No Stupid Questions

I think the only way is to be less popular and to keep moving. People that run bots are like bullies, and are either crazed zealots that eventually will run out of motivation, or already have limited motivation and you have to make it harder for them until they stop caring. In which case, they basically just become an actual user.

Now the trick is how to string along your users in the same way that doesn't turn them away.

Offer something juicy to people who care, but foul to those who don't.

Or just have better human moderation, like what Ada said. Treat your instance like a community and a team, watch over them and get rid of the bots, and then block instances that do a bad job at that. Isn't that basically the fediverse way, already? Because there will always be spam and bad actors and dissent. Only through the strengths of humanity can we beat the bots.

Combine these two arms, and they would be pretty solid. I leave the more rock hard, third arm solution to somebody much smarter than me, but welcome it gratefully and happily if and when it comes.

• ramblings of somebody just waking up

Text wise, there is no way to tell anymore unless the bot fucks up, which happens rarely.

Image wise, I doubt someone has an automatic pipeline where a bot generates pictures on it's own and posts them. What you are seeing are real people using AI to make their memes, or people who are enthusiastic about AI reposting pictures they find. Nothing wrong with that.

There's also posting bots, which should be labeled as such but I guess most people don't. It's just a way to bring content in, I don't really see a problem with this.

And there's vote manipulation obviously.

All that to say that the first and last one are the only problematic ones since it's used to manipulate and sway opinions. But there isn't anything we can do if someone is mildly smart about it and uses a proxy service. Llms are simply too good at making themselves look like regular commenters.

We could ask for ID from every user and cross reference with the help of governments to make sure it's a real one, or have heavy and intense captchas, but who wants to do that?

You can reduce bot noise on the Fediverse through a mix of server settings, moderation tools, and user-side filtering. Since it is decentralized, no one can stop bots everywhere, but individual servers and clients can limit how much spam actually reaches people.

Server admins can require email verification or CAPTCHAs at signup, use manual account approval for new users, limit posting speed for new accounts, and block or silence servers that are known sources of spam. Many Fediverse servers already share blocklists and coordinate moderation so that problem servers get isolated quickly.

Fediverse software is also adding better tools for detecting automated accounts, labeling bots, filtering low-quality AI images, and helping moderators review suspicious posting patterns. Some servers use anti-spam plugins or machine-learning filters to automatically flag or quarantine obvious bot posts. Individual users can mute keywords, block accounts, report spam to their server admins, or switch to a Following-only timeline to avoid noise from the wider network.

Bot spam will never be fully eliminated, but stronger moderation tools, shared blocklists, and user controls make it possible to keep timelines clean without centralizing the network.

Keep normies away from Fediverse. Easiest way. Bad shit follows popularity.

but now I am starting to see it myself, blatant bots posting really crappy AI images

There's one account that mods a shit ton.of AI image communities...

If you block that one account, it will.pretty much fix all of it. They're super weird and going off memory they mod an insane number of communities for AI images, so I wouldn't worry about pre-emptively blocking everyone, because it's just the one account posting most of it.

But as you see posts block the community.

It ain't that difficult.

But there's entire instances that the admins have lost it to AI brainrot already. That's where the communities are usually hosted and no amount of facts, logic, or even opinions and feelings will get those admins to "do something" about it.

The fediverse isn't centralized, you'll never "get rid of" any subject or topic. Because even if the big instances do, anyone can make a new one.

"Fighting" the people who's brains have been rotted by AI will never be productive and most likely drives them further into AI

Not sure why it still needs repeated so much, but:

Don't feed the trolls

Block them and move on.