Sashiko review email for [email protected]?
Sean Christopherson
reviewer+KVM and LKML, which I stupidly forgot to Cc :-(
Quoted 21 lines · Janosch Frank
Quoted 20 lines · Sean Christopherson
Hello people with a
MAINTAINERSentry that uses [email protected] as a mailing list!How would y'all feel about enabling Sashiko[*] emails for [email protected]? For a variety of reasons, Sashiko currently only logs its reviews to https://sashiko.dev
by default. If subsystems want to receive on-list mails, they need to opt-in.I really, really want to enable email reviews for KVM x86, as Sashiko has found an almost embarassing number of bugs that (a) would have been painful to debug had they escaped review and (b) I'm not convinced would have been found by traditional review. And for me at least the signal:noise ratio is more than good enough. There are still hallucinations and false positives from time to time, but the good outweighs the bad by quite a bit, it's cathartic to flame AI when it's wrong, and worst case scenario I can simply ignore Sashiko.
But, currently Sashiko is only capable of making decisions based on mailing list, i.e. as things stand, _all_ of kvm@ needs to opt-in. Before I badger Roman to add bespoke logic to Sashiko's email flow, e.g. to special case KVM x86 in some way, I want to see if there's a general consensus in favor (or against) enabling review emails.
Quoted 5 lines
Quoted 3 lines
Thanks!
Sure,
^
|- This
Quoted 1 line
as long as there will be no mails from Sashiko or at most one mail per thread.
is in conflict with the caveats here, as per-patch email is exactly what I am proposing (the current state is that Sashiko never sends mails).
Quoted 2 lines
I'd appreciate something like "I found problems in this thread, here's the link, go look if you want to".
While this would be easier than manually searching through the web site, there would still be a sizeable barrier between contributors/maintainers and Sashiko feedback. E.g. to click through an out-of-band source, copy+paste the response into the original thread, etc.
What are your concerns with per-patch email? Hallucinations and noise are definitely a potential problem, but IMO that can be handled by per-subsystem policy. E.g. if the signal:noise ratio is particularly poor for a subsystem, that subsystem can document/state that responding to, or even reading, Sashiko mails is completely optional.
Beyond that, I'm struggling to understand why folks are opposed to getting mails from Sashiko, especially for a list as large as kvm@. As others pointed out, the volume for kvm@ is already high, and it's trivially easy to create a filter for mails from [email protected]. I.e. it seems highly unlikely that mail from Sashiko will require anyone to significantly rethink and/or rework their workflow, whereas the web site approach is very disruptive to email-based review, at least for me.
Sean Christopherson
reviewer+KVM and LKML (to capture as many of these discussions possible)
Quoted 21 lines · Pranjal Shrivastava
Quoted 14 lines · Sean Christopherson
Hello people with a
MAINTAINERSentry that uses [email protected] as a mailing list!How would y'all feel about enabling Sashiko[*] emails for [email protected]? For a variety of reasons, Sashiko currently only logs its reviews to https://sashiko.dev
by default. If subsystems want to receive on-list mails, they need to opt-in.I really, really want to enable email reviews for KVM x86, as Sashiko has found an almost embarassing number of bugs that (a) would have been painful to debug had they escaped review and (b) I'm not convinced would have been found by traditional review. And for me at least the signal:noise ratio is more than good enough. There are still hallucinations and false positives from time to time, but the good outweighs the bad by quite a bit, it's cathartic to flame AI when it's wrong, and worst case scenario I can simply ignore Sashiko.
Quoted 5 lines
But, currently Sashiko is only capable of making decisions based on mailing list, i.e. as things stand, _all_ of kvm@ needs to opt-in. Before I badger Roman to add bespoke logic to Sashiko's email flow, e.g. to special case KVM x86 in some way, I want to see if there's a general consensus in favor (or against) enabling review emails.
Quoted 3 lines
I vote for enabling it, it has proven helpful at multiple places. I would wanna ratelimit the # emails it may send in case of a malfunction though.
