to an agent (as opposed to use it for prospection or menial work) makes me already cringe, and i'm unable to wrap my head around vibe coding.
I’m sorry.
You don't have to trust it. You can review its output. Sure, that takes more effort than vibe coding, but it can very often be significantly less effort than writing the code yourself.
Also consider that "writing code" is only one thing you can do with it. I use it to help me track down bugs, plan features, verify algorithms that I've written, etc.
And document!
Many of us are literally being forced to use it at work by people who haven't written a line of code in years (VPs, directors, etc) and decided to play around with it during a weekend and blew their minds.
LLMs are tool-shaped objects: https://minutes.substack.com/p/tool-shaped-objects
Without adequate real-world feedback, the simulation starts to feel real: https://alvinpane.com/essays/when-the-simulation-starts-to-f...
I could say the same about every web app in the world... they fail every single day, in obvious, preventable ways. Don't look into the javascript console as you browse unless you want a horror show. Yet here we all are, using all these websites, depending on them in many cases for our livelihoods.
I don't trust it completely but I still use it. Trust but verify.
I've had some funny conversations -- Me:"Why did you choose to do X to solve the problem?" ... It:"Oh I should totally not have done that, I'll do Y instead".
But it's far from being so unreliable that it's not useful.
I find that if I ask an LLM to explain what its reasoning was, it comes up with some post-hoc justification that has nothing to do with what it was actually thinking. Most likely token predictor, etc etc.
As far as I understand, any reasoning tokens for previous answers are generally not kept in the context for follow-up questions, so the model can't even really introspect on its previous chain of thought.
I mostly find it useful for learning myself or for questioning a strange result. It usually works well for either of those. As you said, I'm probably not getting it's actual reasoning from any reasoning tokens but never thought that was happening anyway. It's just a way of interrogating the current situation in the current context.
It providing a different result is exactly because it's now looking at the existing solution and generating from there.
It depends on the harness and/or inference engine whether they keep the reasoning of past messages.
Not to get all philosophical but maybe justification is post-hoc even for humans.
> Trust but verify.
I guess I should have used ‘completely trust’ instead of ‘trust’ in my original comment. I was referring to the subset of developers who call themselves vibe coders.
I think I like "blindly trust" better because vibe coders literally aren't looking.
Sure, but we’re trying to have curious conversation here, whereas this is the kind of dismissive, even curmudgeonly comment we're hoping to avoid.
https://news.ycombinator.com/newsguidelines.html
we worked with humans for decades and are used to 25x less reliability
[flagged]
I certainly wouldn't use a compiler that "screws up" 1% of the time; that's the perfect amount where it's extremely common where everything I use it for will have major issues but also so laborious to find amongst the 99% of correct output that I might as well not use it in the first place.
Which is ironically, the exact case those of us who don't find LLM-assisted coding "worth it" make.
How about a human coworker who screws up 1% of the time? Doesn’t sound so bad in that light. It’s the nature of being human.
Good code review is the solution but if it’s faster to do it yourself, that’s fine too.
You're not any better my friend. Name calling and straw man fallacies make a far worse point, if any, that that commenter made.
If they only screwed up 1% of the time, they'd be as good as the LinkedIn hype men want you to believe. They're far far worse then that in reality
Where's the evidence of the productivity, or does it just feel productive? https://minutes.substack.com/p/tool-shaped-objects
Please don't reply to a bad comment with another bad comment.
When disagreeing, please reply to the argument instead of calling names. "That is idiotic; 1 + 1 is 2, not 3" can be shortened to "1 + 1 is 2, not 3."
https://news.ycombinator.com/newsguidelines.html
LLMs screw up far more than 1% of the time. They screw up routinely, far more than a professionally trained human would, and in ways that would have said human declared mentally ill.
> enabling programmers around the world to be far more productive
I know a lot of us feel this way, but why isn't there more evidence of it than our feelings? Where's the explosion of FOSS projects and businesses? And why do studies keep coming out showing decreased productivity? Why aren't there oodles of studies showing increases of productivity?
I like kicking back and letting claude do my job but I've yet to see evidence of this increased productivity. Objectively speaking, "I" seem to be "writing" the same amount of code as I was before, just with less cognitive effort.
It's like everyone forgot that "lines of code" as a productivity metric was a running joke for a decade-plus. The real bottleneck in our work isn't producing boilerplate code, it's producing more or less the right kind of code for the problem at hand, and LLMs, having no real underlying ability to reason, are just not very good at it.
I haven’t done web development since 2002 except for some copy and paste work. My development is purely back end and AWS IAC. I have completely vibe coded three internal web admin sites that had about 10 pages of functionality and authentication with Amazon Cognito. I didn’t look at a line of code. I just told it what I wanted and the changes based on the UX I wanted
not questioning the cost of adopting new tech is so foolish it boggles my mind that so many nominally intelligent people just close their eyes and take a bite without wondering whether that's really fudge on their sundae or something fecal.
Pure ideology, as a certain sniffing slav would say
FTFY: “There’s this incredible new technology that allows evil megacorporations to get richer and control the world while destroying the beauty of the Web.”
OP isnt holding it right.
How would you trust autocomplete if it can get it wrong? A. you don't. Verify!