Re: [ANNOUNCE] A Syzbot-style Platform for Verifying and Fixing LLM-reported Bugs

[Yuan Tan]

On 9/2/26 08:10, Jan Kara wrote:
> Hi,
>
> On Sun 30-08-26 04:55:45, Yuan Tan wrote:
>> A month ago, I posted an RFC[1] to the mailing list proposing an automated
>> platform that validates AI-reported bugs and prepares draft fixes, and
>> later discussed the idea at the Netdev conference. After further
>> development, it is finally ready.
>>
>> While preparing to send this email, I noticed that Roman has since started
>> a related discussion:
>> [MAINTAINERS SUMMIT] The place of AI code review in the Linux Kernel process
>>
>> It turns out this platform already addresses several of the needs raised
>> there.
>>
>> The platform is available at:
>> https://bugtracker.nebusec.ai
>>
>> It is currently hosted under my company's domain for convenience. I would
>> prefer to move it to a neutral, community-oriented domain once the project
>> name is settled.
>> Access is currently restricted to maintainers whose email addresses are
>> listed in the Linux kernel MAINTAINERS file.
>> For now, only bug reports from the net subsystem have been fully imported
>> and processed.
> I was playing with this for a while and this looks useful. Some notes I have:
>
> 1) When you download the patch, it has 'From' field set to some value (I've
> actually seen different values in different patches). Perhaps it would make
> sense to automatically set From to the person downloading the patch (or
> maybe value configured in user's profile)?
>
Fixed!
>
> 2) Based on current state of the kernel doc, the patches should contain
> "Assisted-by: LLM" tag although I understand that might be controversial.
Fixed! 
>
> 3) It would be nice if you could "assign" the report to yourself - i.e.,
> you've decided to handle this and don't want co-maintainers to waste time
> on it anymore.

This feature is ready now. Our fixing team will also assign bugs to
themselves. Feel free to remove their names if you think it would be
better for you to fix a particular bug yourself. Our team definitely
won’t know this part of the code as well as the maintainers do, and
reviewing our patches may sometimes take more effort than fixing the bug
directly.

As for patch generation, I’ll make some adjustments. This is indeed
because I explicitly asked the llm in the prompt to follow the reverse
Christmas tree style.

Also, I haven’t had a chance yet to enable fix-status tracking or import
the Sashiko bug reports for the fs subsystem. So far, I’ve only finished
this for net, as cleaning up and normalizing all the data has been quite
a bit of work.

Some fs bugs may still be outside the threat model, such as those
requiring a corrupted or malicious filesystem to trigger. I haven’t
filtered those out yet.

Over the next couple of days, I’ll first run the fix-status detection
for the filesystem bugs and try to reduce as much unnecessary work for
you as possible.

Yuan

>
> Thanks for putting together the service.
>
> 								Honza