The headline is "Development statistics for the 7.2 kernel", and the last paragraph is highly LLM critical in contrast with the editorialized headline "Linux bugs fixed per release over time: >2× rise since 2026-04", which seems to imply some sort of Mythos bug finding.
From the last paragraph:
"The Linux kernel is aimed at production use, not research or experimentation. But there is currently a massive experiment being run on the kernel's development processes and community."
"This community has absorbed new processes and tools many times over its 35-year history, and will almost certainly find a way to do that this time as well. But that absorption has not always been without turbulence along the way."
While great in theory, the flip side is all the slop patches and PRs that both the kernel and open source in general now has to deal with, often with only agents as responders.
It honestly doesn't want to make me open anything for outside contributions anymore.
> Here's a new rule just for you: don't use compilers for any of your
kernel submissions.
> Because if you can't show that you really understand what the machine
is actually doing by writing your code in assembler, then I don't want
to see your code contribution. You clearly aren't competent if you
can't write it that way.
the question is about whether you understand in the slightest the output of the tool. does the determinism of the compiler somehow imbue you with a better understanding of the assembly it generates?
> You must have a very weak understanding on this topic
i work on the codegen for a C compiler i'm pretty sure my understanding is better than yours <shrug>
EDIT: and also you've clearly never read that article
> One of the key attributes of a low-level language is that programmers can easily understand how the language’s abstract machine maps to the underlying physical machine
so you did exactly imply "C is a low level language"
The idea that C is a smol language that can be completely understood by one person is one of those myths that need to be put to bed. C is riddled with complexities and footguns, especially but not exclusively around undefined behavior.
UB is basically impossible to avoid in practice--that is why the Linux kernel forced GCC to add a bunch of flags to "do what I mean", making UB defined in those cases.
> The idea that C is a smol language that can be completely understood by one person is one of those myths that need to be put to bed
You don’t need to understand the language completely. You only need to understand the general semantics and refer to the standard and docs to get the semantics down. That’s what they’re here for.
The point is, new technology arrived that allowed developers to do much more. Existing programmers hemmed and hawed about it because it threatened their egos, making easy what they once found very difficult. But the sensible engineers adopted the technology.
AI may not be deterministic, but on small to medium-sized tasks it produces more correct code, more reliably, faster than a human developer does. By any objective measure, not adopting it is professional irresponsibility.
> AI may not be deterministic, but on small to medium-sized tasks it produces more correct code, more reliably, faster than a human developer does. By any objective measure, not adopting it is professional irresponsibility.
How do you define correctness for any given task? If you know the correct logical process for any given process, writing it in code is just a matter of typing. The issue is that the human author, even when assisted by AI tools, does not know what is the correct algorithm for the task. In most cases, the output is probable code, not correct code.
I believe we are at a crossroads here. The key question is: Do we want (desire or require) humans to understand the implementation?
If the answer is no, then AI agents producing code faster and "more correct" (in some arguably questionable sense but let's fly with the assumption for a moment) should be embraced fully. Take the humans out of the loop, why review code, if there is a problem later then just ask the next AI agent to fix it. Similar to not looking at generated code by a compiler. Iterate fast, don't look back. Some code bases and some entire companies have adopted this view.
If the answer is yes then we need to keep the human in the loop, ensure they have enough understanding to maintain the thing, review all the code etc. AI is just another tool to produce the code which ultimately the human still owns. Many code bases follow this philosophy.
It seems to me that the discussion always ultimately falls on one of these two sides. They are incompatible but you need to pick one. Depending on which you pick, it is easy to predict how you argue in such discussions.
> The key question is: Do we want (desire or require) humans to understand the implementation?
Understanding the implementation is not the root cause here. The actual issue is that all software are built for a particular needs which is human related. In most software, the cost mostly decays to a constant value unless that need has changed or an external event has occurred.
Embracing AI fully is keeping the software in constant flux as it can’t guarantee it will actually follow the requirements and the platform specs. Any prompt has a non zero chance to introduce regressions and breaking changes, disrupting the workflow of the users.
