this post was submitted on 04 May 2026
299 points (91.0% liked)

Fediverse

41887 readers
768 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?

(page 5) 50 comments
sorted by: hot top controversial new old
[–] TheCornCollector@piefed.zip 8 points 21 hours ago

I’m really not fond of the profiling by automated means, but it seems like an inevitable consequence of the design of the threadiverse. Everything is public and easily accessible by anyone that would like to profile you.

I certainly disapprove of moderation based on ideology. Moderation should be based on quality of the content and if it fits in the publicly readable rules. Definitely not some hidden analytics or if the user completely fits in the in-group of the moderator.

I will admit that this might be a good way to find and filter out LLM based bots that are only there to promote or manipulate the conversation. But it should still be done according to public rules.

[–] melsaskca@lemmy.ca 3 points 17 hours ago (1 children)

So they are not using AI to assist the user or administrator, but as a cop who points out the "guilty". All the ploughshares are being converted back into weapons.

load more comments (1 replies)
[–] A_norny_mousse@piefed.zip 17 points 1 day ago* (last edited 1 day ago) (1 children)

I recently discovered that some popular federated instances have been using LLM-assisted moderation tooling

First of all, I agree with your main point, that this* is problematic, wrong even (and should not happen).

But I need to ask: how did you find out? Is this something that could be traced objectively, or did some people report/admit it?

Are they uploading stuff to corporate LLMs, i.e. LLMs that do not run themselves? (I think you answered this already when you wrote OpenAI, but I want this spelled out)

Are only admins or also mods doing this? That would make a big difference.

I'm also a little unclear about the process: are they uploading (copy-pasting) the actual comments, or links to them? To what extent can all this be automated on Lemmy/Piefed etc.? I.e., are there admin tools that just spit out all of a user's content?

* again: specific political profiling outsourced to LLMs. OTOH we already have instances that do this manually.
But imo the process is deplorable even if they use LLMs with different prompts for modding.

[–] rimu@piefed.social 7 points 1 day ago (4 children)

It can be traced objectively.

It's mods.

They're using software that they made to do this quickly and easily, it's not a manual copy and paste situation.

load more comments (4 replies)
[–] WongKaKui@piefed.ca 15 points 1 day ago

As for the privacy issue:

The only counter to this is to move to a closed end-to-end encrypted groupchat so it can't be mass LLM analyzed...

If you want a public forum, well... its public...

You can't stop a script from just grabbing all the posts/comments... and its also federated, so the bot only needs to be able to access one instance and get it...

I mean they could simply just set up their own instance and pretend its just a benigh single-user instance... like what are you gonna do, defed all small instances preemptively? Use "login walls" to make the forum private? And somehow trust all other admins that are federated and make them also enforce a "login wall" policy?

Its a PUBLIC forum...

the only solution for privacy is a groupchat and only let in people that can keep a promise to not screenshot everything and give it to a LLM.

[–] the_abecedarian@piefed.social 12 points 1 day ago (1 children)

this is the kind of thing that makes me want to never post or comment anywhere on the internet

[–] scrubbles@poptalk.scrubbles.tech 11 points 1 day ago (1 children)

What safeguards do we need?

None, defederate, switch instances if you disagree. Fediverse is open, there are no rules beyond what the instance owner puts in place.

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)?

Yes. That's out of your control though, beyond switching instances.

What are our transparency expectations?

None, beyond what you trust of the admins in putting in their own transparency expectations. You should not expect any transparency from the admin, these are random people you are trusting with your data.

Is this acceptable and normal?

It's their server, they can do what they like. Acceptable or normal are irrelevant.

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

Again, who would force it? Even if Lemmy/Piefed forced a checkbox, they could just fork it to ignore that checkbox.

Can we opt out?

If the instance owner opted for that, it's on a server by server basis

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

Probably, but everything here is open and unencrypted, see my other comments. It's hard to argue that what you put on here in an unencrypted and open platform which is then blasted out to any other server who wants to listen had an expectation of privacy.

Are private messages being scanned and sent to OpenAI?

You should assume your unencrypted open DMs are scanned by anyone. If privacy is needed, follow the guidelines and switch to something like Matrix for DMs. ActivityPub is open.

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

Per legal requirements, or asking your instance owner.

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

Depends on how the instance owner set up their API usage. For a user, you should assume yes.

