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.
>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.
> > 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.
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.
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."
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.
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.
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?
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...
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.
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.
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.
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.
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.
I have noticed the same on my project.
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.
>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.
> > 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.
1 reply →
> I think user just use their agents to code, and agents don't report bugs, they just work it around somehow.
It's quite a pity, preventing us from improving our model of the domain, from Naurian theory building and presenting a perfected API etc.
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? People also introduce bugs. If you are too lazy to setup verification harness, you will be even more lazy to do all testing manually.
Rsync is hopelessly underfunded under staffed. Current developer was forced to takeover, because everyone quit!
Greg KH did a video on the flood of LLM created stuff: https://news.ycombinator.com/item?id=49929391
Which covers how he responds and pushes back on much of this, as well as asking for a patch (not just bug reports)
> pushes back on much of this
He's "pushing back on this" because he's being obsoleted in real time.
Oh, you dont have to worry. You'll be obsoleted waaay before him.
8 replies →
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."
The following sentence:
"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."
Elaborated in here https://news.ycombinator.com/item?id=50133642
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.
Just how massive can the machine-generated amdgpu header files get, it may be time to set some limits.
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.
YMMV
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?
Please don't editorialize titles.
(Edit: title has been fixed)
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...
I got shadow banned. How do I delete my account?
3 replies →
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.
do you want the bugs in your project fixed, no matter the source, or do you want only humans to contribute.
Linus wants the bugs fixed.
greatly exaggerated as indicated by linus' own feelings
https://lore.kernel.org/lkml/CAHk-=whTs09_ozN+e09GU68N1wPP56...
Clearly, Linus is all over the place here.
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
2 replies →
Linus's claim that use of LLM tools is uncorrelated with understanding or competence is ludicrous.
25 replies →
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.
> where Linus embraced AI as frictionless has its been
Why? He seems very pragmatic. I fully expected him to embrace it, with the only concern being correctness and quality.
True, but I think there are quite a few very pragmatic people in here, and yet you see the they don't exactly go around singing praises.
8 replies →
Also, it took a long time for rust to mature to be considered for linux kernel development. AI is faster but easier to integrate.
As someone who hates c++ so much, he is surprisingly nice to llm.
1 reply →
That's exactly why one would expect him to not embrace it. LLM usage is anti-correlated with either of those things.
1 reply →
100%. Too many people equate LLM assisted programming with vibe coding some slop. Which is just a weird thing to do at this point.
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.
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.
[dead]
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.
New leadership is needed over there.
https://news.ycombinator.com/item?id=50134666
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.
I suppose, feel free to fork the kernel and take the lead?
Come on.
[flagged]
atlantic 0000:0f:00.0: PM: dpm_run_callback(): pci_pm_resume.llvm.11545057702175119861 returns -12
atlantic 0000:0f:00.0: PM: failed to resume async: error -12
AI fix this, thanks
You can literally do that now. Exactly as you wrote it...
Not good enough, I am testing if some agent is checking hackernews and will fix it for me