Ya, there's definitely an implied "we'll turn it back off if there are major problems". But I don't see any reason to treat Sashiko any differently than other automated systems in this regard; when bots have been too noisy in the past, we've complained, and the bot/system was "fixed".
Quoted 24 lines · Sean Christopherson
+KVM and LKML (to capture as many of these discussions possible)
Quoted 21 lines · Pranjal Shrivastava
Quoted 19 lines · Sean Christopherson
Hello people with a
MAINTAINERSentry that uses [email protected] as a mailing list!How would y'all feel about enabling Sashiko[*] emails for [email protected]? For a variety of reasons, Sashiko currently only logs its reviews to https://sashiko.dev
by default. If subsystems want to receive on-list mails, they need to opt-in.I really, really want to enable email reviews for KVM x86, as Sashiko has found an almost embarassing number of bugs that (a) would have been painful to debug had they escaped review and (b) I'm not convinced would have been found by traditional review. And for me at least the signal:noise ratio is more than good enough. There are still hallucinations and false positives from time to time, but the good outweighs the bad by quite a bit, it's cathartic to flame AI when it's wrong, and worst case scenario I can simply ignore Sashiko.
But, currently Sashiko is only capable of making decisions based on mailing list, i.e. as things stand, _all_ of kvm@ needs to opt-in. Before I badger Roman to add bespoke logic to Sashiko's email flow, e.g. to special case KVM x86 in some way, I want to see if there's a general consensus in favor (or against) enabling review emails.
Quoted 8 lines
Quoted 3 lines
I vote for enabling it, it has proven helpful at multiple places. I would wanna ratelimit the # emails it may send in case of a malfunction though.
Ya, there's definitely an implied "we'll turn it back off if there are major problems". But I don't see any reason to treat Sashiko any differently than other automated systems in this regard; when bots have been too noisy in the past, we've complained, and the bot/system was "fixed".
Yea, fair point. Enable +1 from me.
Thanks,
Praan
Quoted 24 lines · On Wed, 20 May 2026 14:34:11 +0000 Sean Christopherson <[email protected]>…
+KVM and LKML (to capture as many of these discussions possible)
Quoted 21 lines · Pranjal Shrivastava
Quoted 19 lines · Sean Christopherson
Hello people with a
MAINTAINERSentry that uses [email protected] as a mailing list!How would y'all feel about enabling Sashiko[*] emails for [email protected]? For a variety of reasons, Sashiko currently only logs its reviews to https://sashiko.dev
by default. If subsystems want to receive on-list mails, they need to opt-in.I really, really want to enable email reviews for KVM x86, as Sashiko has found an almost embarassing number of bugs that (a) would have been painful to debug had they escaped review and (b) I'm not convinced would have been found by traditional review. And for me at least the signal:noise ratio is more than good enough. There are still hallucinations and false positives from time to time, but the good outweighs the bad by quite a bit, it's cathartic to flame AI when it's wrong, and worst case scenario I can simply ignore Sashiko.
But, currently Sashiko is only capable of making decisions based on mailing list, i.e. as things stand, _all_ of kvm@ needs to opt-in. Before I badger Roman to add bespoke logic to Sashiko's email flow, e.g. to special case KVM x86 in some way, I want to see if there's a general consensus in favor (or against) enabling review emails.
Quoted 9 lines
Quoted 3 lines
I vote for enabling it, it has proven helpful at multiple places. I would wanna ratelimit the # emails it may send in case of a malfunction though.
Ya, there's definitely an implied "we'll turn it back off if there are major problems". But I don't see any reason to treat Sashiko any differently than other automated systems in this regard; when bots have been too noisy in the past, we've complained, and the bot/system was "fixed".
Given the number of emails to lkml a few more won't hurt :-) But perhaps they should come from "Sashiko (AI bot)" to remind everyone on every email.
