OOT: some LLM-generated humor over a patch description - Was: Re: [PATCH v3 4/4] scripts/kernel-doc: some fixes to kernel-doc comments

[Mauro Carvalho Chehab <mchehab+huawei@kernel.org>]

Em Tue, 13 Jan 2026 23:10:36 +0100
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> escreveu:

> Em Tue, 13 Jan 2026 22:49:43 +0100
> Mauro Carvalho Chehab <mchehab+huawei@kernel.org> escreveu:
> 
> > Em Tue, 13 Jan 2026 13:55:18 -0700
> > Jonathan Corbet <corbet@lwn.net> escreveu:
> > 
> > > Mauro Carvalho Chehab <mchehab+huawei@kernel.org> writes:
> > >   
> 
> > > "flowers"?  Did the LLM put that out too? :)  
> 
> Heh, asking it to be funny and use figures of speech gave a funny
> yet precise description:

Heh, apparently I had nothing to do this night and decided to
see how LLM can play converting a patch description to something
different.

Feel free to Ignore this e-mail except if you're curious enough to see 
what can be produced on my local GPU.


---

Original patch description:

<description>
There are some typos and English errors at the kernel-doc.py comments.

Locate them with the help of LLM (gpt-oss 14B), locally excecuted
with this prompt:

    review English grammar andsyntax at the comments on the code
    below:
    <cat scripts/kernel-doc.py>

Not all results are flowers, although it caught several minor
issues there. Add the pertinent fixes, discarding the bad ones.
</description>

I asked gpt-oss to modify them to different styles, after those
initial prompts:

prompt 1: rewrite the text abusing with Figures of speech and being funny
prompt 2: write just the original text converted with metaphors. Place in a code block

(I placed already the results for it)

Then, I submitted some other prompts, asking to modify it to
several different styles:

1) The Fresh Prince of Bell-air
-------------------------------

Prompt: modify it to use “the fresh prince of bell-air” humor:

<llm>
	Yo, what's up? Look, there are some miss‑spelled words and grammar ghouls hiding in the kernel‑doc.py comments. 
	It's like my dad's closet—full of half‑forgotten stuff. 
	So let's roll up a fresh 14‑billion‑parameter LLM (think of it as the Fresh Prince's ride) and run it locally. 
	Tell it, “Check my grammar and syntax in the comments below, just like I check my reflection in the mirror.”

	    review English grammar and syntax at the comments on the code below:
	    <cat scripts/kernel-doc.py>

	The LLM didn't just spit out a rose‑filled bouquet; it found a few wilted flowers—some minor issues, no biggie. 
	Grab the good ones, toss the bad ones out, and keep the code as clean as a fresh pair of Jordans on the block. 
</llm>

2) Shakespearean style (LLM suggestion)
---------------------------------------

prompt: Could you rewrite the same message in a Shakespearean style instead of Fresh Prince?

<llm>
Hark! There be misspelt words and errant syntax lurking within the comments of kernel‑doc.py,
as if ghosts in a moonlit chamber.  
Summon then a mighty LLM (gpt‑oss 14B), as if a wizard of old, and run it anon upon the local realm,
with this solemn utterance:

    review English grammar and syntax at the comments on the code below:
    <cat scripts/kernel-doc.py>

The oracle returned no perfumed roses; it uncovered but a few wilted blooms—mere minor faults, indeed.
Gather the sweet ones, cast aside the withered, and let thy code shine as a polished shield beneath the sun.  
</llm>

3) for the the dress like a pirate day (LLM suggestion)
-------------------------------------------------------

prompt: Could you rewrite the message in a pirate‑literate style?

<llm>
Arrr, me hearties!  
Yar, there be misspelt words and bally syntax buried in the kernel‑doc.py comments – like doubloons in a sun‑baked chest.  
Summon ye a mighty LLM (gpt‑oss 14B), as stout as a kraken, and run it locally upon yer rigging with this command:  

    review English grammar and syntax at the comments on the code below:
    <cat scripts/kernel-doc.py>

The beast returned no fragrant roses, but spied a few wilted blooms – minor squalls, aye.  
Collect the gold, toss the rotten, and let yer code sail smooth as a polished hull.  
</llm>

4) noir detective (LLM suggestion)
----------------------------------

prompt: Can you rewrite the message in a noir detective style?

<llm>
I was staring at the back‑lit screen of kernel‑doc.py, the comments crawling like neon‑glowing alley cats.  
Something was off – misspelt words, syntax that smelled of bad coffee.  
I knew the only way to clean up the mess was to bring in the big guns.  

So I pulled out the LLM (gpt‑oss 14B), a private eye with a 14‑billion‑parameter brain, and set it to work right there in my office.  
With a cigarette in one hand and a keyboard in the other, I told the machine:  

    review English grammar and syntax at the comments on the code below:
    <cat scripts/kernel-doc.py>

The LLM didn't give me a bouquet of roses – it found a handful of wilted blooms, minor issues that could have turned the whole case sour.  
I snatched up the good ones, tossed the bad into the trash, and let the code breathe again, clean and sharp as a well‑sharpened revolver in a rain‑slick night.  
</llm>

5) Buffy the Vampire Slayer
---------------------------

by purpose, I used the wrong name on this TV series

prompt 1: what if it was part of buffy the vampire hunter script?
prompt 2: convert it into a description that buffy is doing to Angel about a past hunt


<llm>
**Buffy’s Tale of the “Kernel‑Doc” Hunt**

When Buffy approached Angel one night, her eyes still glittered with the after‑glow of a successful hunt. She leaned in, elbows on the battered wooden desk, and began to recount the latest battle—a hunt that, oddly enough, had started with a line of code rather than a silver stake.

“First thing I noticed,” she said, tapping her fingers against the monitor, “was that the victim’s lair—well, *kernel‑doc.py*—was littered with typo‑tombs and syntax‑slugs.” She paused, watching Angel’s skeptical gaze. “I mean, who writes code like that when they’re about to unleash a demon?”

Angel shifted, his winged silhouette casting a long shadow across the wall. “Did you just… fight a ghost in a file?”

Buffy smiled, a flash of mischievous humor in her voice. “Not a ghost, but a *vampire of the void*—the sort of entity that lingers in the shadows of poorly written scripts. I pulled out my trusty LLM, *gpt‑oss‑14B*, a 14‑billion‑parameter AI with a taste for order. I ran it locally, fed it the code with a simple prompt: “review English grammar and syntax at the comments on the code below,” and waited.”

She described how the AI combed through the comments like a detective sifting through evidence. “It wasn’t a bouquet of roses,” she laughed, “but it did flag a handful of minor glitches—those little syntax errors that could have turned a tidy codebase into a chaotic battlefield.”

Angel nodded, eyes widening as the picture painted itself. “So you used a language model to debug the demon’s lair?”

“Exactly,” Buffy confirmed. “I cherry‑picked the clean fixes, threw the corrupted ones out, and the code—our last line of defense—was restored to pristine condition. The demon didn’t stand a chance against an algorithmically flawless script.”

She paused, looking at Angel, her tone turning reflective. “That night, I realized that sometimes the real monsters we fight are the invisible ones in our systems. And with the right tools—human ingenuity and machine precision—you can patch up the weak spots before they’re exploited.”

Angel, ever the philosophical one, smiled. “So in the end, you saved the day by cleaning up a file instead of a coffin?”

Buffy grinned. “That’s one way to put it.”
</llm>

Thanks,
Mauro