• 1 Post
  • 17 Comments
Joined 11 months ago
cake
Cake day: January 3rd, 2026

help-circle










  • People don’t like to admit it, but jellyfin doesn’t have feature parity yet. I think they could solve a lot of the issues if they went the federation route, but until then, it’s just easier for my family and friends to each have 1 plex account instead of N jellyfin accounts. Not to mention the jellyfin vulnerabilities that prevent me from considering hosting it openly

    Could you maybe elaborate on the feature parity? What is missing? I also don’t get the info about N jellyfin accounts, as in separate jellyfin account per each different jellyfin server?

    Why would you host it openly rather than in a VPN like Tailscale or whatever wire guard is?




  • Huh? That is the literal opposite of what I said. Like, diametrically opposite.

    The system summarizes and hashes docs. The model can only answer from those summaries in that mode. There’s no semantic retrieval step.

    No, that’s exactly what you wrote.

    Now, with this change

    SUMM -> human reviews

    That would be fixed, but will work only for small KBs, as otherwise the summary would be exhaustive.

    Case in point: assume a Person model with 3-7 facts per Person. Assume small 3000 size set of Persons. How would the SUMM of work? Do you expect a human to verify that SUMM? How are you going to converse with your system to get the data from that KB Person set? Because to me that sounds like case C, only works for small KBs.

    Again: the proposition is not “the model will never hallucinate.”. It’s “it can’t silently propagate hallucinations without a human explicitly allowing it to, and when it does, you trace it back to source version”.

    Fair. Except that you are still left with the original problem of you don’t know WHEN the information is incorrect if you missed it at SUMM time.