Hi folks,
I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called "This Week in Fedora" https://abompard.fedorapeople.org/twif/. This generation uses an LLM. The goal is to make it easier to catch up with everything that's going on in the project, and to give visibility to each group's work and requests for help or testing. I think that from a newcomer's point of view, having an insight on what a group is working on at a point in time is helpful to decide whether it's interesting and worth contributing to. I'm collecting activity from: - this mailing-list - discourse posts with the #kernel tag
In the latest version, I've added the possiblity to gather messages exchanged in Matrix channels. The `#kernel` channel is public and its history is available to anyone, but a quite a few people in mutiple Matrix channels were unhappy about the LLM collecting this info, for various reasons. I would like to know whether this group is OK with my program collecting and submitting info to an LLM from the following sources: 1. mailing-lists and discourse posts 2. the matrix channel
I would like to make the case for source 2 (the Matrix channel) because I think it's less obvious: knowing the "tone" of a conversation and the currently discussed subjects before joining is very important to help contribute to it. It's like when you're added to an empty group chat and you don't know how to start. That's why we show history to new channel members, and this would be the same idea at a higher level. Plus there's actual work going on in there for a lot of groups. That said, I recognize that the form of the tool influences its use, chat messages are usually less thought-through than emails or forum posts, and members could be indimidated that something they write there and regret end up in a visible summary (the program respects message edits, but anyway). Since my goal is to foster participation, the one thing I don't want to do is to hinder it in another way.
I know I've asked this in the chat last week but someone in another room noted that people can easily miss Matrix messages, which it true.
Please decide which collected sources, if any, you are OK with (and if you work in other places that you would like to have collected, of course (I can do RSS feeds!)). If the group is OK with Matrix channel collection but some individuals aren't, I can also exclude certain Matrix usernames from collection throughout the Matrix channels that are not meetings.
I'm happy to answer questions if you have any. Thanks!
On 17 Sep 2026 09:21, Aurelien Bompard wrote:
Hi folks,
I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called "This Week in Fedora" https://abompard.fedorapeople.org/twif/. This generation uses an LLM.
[...snip...]
Sorry, you lost me right here. I am not okay with *any* LLM collecting anything I have ever written or said. I am simply tired of being used as a data source by everyone and everything.
On Thu, Sep 17, 2026 at 3:21 AM Aurelien Bompard abompard@fedoraproject.org wrote:
Hi folks,
I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called "This Week in Fedora" https://abompard.fedorapeople.org/twif/. This generation uses an LLM. The goal is to make it easier to catch up with everything that's going on in the project, and to give visibility to each group's work and requests for help or testing. I think that from a newcomer's point of view, having an insight on what a group is working on at a point in time is helpful to decide whether it's interesting and worth contributing to. I'm collecting activity from:
- this mailing-list
- discourse posts with the #kernel tag
In the latest version, I've added the possiblity to gather messages exchanged in Matrix channels. The `#kernel` channel is public and its history is available to anyone, but a quite a few people in mutiple Matrix channels were unhappy about the LLM collecting this info, for various reasons. I would like to know whether this group is OK with my program collecting and submitting info to an LLM from the following sources:
- mailing-lists and discourse posts
- the matrix channel
I would like to make the case for source 2 (the Matrix channel) because I think it's less obvious: knowing the "tone" of a conversation and the currently discussed subjects before joining is very important to help contribute to it. It's like when you're added to an empty group chat and you don't know how to start. That's why we show history to new channel members, and this would be the same idea at a higher level. Plus there's actual work going on in there for a lot of groups. That said, I recognize that the form of the tool influences its use, chat messages are usually less thought-through than emails or forum posts, and members could be indimidated that something they write there and regret end up in a visible summary (the program respects message edits, but anyway). Since my goal is to foster participation, the one thing I don't want to do is to hinder it in another way.
I know I've asked this in the chat last week but someone in another room noted that people can easily miss Matrix messages, which it true.
A few members expressed opposition to this in chat. While I am personally not completely opposed, as I expect anything said in the matrix channel is public discourse, I do also understand people's concerns. As I end up as somewhat a defacto moderator for the channel, I would be happy to provide a (human written) summary of the week's conversation when there is any of note, if it helps, for the newsletter.
Justin
Please decide which collected sources, if any, you are OK with (and if you work in other places that you would like to have collected, of course (I can do RSS feeds!)). If the group is OK with Matrix channel collection but some individuals aren't, I can also exclude certain Matrix usernames from collection throughout the Matrix channels that are not meetings.
