

conceal
I think you might’ve made a typo here, did you mean concede?
Yes, you give up if you want to talk to them. What else csn you do. Ten year campaign to switch everyone?


conceal
I think you might’ve made a typo here, did you mean concede?
Yes, you give up if you want to talk to them. What else csn you do. Ten year campaign to switch everyone?
Thank you very much!
Posts here are to be centered around self-hosting. Please ensure it is clear in your post how it relates to self-hosting.
Does that mean my post where I ask for hardware storage options for my selfhosted Jellyfin will be unremoved?


2TB, but I’m also new to this. I am literally running ffmpeg on some of the shows to compress them a little or dropping unnecessary audio streams


Whoopps, my bad, I read it as Google Keyboard. I can blame not having my first coffee for the brain fog.


I need to try different keyboards as I’m not loving the GOS one
Considering it sends anything and everything to Google servers then yes, you should.
Ignore it I read the name wrong
There is no requirement to use it though. So blame the manufacturers if it’s hard to disable it.


Thanks
but it does have a second M.2 port.
As in - open and stick the ssd inside? I believe I already have both slots taken, got the model with extra storage.


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?


As in you set it up outside your home server for only that? What’s the hard drive capacity there? Can you share a link to this offer?


How would that help? Bots will just move to another instance. Maybe yours.
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.
The system summarizes and hashes docs. The model can only answer from those summaries in that mode
Oh boy. So hallucination will occur here, and all further retrievals will be deterministically poisoned?
So… Rag with extra steps and rag summarization? What about facts that are not rag retrieval?
A very tailored to llms strengths benchmark calls you a liar.
https://artificialanalysis.ai/articles/gemini-3-flash-everything-you-need-to-know (A month ago the hallucination rate was ~50-70%)
I want to believe you, but that would mean you solved hallucination.
Either:
A) you’re lying
B) you’re wrong
C) KB is very small
I have NOT heard of a company whose productivity increased dramatically though (but the quality goes down, I wonder why).
There are startups that are getting PoCs faster, but thats about it.