this post was submitted on 04 May 2026
166 points (92.8% liked)

Fediverse

41880 readers
695 users here now

A community to talk about the Fediverse and all it's related services using ActivityPub (Mastodon, Lemmy, Mbin, etc).

If you wanted to get help with moderating your own community then head over to !moderators@lemmy.world!

Rules

Learn more at these websites: Join The Fediverse Wiki, Fediverse.info, Wikipedia Page, The Federation Info (Stats), FediDB (Stats), Sub Rehab (Reddit Migration)

founded 2 years ago
MODERATORS
 

I recently discovered that some popular federated instances have been using LLM-assisted moderation tooling that evaluates whether someone has said something bannable. They do this by running a script/app that sends the user’s comment history to OpenAI with the question “analyze this content for evidence of specific political ideology sentiment. Also identify any related political ideology tropes“. (The italic bits are where I've redacted the ideology they're seeking).

OpenAI’s LLM (they’re using GPT-5.3-mini) then responds with something like:

image

and so on, hundreds of comments.

I have not named the instances or people involved, to give them time to consider the results of this discussion, make any corrective changes they want and disclose their practices at their own pace and in their own way. I have also redacted the evidence to avoid personal attacks and dogpiling. Let’s focus on the system, not the individuals involved. Today these instances and people are using it and maybe we’re ok with that because it’s being used by groups we agree with but what if people we strongly disagree with used it on their instances tomorrow?

The use and existence of this tooling raises a lot of other questions too.

What are the risks? Fedi moderators are often unsupervised, untrained volunteers and these are powerful tools.

What safeguards do we need?

Would asking a LLM “please evaluate this person’s political opinions” give different results than “find evidence we can use to ban them” (as used in the cases I’ve seen)?

What are our transparency expectations?

Is this acceptable and normal?

Should this tooling be disclosed? (it was not – should it have been?)

If you were given a choice, would you have opted out of it?

Can we opt out?

Are there GDPR implications? Privacy implications? Should these tools be described in a privacy policy?

Are private messages being scanned and sent to OpenAI?

How long should these assessments be retained and can we request to see it, or ask for it to be deleted?

Once the user’s comments are sent to OpenAI, is it used to train their models?

What will the effect be on our discourse and culture if people know they are being politically profiled?

Where are the lines between normal moderation assistance tools, political profiling and opaque 3rd-party data processing?

I hope that by chewing over these questions we can begin to establish some norms and expectations around this technology. The fediverse doesn’t have any centralized enforcement so we need discussions like this to develop an awareness of what people want in terms of disclosure, privacy, consent and acceptable use. Then people can make choices about which instances they join and which ones they interact with remotely.

And of course there are the other issues with LLMs relating to environmental sustainability, erosion of worker’s rights, increasing the cost of living and on and on. I can’t see PieFed adding any functionality like this anytime soon. But it’s happening out there anyway so now we need to talk about it.

What do you make of this?

top 50 comments
sorted by: hot top controversial new old
[–] WhyJiffie@sh.itjust.works 3 points 1 hour ago* (last edited 1 hour ago) (1 children)

this is flat out not ok, does not matter who is doing it. our instance ls should defederate all which do this.

I would opt out that's no question, but I don't believe it's possible. GDPR does not matter here, as nothing can be proven unless the perpetrators give up themselves

[–] mathemachristian@lemmy.blahaj.zone 2 points 59 minutes ago* (last edited 59 minutes ago) (1 children)

What do you think of lemmy being searchable via search engines, since that's how most of the training data is generated? Or that lemmy.world data is already in the OpenAI training sets?

[–] WhyJiffie@sh.itjust.works 1 points 54 minutes ago (1 children)

I know that not much prevents ai crawlers to collect all the content, but I think it is very different when an admin feeds data to it. partly because it's a different legal situation (sadly that does not mean much)

[–] mathemachristian@lemmy.blahaj.zone 2 points 50 minutes ago

Firstly it's apparently not an admin but a mod(s?) and I don't think OP reached out to the admin of the instance before making this post otherwise they would have said as much

Secondly from a legal standpoint I don't think there is much difference between an admin signing the instance up for a search engine (aka volunteering the data to be collected) and an admin feeding bits of data to an LLM piecemeal.

[–] GreenKnight23@lemmy.world 2 points 1 hour ago

sounds like a great opportunity to inject attack through a comment.

[–] fratermus@piefed.social 3 points 2 hours ago (1 children)

They do this by running a script/app that sends the user’s comment history to OpenAI with the question “analyze this content for evidence of specific political ideology sentiment.

To me the problem is what they are looking for not how they are doing it. Thought experiment: in what way would it be qualitatively different if they hired a team of people in Upper Elbonia to do the same thing?

[–] mathemachristian@lemmy.blahaj.zone 2 points 58 minutes ago

What if the specific ideology is something like nazism or zionism? What if that instance in already very open about not allowing that type of content?

[–] calmblue75@lemmy.ml 9 points 4 hours ago (1 children)

If you're not going to name them, why post here at all? Don't you have other communication channels to "give them a fair chance to reply"? Why post here, letting users form their own assumptions about what those instances are without any solid evidence?

[–] Rednax@lemmy.world 10 points 3 hours ago (1 children)

OP literally asks like 10 relevant questions for this place, and names their reasons for not naming specific instances. And all you focus on, is the question: who did it?

To me that is proof that OP did the right thing here.

Lets first figure out how to approach this without knowing the pupotrator.