I'm happy to answer questions if you have any. Thanks!
kernel mailing list -- kernel@lists.fedoraproject.org To unsubscribe send an email to kernel-leave@lists.fedoraproject.org Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/ List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines List Archives: https://lists.fedoraproject.org/archives/list/kernel@lists.fedoraproject.org Do not reply to spam, report it: https://forge.fedoraproject.org/infra/tickets/issues/new
Justin Forbes wrote:
As I end up as somewhat a defacto moderator for the channel, I would be happy to provide a (human written) summary of the week's conversation when there is any of note, if it helps, for the newsletter.
That would be very cool! Are you folks still OK with me collecting messages from this mailing-list and the discourse posts with the `#kernel` tag? (besides Al, I've added them to the exclude list so none of their messages will reach the LLM) If collecting from those two sources is representative of the work of this group, then no need to add yourself the burden of sending me a hand-written summary. I usually build the summary around 08:00 UTC on Mondays, but I can edit it at any time, so if you still want to go that route please send me the summary at my Red Hat email (same username, redhat.com domain) or on this alias (if email aliases keep working through all the spam protection...)
Thanks!
On 9/22/26 01:08, Justin Forbes wrote:
On Thu, Sep 17, 2026 at 3:21 AM Aurelien Bompard abompard@fedoraproject.org wrote:
I'm generating a weekly report of activity in the Fedora project centered on teams and SIGs, it's called "This Week in Fedora" https://abompard.fedorapeople.org/twif/.
Side note: I like the idea, as this is something where AI/LLMs can make life easier and handle things that otherwise would never be done. I'm also the exact target audience, as I would like to know more about what happens within the project but lack the time. But FWIW, I quickly stopped reading them, as they are way too long/detailed for me and/or badly structured. The summary, as found in the latest issue, is no help there: it's a block of text that starts with a sentence I guess every writer/editor would immediately remove, as it transports no valuable information and does not get you hooked. But well, I'm a former editor/writer, so I might be overly strict here. Anyway, if you are interested in more feedback on this, let me know where to provide it (or talk to me on Matrix), as this is the wrong place for that.
I know I've asked this in the chat last week but someone in another room noted that people can easily miss Matrix messages, which it true.
A few members expressed opposition to this in chat. While I am personally not completely opposed, as I expect anything said in the matrix channel is public discourse, I do also understand people's concerns.
I understand those concerns, but for me it's more like: "it's public communication, so people always have and always will process in various (sometimes unforeseen and sometimes bad) ways, and I think that's okay". Furthermore, I fear that trying to established a "no llvm processing" policy on a per-channel level just leads to a mess so that that will be ignored by everyone except a few good guys like Aurelien or Justin, but makes their already life harder.
As I end up as somewhat a defacto moderator for the channel, I would be happy to provide a (human written) summary of the week's conversation when there is any of note, if it helps, for the newsletter.
I hate a lot about the state of the world wrt to AI/LLMs -- and something human written is often way better. But Justin, you have a lot of things to handle already. I don't think you should put this ontop So I'd vote for: leave this to an LLM -- and maybe give Justin or one or two others a chance to edit it before publication.
Ciao, Thorsten
Hey Thorsten!
But FWIW, I quickly stopped reading them, as they are way too long/detailed for me and/or badly structured. The summary, as found in the latest issue, is no help there: it's a block of text that starts with a sentence I guess every writer/editor would immediately remove, as it transports no valuable information and does not get you hooked. But well, I'm a former editor/writer, so I might be overly strict here. Anyway, if you are interested in more feedback on this, let me know where to provide it (or talk to me on Matrix), as this is the wrong place for that.
Yeah I'm very interested! I'm neither a writer nor a native English speaker so my writing abilities are limited, I'd be very interested in making the report more readable, especially the top-level summary. I'd be happy to discuss that with you, could you please open a ticket on https://forge.fedoraproject.org/infra/this-week-in-fedora/issues ? Thanks for your help!
I'd vote for: leave this to an LLM -- and maybe give Justin or one or two others a chance to edit it before publication.
Justin Wheeler is currently working on getting the app to output to a Community Blog article in draft mode, where any blog editor could go and amend it. Hopefully that will help group members fix errors.
kernel@lists.fedoraproject.org
-
Al Stone -
Aurelien Bompard -
Justin Forbes -
Thorsten Leemhuis