The tools to write the code does not matter to the user just like the hammer does not matter to the person that needs a home. But if your tools results in a badly constructed house that always needs repair and what not, expect complaints.
> Embracing AI fully is keeping the software in constant flux as it can’t guarantee it will actually follow the requirements and the platform specs. Any prompt has a non zero chance to introduce regressions and breaking changes, disrupting the workflow of the users.
You can pin down existing expected behavior pretty well with automated test cases and even bringing formal verification into the mix. Using LLMs to create those, it's not even a major cost factor. Then you are safe from such regressions. Just like when humans make changes. So, I don't see how this is introducing a difference.
> The tools to write the code does not matter to the user just like the hammer does not matter to the person that needs a home. But if your tools results in a badly constructed house that always needs repair and what not, expect complaints.
Indeed. Though I don't see the connection to my point.
Nice rhetorical sleight of hand, trying to paint your opponents as ego-driven and senseless. But LLMs are not compilers. They cannot be relied upon to work correctly, and indeed can be relied upon to introduce bugs that a human would never introduce. The situation is different, therefore the reactions are different.
> AI may not be deterministic, but on small to medium-sized tasks it produces more correct code, more reliably, faster than a human developer does.
Presumably the person who's full-time job is staying on top of proposed changes to the linux source tree knows something about this; what are your credentials on the topic?
As an example, I’m in the process of putting up a patch series to optimize some specific filesystem operations. The amount of boilerplate that has to know to get done is completely unapproachable to an outsider both from the amount of time needed to learn that boilerplate and form it in such a way that maintainers will be happy. Even though I know exactly how the code is working, it bridges that understanding gap but I don’t see how it correlates with incompetence. I may be an outlier but I suspect there’s a huge amount of people who are extremely capable and competent and it’s just that the Linux kernel has so many processes that it’s difficult to onboard into the community without LLM assistance.
The Linux kernel project is not hurting for contributors nor was it prior to LLMs. The processes you describe as roadblocks don’t seem to have been preventing the Linux kernel from getting code contributions. Maybe they don’t need or want more easy onboarding or broader audience?
> The kind of expectations I have is that people do their best and I expect people to understand what they are doing.
> But that understanding has very little to do with what tools they use.
> And quite honestly, in my experience, the people I respect and call intelligent are not the ones that shy away from using new and interesting tools.
He’s saying that understanding or competence are more about the person than their AI use. I think that’s a reasonable argument, even though I disagree on the basis that it’s at least a little correlated in the shortcuts in understanding the many devs I’ve seen (not all, but a nontrivial amount) seem to be taking.
To be clear: I believe that it's entirely possible to use LLMs to amplify understanding and competence, but that in practice LLM usage is anticorrelated with understanding and competence. This is about empirical reality, not logical entailment.
Linus himself is actually comically incompetent. He only became famous after the Linux kernel took off... decades ago? Since Git, he has made ZERO code contributions whatsoever (not even to the Linux kernel). He doesn't even review code and has his team of capos do it for him. All in all he's no different than the CEO of some tech company, his thoughts on LLMs are no longer relevant (for more lack of credibility, see his stance on Rust, C++, Go)
He used Claude Code to write one of his patches in [0] and introduced a data race bug in the kernel unbeknownst to himself but this bug was caught by other reviewer [1] before it made it into a new kernel release.
So I'm afraid Linus himself did not understand the changes Claude made to the code he submitted in the mailing list, despite his "principles" in telling others previously that AI was creating slop patches and then now shouting at others who were concerned about using LLMs on code where they do not understand the generated code themselves when it all applied to....himself.
The data race is exactly the kind of subtle bug that even very experienced programmers would make in this circumstance.
The patches that Linus posted are relatively small and self contained and from reading the thread it seems came from a series of in depth conversations with Claude and were carefully reviewed by Linus.
So what we're seeing here is a tricky concurrency bug that even an expert would make. You can't use it as an example of slop
To the surprise of no one. Although, I must recognise that I did not envision a future where Linus embraced AI as frictionless has its been, then again after the inclusion of Rust in the kernel, I probably would've risked some money on it.
Yes, Linus is quite forward thinking, and we can credit that with why Linux has stayed relevant for so many decades. Not many software projects manage to pull that off.
