Re: [PATCH v2 0/8] mm/page_owner: Add PID/TGID/COMM and cgroup filtering
From: zhen.ni
Date: Tue Sep 08 2026 - 07:44:12 EST
在 2026/9/8 17:13, Lorenzo Stoakes (ARM) 写道:
On Tue, Sep 08, 2026 at 03:04:02PM +0800, Weijie Yuan wrote:
On Tue, Sep 08, 2026 at 02:40:10PM +0800, zhen.ni wrote:
在 2026/9/8 14:24, Weijie Yuan 写道:
From an outsider..I really can't distinguish the LLM flavor that clearly in English.
On Tue, Sep 08, 2026 at 10:41:23AM +0800, zhen.ni wrote:
Sorry but your whole reply reads like a LLM slop. It took a lot of
mental effor to actually try and engage with it.
This reply was written by me, and its viewpoints are not simply copied
directly from an LLM. The LLM only assists with the wording.
So that's probably the reason. Your previous replies was indeed very
much like the output of an LLM. Even if the idea is your own, after
being "polished" by LLM, it's hard to read. I know English is not our
first language, and it's not that easy to speak like a native speaker.
But may I ask you did you read it before sending them out? I really
found this bunch of overly formal content a little painful to read.
So I suspect the LLM may have taken too much liberty in polishing your
text, to the point that your replies no longer read like something a
person would naturally write.
The "Summary and Plan" in your reply in v1, both in its formatting and
wording, looks quite similar to LLM-generated text to me. So I can
understand why Lorenzo asked whether you had used an LLM. Come on, we
all know what LLM writing looks like.
That said, I do not know exactly how you used the LLM on your original
text, so please forgive me if I have this wrong.
Thanks.
Yes, sometimes I can not as well. But I guess the native ones can.
So.. ;-)
I'm sorry for causing some trouble.
That's fine. No need to say sorry.
I know and understand that we non-native speakers would rather not make
mistakes over these little language detail issues. But over-polishing
can end up having the opposite effect. Keeping some of your natural
writing style may actually be what the community prefers, especially
these AI days.
My normal reply process is to first describe my ideas, then have the
LLM check for logic and grammar issues, and do a round of polishing. I
check the final draft once more to see if it has deviated from my
ideas, and make corresponding revisions.
Sigh, so it is hard to know where to draw the line. Write more and learn
more about "human-like" writing, perhaps. :)
Thanks!
Thanks Weijie appreciate your input :) and it's good to get a perspective from a
non-native speaker on this!
Generally I empathise with LLM usage for helping non-native speakers with
English, that's a great use of it, so I don't object to it _in general_ BUT as
Weijie points out there's better ways of using and worse ways of using it.
You have to ensure that your meaning is transmitted properly without it
ultimately becoming essentially a conversation between a reviewer and an LLM.
So the technial discussion you are engaging in MUST be your own.
As for the 'summary' emails - please don't send them at all.
I feel like often they're used to generate a new prompt for the LLM and it
really ends up being 'workslopping', that is, making reviewers do more work
while the LLM takes care of things for you.
And that crosses the line really from 'aid to English' into it being a problem.
Instead, ENGAGE IN CONVERSATION with the reviewer, in line.
So if a review says:
"Please make this function do X, Y, Z".
Don't put something in a summary email or anything like that. REPLY to them,
quoting the request and respond. Like:
> Please make this function do X, Y, Z.
OK makes sense about X, Y is a bit tricker because of ... and Z is
impossible because ....
For instance.
That way it is human-to-human interaction at all times, with maybe the LLM
helping with translation along the way.
Noted with thanks.
As for the review - Vlastimil has raised legitimate technical points so I would
engage with those directly.
It's very reasonable for him to conclude an LLM was used for more than
translation, certainly the rather ludicrious 'document the world in the commit
message' approach looks inhuman.
I'm not sure which patch you are referring to, as its commit message
appears to be unusually long (seemingly stuffed with massive LLM-
generated information).
For my 8 patches, the commit messages are not generated by an LLM, and
they are written very concisely.
If you are referring to the cover letter being long, I would like to
briefly explain. The cover letter itself isn't that long; the extra
length comes from the test programs and test results I attached. I felt
it was necessary to let the reviewers know exactly what tests I
performed and how effective they were, so as to ease the review burden.
However, since this information cannot be placed within the individual
patches, I had to put it in the cover letter for now. Please note that
this content will not be included in the final commit messages later on.
So engage on the technical points without summary emails, and please put
documentation in a documentation file :)
Also I think it's reasonable now for you to use an:
Assisted-by: LLM
Tag on this series.
I resorted to an LLM only to structure the language in my reply email —
purely for efficiency, to help expedite the review process. For the
patch series itself, however, I had ample time to prepare, and both the
code and the documentation were written without any LLM involvement.
Therefore, I believe the Tag in question is not really suitable here.
Thanks,
Zhen