-- David
Quoted 50 lines · Sean Christopherson
+KVM and LKML, which I stupidly forgot to Cc :-(
Quoted 21 lines · Janosch Frank
Quoted 20 lines · Sean Christopherson
Hello people with a
MAINTAINERSentry that uses [email protected] as a mailing list!How would y'all feel about enabling Sashiko[*] emails for [email protected]? For a variety of reasons, Sashiko currently only logs its reviews to https://sashiko.dev
by default. If subsystems want to receive on-list mails, they need to opt-in.I really, really want to enable email reviews for KVM x86, as Sashiko has found an almost embarassing number of bugs that (a) would have been painful to debug had they escaped review and (b) I'm not convinced would have been found by traditional review. And for me at least the signal:noise ratio is more than good enough. There are still hallucinations and false positives from time to time, but the good outweighs the bad by quite a bit, it's cathartic to flame AI when it's wrong, and worst case scenario I can simply ignore Sashiko.
But, currently Sashiko is only capable of making decisions based on mailing list, i.e. as things stand, _all_ of kvm@ needs to opt-in. Before I badger Roman to add bespoke logic to Sashiko's email flow, e.g. to special case KVM x86 in some way, I want to see if there's a general consensus in favor (or against) enabling review emails.
Quoted 5 lines
Quoted 3 lines
Thanks!
Sure,
^
|- ThisQuoted 1 line
as long as there will be no mails from Sashiko or at most one mail per thread.
is in conflict with the caveats here, as per-patch email is exactly what I am proposing (the current state is that Sashiko never sends mails).>
Quoted 2 lines
I'd appreciate something like "I found problems in this thread, here's the link, go look if you want to".
While this would be easier than manually searching through the web site, there would still be a sizeable barrier between contributors/maintainers and Sashiko feedback. E.g. to click through an out-of-band source, copy+paste the response into the original thread, etc.
What are your concerns with per-patch email? Hallucinations and noise are definitely a potential problem, but IMO that can be handled by per-subsystem policy. E.g. if the signal:noise ratio is particularly poor for a subsystem, that subsystem can document/state that responding to, or even reading, Sashiko mails is completely optional.
Quoted 7 lines
Beyond that, I'm struggling to understand why folks are opposed to getting mails from Sashiko, especially for a list as large as kvm@. As others pointed out, the volume for kvm@ is already high, and it's trivially easy to create a filter for mails from [email protected]. I.e. it seems highly unlikely that mail from Sashiko will require anyone to significantly rethink and/or rework their workflow, whereas the web site approach is very disruptive to email-based review, at least for me.
In my mind there's a clear separation between human feedback and non-human feedback. So the disruption is something that I prefer. Maybe I just haven't yet fully evaluated how much I trust its review in contrast to my human coworkers.
That being said, I won't be the one holding this back. I see value in this and I'd be happy to test this.
Paolo Bonzini
maintainerQuoted 8 lines · Janosch Frank
Quoted 7 lines
Beyond that, I'm struggling to understand why folks are opposed to getting mails from Sashiko, especially for a list as large as kvm@. As others pointed out, the volume for kvm@ is already high, and it's trivially easy to create a filter for mails from [email protected]. I.e. it seems highly unlikely that mail from Sashiko will require anyone to significantly rethink and/or rework their workflow, whereas the web site approach is very disruptive to email-based review, at least for me.
Quoted 4 lines
In my mind there's a clear separation between human feedback and non-human feedback. So the disruption is something that I prefer. Maybe I just haven't yet fully evaluated how much I trust its review in contrast to my human coworkers.
I think this is solved by saying there's no need to *answer* Sashiko, it's treated just like any bot. It should be enough to mention on v(n+1) what suggestions were taken (or otherwise influenced the code, for example by adding a new comment to the code); and possibly a single reply to the cover letter saying "all remaining issues that AI pointed out are preexisting" (and if there are false positives, perhap, include a short explanation).
Paolo