I’m strongly with you on that. Current models aren’t perfect, but neither am I. In a lot of my daily use, they’re as good as or better than I am at certain tasks.
I hear people around me talking about a bad experience they had with ChatGPT last summer as though it proves all AI coding is “slop”. Honestly, it makes me sad for them. There are reasons to dislike AI, but so many detractors skip right past those to anecdata that just aren’t relevant anymore, if they ever were.
Current models are still worse than I am, or any competent developer I've ever worked with. You act as though people tried ChatGPT in 2023 and gave up forever, but that isn't what is happening here. The cold hard truth is that, contrary to what AI boosters claim, LLMs still suck at programming and output slop.
Or, he has a full understanding that, like everything single thing he's ever been involved with in his career, it's a new tech under development and will, as every measure up to now has demonstrated, improve over time. And, as all tech that has ever existed since the beginning of man starts, has somewhat initially limited, but still very practical and real, use in its current state.
Again, he's pragmatic, and has seen countless types and iterations of tech come into existence. The people expecting perfection from the start have no actual experience with the creative process, engineering or design, and and only want progress to stop (because there is, literally, without exception ever existing, no alternative to iteration).
Linus has always been pragmatic as opposed to dogmatic.
20 years ago he was fine using BitKeeper, proprietary software, for kernel source control, because it was better than Subversion and CVS. He only created git when BitKeeper introduced some road blocks.
Submitted title was "Linux bugs fixed per release over time: >2× rise since 2026-04". We've reverted it now.
Submitters: If you want to say what you think is important about an article, that's fine, but do it by adding a comment to the thread. Then your view will be on a level playing field with everyone else's: https://hn.algolia.com/?dateRange=all&page=0&prefix=false&so...
The agent helps a lot to fix bugs. Just point the agents at the bug reports. They do the reproduction, debugging and fixes. We "just" have to review. (Sometimes ask more details and tell we'd prefer another approach.) This makes bug fixing much faster and automated.
And at the same time, it seems we get less bug reports to our library.
I think user just use their agents to code, and agents don't report bugs, they just work it around somehow.
So overall, the open bug count is decreasing. Which somehow feels good.
On the other hand, we get a lot of PR made by other's people agents, which can be a bit overwhelming when it's just a huge code drop. We can't easily review that.
also the agent might introduce bugs, just like a human (see rsync which now has very busy development). Likely we (and the LLM) just won't notice them as easily. Fun times I guess.
> > and agents don't report bugs, they just work it around somehow.
Yeah I've definitely noticed this. On a project I'm working on Opus 5.5 found a bug in Smithay and another in Winit. It did tell me about them but its preferred solution was just to work around them locally. To be fair we don't really want agents going off and reporting bugs automatically...
I don't run any big open source projects but I think my preferred solution to AI PRs would be to get my AI to implement the same thing, and give then afterwards tell it to look at the PR for anything it missed. Then I at least know that I'm using a competent model and it reduces the danger of just blindly accepting someone else's code. (And obviously review the code if you have time and care, but that isn't always the case.)
Yes the default behavior of working around the bug is good, that’s what everyone was doing anyway pre-LLMs. The good practice is to report the bug. Simply add instructions to your agents to report you the bugs it found in the summary, so you can check the bug and report it correctly upstream.
>I think user just use their agents to code, and agents don't report bugs, they just work it around somehow.
Claude comes up with some truly delicious insane workarounds these days. Like launching something in a subprocess and capturing stdout/stderr and doing string parsing on info logs because of a desire for some hook not exposed by API (or at least that it didn't find on its quick scan).
There's probably no such thing as semver reliability for dependencies anymore in stuff that agents glue together, since they will poke at ANY sort of way of getting additional insight or control if they want it.
The major issue with these kinds of blurbs is that there's no control.
Historical numbers are not valid because incentivizes of a well funded entity have changed. It would require an equally well funded push to up the patch numbers without LLMs to really measure the impact in a quantifiable way.
Not quite. My C++ Linux rewrite is already production ready, meaning in theory I no longer need to rely on the Linux kernel devs. This will, in a matter of months I presume, become the norm.