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

Open to wild speculation, and I assume others will do that for me.

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

About the same as before. Bias in, bias out. Whatever the bias of the mods previously had, positive or negative, will continue through.

[–] Grail@multiverse.soulism.net 6 points 19 hours ago (1 children)

As an instance admin, I'm happy to commit right here and now to defederate any instance whose admins are funneling user content to ChatGPT to analyse political leanings, and I'd like it if all the other admins did too.

[–] mathemachristian@lemmy.blahaj.zone 0 points 9 hours ago (1 children)

Seems lemmy.world is adding training data to ChatGPT, it already knows about your instance for example. The only actual link it provides is a lemmy.world thread where you post about your political belief.

What are grail@multiverse.soulism.net political leanings?Based on available public posts and discussions, the account grail@multiverse.soulism.net appears to hold highly unconventional, fringe political views, but there are some clear patterns.

1) Core ideology: anarchism (explicit)

  • The user explicitly describes their community as “an anarchist instance” and aligns with anarchist principles. (FOSSDLE)
  • They also mention “anarcho-antirealism” as their political philosophy. (FOSSDLE)

👉 So at minimum, their baseline is anti-state / anti-hierarchy anarchism.


2) Strong anti-hierarchy, anti-capitalist leanings

  • Their ideology rejects hierarchies broadly, including capitalism and even “natural laws” framed as oppressive. (FOSSDLE)
  • Posts frame capitalism and “consensus reality” as bourgeois constructs. (Multiverse)

👉 This places them on the far-left / anti-capitalist spectrum, but not in a conventional Marxist sense.


3) Rejection of mainstream left factions (“anti-tankie”)

  • They explicitly say they do not allow “tankie propaganda” (i.e., authoritarian communist ideology). (FOSSDLE)

👉 This suggests alignment with:

  • libertarian-left / anarchist spaces
  • opposition to authoritarian socialism (e.g., Stalinism, Maoism)

4) Extremely unconventional / philosophical layer (“soulism”)

  • Their ideology (“soulism”) mixes:

    • anarchism
    • anti-realism (questioning reality itself)
    • transhumanist / sci-fi ideas
    • spiritual or metaphysical elements (FOSSDLE)

Examples:

  • Viewing natural laws like gravity as unjust hierarchies
  • Treating “money” as a kind of cultural “magic”
  • Emphasizing identity politics and marginalized groups

👉 This is not a standard political ideology—it’s more of a hybrid of:

  • anarchism
  • postmodern / anti-realist philosophy
  • speculative or quasi-spiritual ideas

5) Cultural and social positions

From posts:

  • Strong emphasis on queer, trans, and marginalized identities (FOSSDLE)
  • Belief that “everything is political” (lemmy.world)

👉 This aligns with progressive / radical social politics.


Bottom line

If you had to summarize their political leanings in conventional terms:

  • Far-left (but non-Marxist)
  • Anarchist / anti-authoritarian
  • Anti-capitalist
  • Strongly socially progressive
  • Highly unconventional / fringe philosophical framework (soulism, anti-realism)

They don’t fit neatly into standard categories—they’re closer to an experimental or niche ideological subculture than a recognizable political camp.

load more comments (1 replies)
[–] chicken@lemmy.dbzer0.com 8 points 1 day ago

I would like to see some ROBOT9000 esque oddball meme communities overtly based on heavy algorithmic moderation, can be LLM but wouldn't have to be. Weird rules strictly enforced by robots, could be fun.

[–] webp@mander.xyz 4 points 22 hours ago (3 children)

Nah. So they're basically sending our info/data to some company. Hell nah

[–] Alvaro@lemmy.blahaj.zone 7 points 20 hours ago

Agreed, but also, this is on the open internet, so always assume that all of this data is going to these corporations anyway

[–] Loco_Mex@sh.itjust.works 4 points 19 hours ago (3 children)

You are on PieFed/Lemmy. Anyone can see anything you say, even your private messages are open to viewing by anyone.

[–] webp@mander.xyz 6 points 19 hours ago (1 children)

Yeah, but when the mods intentionally send our data to a company that's kind of next level bullshit. If we come here to escape big tech surely the mods should know better.

load more comments (1 replies)
load more comments (2 replies)
load more comments (1 replies)
load more comments
view more: ‹ prev next ›