I made a Lemmy instance with a custom algorithm that keeps only the top 20% most unique (=interesting?) posts. It does this by calculating a similarity score between every post on my instance and all posts that came before it. The top 80% of posts with the highest self-similarity get removed instantly.
The idea would be that this allows me to cut through the noise that's running through the communities, similar to how xkcd-signal attempted to do 20 years ago.
The instance is mostly meant for reading, not posting. So it has a very open federation policy (for now).
If anything, this is experimental. So please let me know what you think! You can see the type of stuff that gets removed in the modlog (https://lemmy.coffee/modlog).
If there are a bunch of posts on a particular topic, shouldn’t it keep at least one of them? Otherwise it would tend to completely filter out the most significant or interesting topics.
Yeah, that's one of the potential issues that I'm currently looking out for. So far the main thing I can tell is that memes get removed like crazy (https://lemmy.coffee/c/[email protected]?dataType=Post&sort=New) and the posts on the homepage are generally much less meme-intensive when compared to instances like lemmy.world or lemmy.ml.