They are also now vibe coding the kernel which is a major issue. Race conditions were already found in one of the slop suggestions. Linus is apparently fine with this degradation in quality.
Who’s vibecoding the kernel? I’ve heard stories of devs using AI to help write code, but don’t recall a single story of an experienced kernel dev vibecoding anything.
So it seems worth vibecoding a survival analysis for bugs introduced. But not quite a survival analysis because we don't even know the bugs exist until the event of their discovery.... Is there a publicly available dataset for this, with a URL?
Heads up for those upgrading to 7.3, I just downgraded my slackware box from 7.3-rc7 to 7.2.10 because /dev/input/events was missing. Keyboard and mouse only worked in the console as a result.
05kqhg | 4 hours ago
From the last paragraph:
"The Linux kernel is aimed at production use, not research or experimentation. But there is currently a massive experiment being run on the kernel's development processes and community."
mh- | 4 hours ago
"This community has absorbed new processes and tools many times over its 35-year history, and will almost certainly find a way to do that this time as well. But that absorption has not always been without turbulence along the way."
seb1204 | an hour ago
Matl | 4 hours ago
It honestly doesn't want to make me open anything for outside contributions anymore.
mathisfun123 | 4 hours ago
https://lore.kernel.org/lkml/CAHk-=whTs09_ozN+e09GU68N1wPP56...
senderista | 4 hours ago
mathisfun123 | 4 hours ago
> Here's a new rule just for you: don't use compilers for any of your kernel submissions.
> Because if you can't show that you really understand what the machine is actually doing by writing your code in assembler, then I don't want to see your code contribution. You clearly aren't competent if you can't write it that way.
Matl | 4 hours ago
mathisfun123 | 4 hours ago
sedan_baklazhan | 3 hours ago
mathisfun123 | 3 hours ago
sedan_baklazhan | 3 hours ago
mathisfun123 | 3 hours ago
i work on the codegen for a C compiler i'm pretty sure my understanding is better than yours <shrug>
EDIT: and also you've clearly never read that article
> One of the key attributes of a low-level language is that programmers can easily understand how the language’s abstract machine maps to the underlying physical machine
so you did exactly imply "C is a low level language"
bitwize | 3 hours ago
The idea that C is a smol language that can be completely understood by one person is one of those myths that need to be put to bed. C is riddled with complexities and footguns, especially but not exclusively around undefined behavior.
sedan_baklazhan | 3 hours ago
senderista | an hour ago
skydhash | 2 hours ago
You don’t need to understand the language completely. You only need to understand the general semantics and refer to the standard and docs to get the semantics down. That’s what they’re here for.
bitwize | 3 hours ago
The point is, new technology arrived that allowed developers to do much more. Existing programmers hemmed and hawed about it because it threatened their egos, making easy what they once found very difficult. But the sensible engineers adopted the technology.
AI may not be deterministic, but on small to medium-sized tasks it produces more correct code, more reliably, faster than a human developer does. By any objective measure, not adopting it is professional irresponsibility.
skydhash | 3 hours ago
How do you define correctness for any given task? If you know the correct logical process for any given process, writing it in code is just a matter of typing. The issue is that the human author, even when assisted by AI tools, does not know what is the correct algorithm for the task. In most cases, the output is probable code, not correct code.
teiferer | 2 hours ago
If the answer is no, then AI agents producing code faster and "more correct" (in some arguably questionable sense but let's fly with the assumption for a moment) should be embraced fully. Take the humans out of the loop, why review code, if there is a problem later then just ask the next AI agent to fix it. Similar to not looking at generated code by a compiler. Iterate fast, don't look back. Some code bases and some entire companies have adopted this view.
If the answer is yes then we need to keep the human in the loop, ensure they have enough understanding to maintain the thing, review all the code etc. AI is just another tool to produce the code which ultimately the human still owns. Many code bases follow this philosophy.
