That was my first thought: this is a screenless laptop (more or less). And the only reason laptops aren't smaller is because of a touchpad, battery, and screen.
I absolutely agree, algorithms are terrible for recommendations. On the media database[0] my wife and I are building we're experimenting with community upvotes for suggestions. Our userbase is small so the results are inconclusive right now but hopefully time will tell if this method works.
The only good one I've ever seen was in the music business: Rdio, specifically. (Now sadly dead.) I don't know what they were doing, but their recommendations were consistently excellent at pushing me towards new artists and even new genres that I didn't expect but would up enjoying.
Back when I used to use it (about a decade ago), Pandora was good at shuffling, but their library was so small I would get the same songs over and over.
There's no reason algorithms have to be terrible, after all, most of what we do is expressible algorithmically when we give recommendations (similar interests, right level for the reader, not too advanced or too introductory, something they can use or that leads to other insights, etc.) It's just that the algorithms are generally so bad because they are optimizing for the wrong things and not any of these things that actually make for good recommendations.
My wife and I experienced the same disappointments on goodreads, and many of the same flaws exist in other media rating/cataloging sites. We're attempting to solve this problem by creating a centralized collaborative media database that we always wished existed. Without any marketing yet, https://rate.house currently only has ~100 users, but we'd love to hear HN's input and know if we're heading in the right direction.
I think you've got a really nice design going on already, and basic features seem to work without JS, so that's nice. I also like that you haven't polluted it with ads (I'm far more likely to donate to sites that don't have ads).
Two thoughts:
1. I think I would find a 5 star rating system too constraining. My opinions in most areas have more gradations than just 0-5. 0-100 would be entirely too many. I think IMDB's 10 point scale is really the main reason why I've stuck with that for movies. On the other hand I prefer to only thumbs up / thumbs down books, so I'm really not sure you can do anything about this in a way that would make everyone happy.
2. I think there's either a bug with your weighted average or else you're ranking using something like "we're 90% confident the true rating is at least x". But this confidence level seems entirely too high for the number of users you have on your site. For example Avengers: Endgame appears on #13 on this page: https://rate.house/chart/movie despite the fact that it has a rating of only 3.64. I would probably lower the confidence required for now, and if you 10x or 100x your users you can raise it again.
3. Would be nice to know a bit more about what features it has on the home page before signing up. Can I import my ratings from other sites? Can I export my data in some usable format like CSV? Can the information database the users create for media entries be downloaded by users? (Even IMDB offers this.) Can I get recommendations from the site once I've rated enough items? Can I get music recommendations based on my movie ratings? (That would be cool.)
I know, another zero-width related extension, but it's a bit different.
Cleanse notifies you when a page contains zero-width characters and removes them automatically. You can still trigger the removal manually if there are any content generated dynamically after page load.
Cleanse allows you to replace/remove any string you'd like on all websites. One potential use case is for parents to replace inappropriate words with something else. Another use case is for pranks. It also parses regex.
I've never built an extension before until today so feedback is much appreciated.
https://rate.house/ - like a collaborative IMDb but also has music, books, video games, and podcasts
https://wordhoot.com/ - competitive Wordle
None of them are abandoned but I just don't have the resources to do any marketing.