public inbox for linux-input@vger.kernel.org
 help / color / mirror / Atom feed
From: Roman Gushchin <roman.gushchin@linux.dev>
To: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Antheas Kapenekakis <lkml@antheas.dev>,
	Sanjay Govind <sanjay.govind9@gmail.com>,
	Vicki Pfau <vi@endrift.com>,
	Nilton Perim Neto <niltonperimneto@gmail.com>,
	Mario Limonciello <mario.limonciello@amd.com>,
	"Pierre-Loup A. Griffais" <pgriffais@valvesoftware.com>,
	linux-input@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2] xpad: Overhaul device data for wireless devices
Date: Wed, 8 Apr 2026 10:45:47 -0700	[thread overview]
Message-ID: <B636001C-FB54-49EB-9A30-D255879788E7@linux.dev> (raw)
In-Reply-To: <adaOmEQNXXPhxmmx@google.com>



> On Apr 8, 2026, at 10:24 AM, Dmitry Torokhov <dmitry.torokhov@gmail.com> wrote:
> 
> On Wed, Apr 08, 2026 at 05:47:06PM +0200, Antheas Kapenekakis wrote:
>>> On Wed, 8 Apr 2026 at 07:04, Sanjay Govind <sanjay.govind9@gmail.com> wrote:
>>> 
>>> On Wed, Apr 8, 2026 at 4:52 PM Dmitry Torokhov
>>> <dmitry.torokhov@gmail.com> wrote:
>>>> I think you'd have to spin up your own instance for that...
>>> 
>>> makes sense
>>> 
>> 
>> Hi Sanjay,
>> I have a workflow for running an llm and getting reviews locally.
>> Perhaps I will post it to the mailing list soon. I can cc you. I have
>> been out for the Easter holidays
>> 
>> Of course, you will need your own LLM and harness for that, Claude
>> code/Antigravity/Copilot/Opencode, etc. I know they aren't
>> particularly cheap.
>> 
>> Dmitry, sashiko looks great, I left a star. I could also cc you. I
>> will also reference the prompts used in that as it claims some
>> subsystem specific ones. From a quick glance it seems to might suffer
>> from context bloat though. There are a lot of guideline files that
>> could have higher information density.
> 
> I am just a happy user of sashiko, I'll leave it to Roman to comment on
> the potential bloat concerns.

All I can say is Sashiko is an open-source project and I’m happy to take
any pull requests (including alternative prompts) which are improving 
the quality of reviews. I’m not attached to any particular approach to the
prompting and happy to change it assuming there is data showing that
some other approach is better. 

Thanks!

      reply	other threads:[~2026-04-08 17:46 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-04  8:39 [PATCH v2] xpad: Overhaul device data for wireless devices Sanjay Govind
2026-04-07  4:46 ` Dmitry Torokhov
2026-04-07  6:36   ` Sanjay Govind
2026-04-07 19:22     ` Sanjay Govind
2026-04-08  4:52       ` Dmitry Torokhov
2026-04-08  5:04         ` Sanjay Govind
2026-04-08 15:47           ` Antheas Kapenekakis
2026-04-08 17:23             ` Dmitry Torokhov
2026-04-08 17:45               ` 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=B636001C-FB54-49EB-9A30-D255879788E7@linux.dev \
    --to=roman.gushchin@linux.dev \
    --cc=dmitry.torokhov@gmail.com \
    --cc=linux-input@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lkml@antheas.dev \
    --cc=mario.limonciello@amd.com \
    --cc=niltonperimneto@gmail.com \
    --cc=pgriffais@valvesoftware.com \
    --cc=sanjay.govind9@gmail.com \
    --cc=vi@endrift.com \
    /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