It seems to me that the discussion always ultimately falls on one of these two sides. They are incompatible but you need to pick one. Depending on which you pick, it is easy to predict how you argue in such discussions.
skydhash | 2 hours ago
Understanding the implementation is not the root cause here. The actual issue is that all software are built for a particular needs which is human related. In most software, the cost mostly decays to a constant value unless that need has changed or an external event has occurred.
Embracing AI fully is keeping the software in constant flux as it can’t guarantee it will actually follow the requirements and the platform specs. Any prompt has a non zero chance to introduce regressions and breaking changes, disrupting the workflow of the users.
The tools to write the code does not matter to the user just like the hammer does not matter to the person that needs a home. But if your tools results in a badly constructed house that always needs repair and what not, expect complaints.
teiferer | 26 minutes ago
You can pin down existing expected behavior pretty well with automated test cases and even bringing formal verification into the mix. Using LLMs to create those, it's not even a major cost factor. Then you are safe from such regressions. Just like when humans make changes. So, I don't see how this is introducing a difference.
> The tools to write the code does not matter to the user just like the hammer does not matter to the person that needs a home. But if your tools results in a badly constructed house that always needs repair and what not, expect complaints.
Indeed. Though I don't see the connection to my point.
bigstrat2003 | 2 hours ago
> AI may not be deterministic, but on small to medium-sized tasks it produces more correct code, more reliably, faster than a human developer does.
That is not remotely true.
cwillu | 4 hours ago
vlovich123 | 4 hours ago
MobiusHorizons | 3 hours ago
munchbunny | 4 hours ago
> The kind of expectations I have is that people do their best and I expect people to understand what they are doing.
> But that understanding has very little to do with what tools they use.
> And quite honestly, in my experience, the people I respect and call intelligent are not the ones that shy away from using new and interesting tools.
He’s saying that understanding or competence are more about the person than their AI use. I think that’s a reasonable argument, even though I disagree on the basis that it’s at least a little correlated in the shortcuts in understanding the many devs I’ve seen (not all, but a nontrivial amount) seem to be taking.
senderista | 3 hours ago
skydhash | 3 hours ago
rfgplk | 2 hours ago
nullpoint420 | 2 hours ago
Projects like the Linux kernel do not pop up out of thin air. They need a leader.
rvz | 3 hours ago
He used Claude Code to write one of his patches in [0] and introduced a data race bug in the kernel unbeknownst to himself but this bug was caught by other reviewer [1] before it made it into a new kernel release.
So I'm afraid Linus himself did not understand the changes Claude made to the code he submitted in the mailing list, despite his "principles" in telling others previously that AI was creating slop patches and then now shouting at others who were concerned about using LLMs on code where they do not understand the generated code themselves when it all applied to....himself.
[0] https://lkml.iu.edu/2610.1/13146.html
[1] https://lkml.iu.edu/2610.1/13573.html
ceejayoz | 2 hours ago
biorach | 2 hours ago
The patches that Linus posted are relatively small and self contained and from reading the thread it seems came from a series of in depth conversations with Claude and were carefully reviewed by Linus.
So what we're seeing here is a tricky concurrency bug that even an expert would make. You can't use it as an example of slop
dist-epoch | 3 hours ago
Linus wants the bugs fixed.
pelagicAustral | 4 hours ago
nvme0n1p1 | 4 hours ago
nomel | 4 hours ago
Why? He seems very pragmatic. I fully expected him to embrace it, with the only concern being correctness and quality.
pelagicAustral | 4 hours ago
bitwize | 3 hours ago
The ones complaining about "slop" are the ones going on vibes now.
kstrauser | 3 hours ago
I hear people around me talking about a bad experience they had with ChatGPT last summer as though it proves all AI coding is “slop”. Honestly, it makes me sad for them. There are reasons to dislike AI, but so many detractors skip right past those to anecdata that just aren’t relevant anymore, if they ever were.
bigstrat2003 | 2 hours ago
kstrauser | 2 hours ago
biorach | 2 hours ago
pelagicAustral | an hour ago
nomel | 2 hours ago
pelagicAustral | an hour ago
mycall | 4 hours ago
teekert | 3 hours ago
mrheosuper | 3 hours ago
dist-epoch | 3 hours ago
bigstrat2003 | 2 hours ago
nomel | an hour ago
Again, he's pragmatic, and has seen countless types and iterations of tech come into existence. The people expecting perfection from the start have no actual experience with the creative process, engineering or design, and and only want progress to stop (because there is, literally, without exception ever existing, no alternative to iteration).
