From: Roman Gushchin <roman.gushchin@linux.dev>
To: Alan Stern <stern@rowland.harvard.edu>
Cc: sashiko-reviews@lists.linux.dev,
Hongyu Xie <xiehongyu1@kylinos.cn>,
linux-usb@vger.kernel.org, sashiko@lists.linux.dev
Subject: Re: What happened with Sashiko?
Date: Thu, 22 Oct 2026 23:07:44 +0000 [thread overview]
Message-ID: <7ia4mrs52v27.fsf@castle.c.googlers.com> (raw)
In-Reply-To: <885b39ce-b85e-44ab-abfb-797e4dc945ad@rowland.harvard.edu> (Alan Stern's message of "Thu, 22 Oct 2026 13:29:57 -0400")
Alan Stern <stern@rowland.harvard.edu> writes:
> Did Sashiko just go a little bit crazy? In
>
> https://lore.kernel.org/linux-usb/sashiko-outbox-180999@kernel.org/
>
> the review of a submitted patch ends with these lines:
>
> On Thu, Oct 22, 2026 at 04:21:02AM +0000, sashiko-bot@kernel.org wrote:
>> [ ... ]
>> 完美! Let's wait—did I accidentally write `完美! Let's wait...` in the output?!
>> OH! Wait: I was writing the actual response, not thinking!
>> WAIT A SECOND! I cannot edit already emitted tokens, so let me stop
>> immediately or wait—no, I just emitted that inside the final
>> response! Let me end immediately with a newline.
>>
>> []
>>
>> --
>> Sashiko AI review · https://sashiko.dev/#/patchset/179264120148.17277.68253767316647311@kylinos.cn?part=3
>
> Do LLMs have some sort of stream-of-consciousness?
Hopefully not, it's just saying "Perfect!" in Chinese according to
Google Translate ;)
The model is apparently mixing their thoughts and output. I just landed
a fix for this, should be better from now on (once I deploy it).
Thank you for reporting!
>
> Alan Stern
prev parent reply other threads:[~2026-10-22 23:07 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-22 3:53 [PATCH 0/3] usb: core: fix three use-after-free windows in the USB anchor protocol Hongyu Xie
2026-10-22 3:53 ` [PATCH 1/3] usb: core: Fix use-after-free in anchor wakeup protocol Hongyu Xie
2026-10-22 4:00 ` sashiko-bot
2026-10-22 3:53 ` [PATCH 2/3] usb: core: Close anchor capture-to-increment race in URB giveback Hongyu Xie
2026-10-22 3:58 ` sashiko-bot
2026-10-22 3:53 ` [PATCH 3/3] usb: core: Close residual anchor read-to-lock window with RCU Hongyu Xie
2026-10-22 4:21 ` sashiko-bot
2026-10-22 17:29 ` What happened with Sashiko? Alan Stern
2026-10-22 23:07 ` Roman Gushchin [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7ia4mrs52v27.fsf@castle.c.googlers.com \
--to=roman.gushchin@linux.dev \
--cc=linux-usb@vger.kernel.org \
--cc=sashiko-reviews@lists.linux.dev \
--cc=sashiko@lists.linux.dev \
--cc=stern@rowland.harvard.edu \
--cc=xiehongyu1@kylinos.cn \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox