Collection of this group's data for a LLM-powered weekly report

abompard commented

2026-09-09 09:04:25 +00:00

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. 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. 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:

the mailing-list
discourse posts with the #dei-team tag
meetings on the Matrix meeting channels
this tracker

In the latest version, I've added the possiblity to gather messages exchanged in Matrix channels. The 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 tracker
the matrix channel

I would like to make the case for source 3 (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 yesterday 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.

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. 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: - the mailing-list - discourse posts with the `#dei-team` tag - meetings on the Matrix meeting channels - this tracker In the latest version, I've added the possiblity to gather messages exchanged in Matrix channels. The 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 tracker 3. the matrix channel I would like to make the case for source 3 (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 yesterday 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.

jflory7 added the

labels

2026-09-09 17:16:21 +00:00

jflory7 added this to the 2026 Q3 Team Goals milestone

2026-09-09 17:16:25 +00:00

jflory7 commented

2026-09-09 17:20:05 +00:00

Owner

Thanks @abompard for raising this ticket. 🙏 Our meetings are on a temporary pause, so feedback on the ticket might roll in slowly.

Personally, I am -1 only for the DEI Team Matrix room. For mailing lists (we don't have one anymore), Fedora Discussion, and this issue tracker, I am +1.

I think Matrix is different from the other channels because Matrix chat rooms are not indexable, and in this specific aspect, are somewhat less discoverable despite chat history being open access, unencrypted, and public. Although it is public and anyone may participate, sometimes we discuss sensitive topics in our team channel. It is critical that we maintain a safe space for people to feel comfortable to raise issues and discuss sensitive issues, even if the chat room itself is public. I worry that ingesting our team's Matrix room might end up being a troll-magnet for things which are not actually decided or finalized yet.

I could be persuaded otherwise, depending what others in the team think. But my personal view for the DEI Team and LLM-gen-AI summaries is Discourse/Forge good, Matrix bad. 😛

Thanks @abompard for raising this ticket. 🙏 Our meetings are on a temporary pause, so feedback on the ticket might roll in slowly. Personally, I am `-1` only for the DEI Team Matrix room. For mailing lists (we don't have one anymore), Fedora Discussion, and this issue tracker, I am `+1`. I think Matrix is different from the other channels because Matrix chat rooms are not indexable, and in this specific aspect, are somewhat less discoverable despite chat history being open access, unencrypted, and public. Although it is public and anyone may participate, sometimes we discuss sensitive topics in our team channel. It is critical that we maintain a safe space for people to feel comfortable to raise issues and discuss sensitive issues, _**even if the chat room itself is public**_. I worry that ingesting our team's Matrix room might end up being a troll-magnet for things which are not actually decided or finalized yet. I could be persuaded otherwise, depending what others in the team think. But my personal view for the DEI Team and LLM-gen-AI summaries is Discourse/Forge good, Matrix bad. 😛

👍 2

jonatoni commented

2026-09-29 20:02:48 +00:00

Owner

I took some time to think about this, and I really agree with Justin’s perspective here. I also think Matrix deserves a different approach from Discourse and Forge, especially given that some of the conversations in the DEI room can be sensitive or still evolving. I’m definitely +1 for Discourse and Forgejo, while keeping the DEI Matrix room out.

👍 1

jflory7 commented

2026-09-30 22:03:50 +00:00

Owner

Thanks for weighing in @jonatoni. Since it has been about a month, I am going to close this ticket as wontfix. Thanks for raising the ticket and asking us, @abompard! 🙏

Thanks for weighing in @jonatoni. Since it has been about a month, I am going to close this ticket as `wontfix`. Thanks for raising the ticket and asking us, @abompard! 🙏

jflory7

2026-09-30 22:03:50 +00:00

closed this issue
added
state
wontfix
and removed
needs
team vote
labels

Rows
Columns

Collection of this group's data for a LLM-powered weekly report #69