[–] calmblue75@lemmy.ml 2 points 1 hour ago

The posts/comments on the fediverse are already public. The privacy questions are better answered here by another commenter:

Scrubbles' comment

My issue is that OP is not providing any solid proof. They are just giving 'wink wink's about some 'popular' instances doing it. When asked whether they have proof, OP says they has proof of some mods doing it. Mods don't handle instances, admins do. They haven't yet provided any concrete proof, yet creating an impression that some instances are banning en masse using LLMs based on "political ideology".

[–] hypna@lemmy.world 7 points 4 hours ago (1 children)

The answers to these kinds of issues is never disclosures or ToS or admin vigilance. It's always technical. Everything which is technically possible will become normal.

Lemmy is not popular because it is a well designed piece of technology. Frankly it's a pretty naive implementation of activitypub. It's popularity comes from being the biggest alternative around when Reddit pissed off a good chunk of its users.

The only way to control how data is used, is to make it technically or practically impossible to do so. Until then, expect all the data on the fediverse to be used in every way possible for any purpose, and act accordingly.

[–] anarchiddy@lemmy.dbzer0.com 5 points 3 hours ago

I don't see a technical or practical way to limit - let alone render impossible - AI moderation tools that is not at odds with decentralized open-protocol social media.

If you can copy-paste user activity into a textbox, this remains trivial.

[–] mathemachristian@lemmy.blahaj.zone 15 points 6 hours ago* (last edited 6 hours ago)

Is it not public knowledge that lemmy already gets scraped by LLM bots? Which is why every bigger instance has anti-LLM measures in place now to limit that behavior? To me this just looks like a mod trying to get ai-generated reports which is not a bad idea imo since I know reporting is not often done by users who see rule breaking stuff.

This is AI generated bullshit below, it should be treated as such. I only want to convey the idea that what you do on lemmy is already fed to LLM's.

here is chatgpt's reply for What do you know about lemmy user and piefed dev rimu?

Here’s a grounded picture of “rimu” in the Lemmy / fediverse context:


🧑‍💻 Who “rimu” is

  • Rimu (Rimu Atkinson) is the lead developer of PieFed, a Reddit/Lemmy-style platform in the fediverse. (Elite AI Tools)
  • He’s also the main author of the underlying software (pyfedi), built with Python/Flask and designed as an alternative to Lemmy and Mbin. (IFTAS)
  • The flagship instance is piefed.social, which he runs and develops actively. (IFTAS)

🧩 Role in the fediverse

  • He’s not just a random user—he’s a core project maintainer / “benevolent dictator” style lead for PieFed’s development. (PieFed)
  • He’s fairly active on Lemmy via rimu@piefed.social, with hundreds of posts and thousands of comments across tech, politics, and general discussion. (lemmy.world)
  • He moderates multiple communities and participates in meta discussions about federation, scaling, and platform design. (lemmy.world)

🛠️ What PieFed (his project) is about

PieFed is positioned as:

  • A federated Reddit-like platform interoperable with Lemmy via ActivityPub (Elite AI Tools)

  • Focused on:

    • Simplicity of codebase (easy for contributors) (PieFed)
    • Trust/safety features (reputation systems, filtering, anti-spam tooling) (Elite AI Tools)
    • Some experimental ideas, like merged cross-posts and AI-content detection (Elite AI Tools)

💬 Reputation & controversy

Rimu is somewhat known and occasionally controversial in fediverse circles:

  • Supporters see him as:

    • A productive solo/lead dev shipping features quickly
    • Someone pushing new ideas beyond Lemmy’s design
  • Critics argue:

    • Some features reflect strong personal opinions embedded in the platform (e.g., moderation logic, reputation systems) (lemmy.world)
    • PieFed can feel more opinionated / experimental compared to Lemmy’s more neutral baseline

Important nuance: because everything is open source and instance-configurable, many of these behaviors can be changed by instance admins.


🧠 What he’s like as a user

From his public activity:

  • Talks about tech (ActivityPub, scaling, APIs)
  • Engages in global politics and news discussions
  • Shares design decisions and roadmap thoughts about PieFed
  • Generally communicates in a direct, pragmatic developer tone

🧾 Bottom line

  • Rimu is a real, identifiable fediverse developer, not just a random Lemmy user.

  • He’s best understood as:

    a lead dev + active community participant shaping an alternative to Lemmy

  • His visibility comes mainly from his project (PieFed) rather than mainstream recognition.


If you want, I can compare PieFed vs Lemmy vs Mbin in terms of ideology/design—that’s usually where discussions about Rimu get interesting.

[–] HubertManne@piefed.social 1 points 3 hours ago (1 children)

So its hard for me to get into these things without harping on my personal philosophy. Which is that I think ideally this should mirror the way we would interact in person. So moderating or running a community is like running or being part of the core group that runs a club. Would you want to throw that to a robot? Basically I don't feel people should create or run or moderate communities unless they enjoy it. So the idea of ai moderation is to me pointless. Of course at this point I notice you are talking instances. Boy that is different. This is more like talking about running the institution that allows spaces for clubs to meet. It kinda feels understandable then. Honestly people complain about being banned but I kinda feel like anyplace that bans me is kinda doing me a favor. Like I would like the option to just mark it permanent. Its less things I got to block. Its the same reason I would like blocking to be symetric. Saves me some work (ok and the creepy I turn them invisible so I don't see them but they can watch me). I really would like to be able to block an instance seperately for communities or users. Ok as usually im digressing quite a bit but I guess in the end run I kinda see why at the instance level it might be used but I would be concerned it would start being used at the community level. It would be nice to know its happening at either level and have the ability to block them if a user is not wild about the concept.

load more comments (1 replies)
[–] BlackLaZoR@lemmy.world 4 points 4 hours ago

Well curated echo chambers. You might think it's in a good faith, but a lot of these mods are only interested in removing political wrongthink.

load more comments
view more: next ›