dist-epoch | 3 hours ago
20 years ago he was fine using BitKeeper, proprietary software, for kernel source control, because it was better than Subversion and CVS. He only created git when BitKeeper introduced some road blocks.
cwillu | 4 hours ago
(Edit: title has been fixed)
dang | 4 hours ago
Submitters: If you want to say what you think is important about an article, that's fine, but do it by adding a comment to the thread. Then your view will be on a level playing field with everyone else's: https://hn.algolia.com/?dateRange=all&page=0&prefix=false&so...
lurk2 | 4 hours ago
tomwojcik | 3 hours ago
steelframe | 3 hours ago
dang | 2 hours ago
ogoffart | 4 hours ago
The agent helps a lot to fix bugs. Just point the agents at the bug reports. They do the reproduction, debugging and fixes. We "just" have to review. (Sometimes ask more details and tell we'd prefer another approach.) This makes bug fixing much faster and automated.
And at the same time, it seems we get less bug reports to our library. I think user just use their agents to code, and agents don't report bugs, they just work it around somehow.
So overall, the open bug count is decreasing. Which somehow feels good.
On the other hand, we get a lot of PR made by other's people agents, which can be a bit overwhelming when it's just a huge code drop. We can't easily review that.
fock | 3 hours ago
throw73847939 | 3 hours ago
Rsync is hopelessly underfunded under staffed. Current developer was forced to takeover, because everyone quit!
timhh | 3 hours ago
Yeah I've definitely noticed this. On a project I'm working on Opus 5.5 found a bug in Smithay and another in Winit. It did tell me about them but its preferred solution was just to work around them locally. To be fair we don't really want agents going off and reporting bugs automatically...
I don't run any big open source projects but I think my preferred solution to AI PRs would be to get my AI to implement the same thing, and give then afterwards tell it to look at the PR for anything it missed. Then I at least know that I'm using a competent model and it reduces the danger of just blindly accepting someone else's code. (And obviously review the code if you have time and care, but that isn't always the case.)
cocoto | 2 hours ago
0x696C6961 | an hour ago
veqq | an hour ago
It's quite a pity, preventing us from improving our model of the domain, from Naurian theory building and presenting a perfected API etc.
majormajor | 44 minutes ago
Claude comes up with some truly delicious insane workarounds these days. Like launching something in a subprocess and capturing stdout/stderr and doing string parsing on info logs because of a desire for some hook not exposed by API (or at least that it didn't find on its quick scan).
There's probably no such thing as semver reliability for dependencies anymore in stuff that agents glue together, since they will poke at ANY sort of way of getting additional insight or control if they want it.
jayd16 | 4 hours ago
Historical numbers are not valid because incentivizes of a well funded entity have changed. It would require an equally well funded push to up the patch numbers without LLMs to really measure the impact in a quantifiable way.
zdw | 4 hours ago
Which covers how he responds and pushes back on much of this, as well as asking for a patch (not just bug reports)
rfgplk | 2 hours ago
He's "pushing back on this" because he's being obsoleted in real time.
MarceColl | 2 hours ago
rfgplk | 2 hours ago
fooblaster | 2 hours ago
IncreasePosts | 2 hours ago
nullpoint420 | an hour ago
HackerThemAll | 38 minutes ago
oytis | 2 hours ago
nullpoint420 | 2 hours ago
amluto | an hour ago
lousken | 4 hours ago
atlantic 0000:0f:00.0: PM: failed to resume async: error -12
AI fix this, thanks
viraptor | 3 hours ago
lousken | 3 hours ago
VCFundedGenYer | 3 hours ago
New leadership is needed over there.
ttul | 3 hours ago
AspireOne | 3 hours ago
kstrauser | 3 hours ago
seb1204 | an hour ago
dash2 | 3 hours ago
tosti | 3 hours ago
YMMV
AmazingEveryDay | 2 hours ago