Kuvwert

Thats a cool project as well! I dont think there's very much overlap in functionality between the two

Here's the rundown from the repo:

Proposed Project Features:

Books (Readarr & Anna’s Archive)

✅ Missing List → Read from Readarr, fetch missing books and auto-download via Anna’s Archive ✅ Manual Search → Search Anna’s Archive and download books (user selection and defined file structure) ✅ Recommendations → Generate book suggestions based on Readarr library (using a background tasks to scrape from Goodreads) - with options to add or dismiss suggestions including filters and sorting

Movies (Radarr & TMDB)

✅ Recommendations → Read Radarr library and suggest similar movies via TMDB (with options to add or dismiss suggestions including filters and sorting) ✅ Manual Search → Search via TMDB with option to add to Radarr

TV Shows (Sonarr & TMDB)

✅ Recommendations → Read Sonarr library and suggest similar shows via TMDB (with options to add or dismiss suggestions including filters and sorting) ✅ Manual Search → Search via TMDB with option to add to Sonarr

Music (Lidarr, LastFM, yt-dlp, Spotify)

✅ Manual Search → Search Spotify for music and download via spotDL (which uses yt-dlp) ✅ Recommendations → Generate artist recommendations from LastFM based on Lidarr library (with options to add or dismiss suggestions including filters and sorting) ✅ Missing List → Read Lidarr library, fetch missing albums and download via yt-dlp

Downloads (via yt-dlp)

✅ Direct Download Page → Input YouTube or Spotify link and download video/audio using spotDL or yt-dlp

Subscriptions (via spotdl and yt-dlp)

✅ Schedule System → Subscribe to YouTube Channels, Spotify or YouTube Playlists and download on a schedule

Woah nice heads up I appreciate it!

I'll keep the janitor tool in my pocket for now as my instance takes up negligible space at the moment but someday that might not be the case.

Here's the referenced tool for anybody else interested:

https://git.cyberia.club/cyberia/matrix-synapse-diskspace-janitor

What are you using instead? I only recently set up my synapse server and I'd be interested to head what the alternatives are

Ah this is so exciting!

Discord 'existing' has held back development motivation on Foss Federated Communication alternatives.

When they go public only good things will happen for projects like matrix :)

I'm very excited!

They use cloudflare r2 and cf pages

Neat!

What's your pillow brand?

Anybody got a link to a codeberg fork that looks reliable ?

I wanna hear them get SLAMMED

Yes they have a stealth feature that is helpful for detecting a VPN

Here's what my local ai said about your supposition:

Your supposition about LLMs is actually quite close to the basic concept! Let me audit this for you:

You've correctly identified that LLMs work on statistical patterns in text, looking at what words are likely to follow a given sequence. The core idea you've described - that models can learn patterns without storing every example verbatim - is indeed fundamental to how they work.

Your example of "a b c d" appearing 12 times and the model learning that "d" follows "a b c" is a simplified but accurate illustration of the pattern recognition that happens in these models.

The main difference is that modern LLMs like myself use neural networks to encode these patterns in a complex web of weighted connections rather than just simple frequency counts. We learn to represent words and concepts in high-dimensional spaces where similar things are close together.

This representation allows us to make predictions even for sequences we've never seen before, based on similarities to patterns we have encountered. That's why I can understand and respond to novel questions and statements.

Your intuition about the statistical foundation is spot on, even if you're not familiar with the technical details!