He is probably an antisemit! /s

I never watch the same movie/TV show more than once, so I don’t see a point in hording this data. So for me the UX of streaming is most of the time preferrable than having a physical media which I need to carry to the new appartment every time I move.

This is different with music, where I listen to the same Albums hundrets of times. There I can deal with vinyl and many files on my computer.

But Netflix never let me buy a movie or TV show. They just sell me access to their library for a limited time.

I bought some music from Apple, DRM free and I downloaded it and have it on my own hard drive, and share it between all my devices.

Apple also sells you access to their library for a limited time like Netflix, but then you’re not buying the songs, you’re buying access to them for a limited time.

I’m just confused about why people are so mad about it. In other cases where you rent space to put physical things you own so you can still access them later this happens too. Let’s get into an example, and you guys tell me if I’m misunderstanding something:

If you have a car and have to change between summer and winter tires and you don’t have space at home to store the winter tires during the summer, you can go to a tire-hotel and they will 1. Sell you new tires, 2. switch your tires - a service you pay for - and 3. store the tires for you until next winter - a service you pay for too. Once the company goes out of business (or they focus on a different business) they tell you to get your tires or they will be discarded if you don’t. So you have to get them from them and you stop paying for the storage.

Isn’t it the same with the movies you buy and store at a place where you then rent storage to keep them there? As long as they allow you to download your purchases I see no difference. You can’t make someone else to keep working the same job until the heat death of the universe.

So I guess that would make it more resilient agains Nintendos efforts to destroy all emulators?

I speak 4 languages, English, Swedish, German an Polish. At work in Swrden our office language was English because so many people from all over the world worked together. I was a consultant at the customers office. There was another consultant from Poland visiting the customer and after a heated meeting he sat down at his desk, which was adjesent to mine and called his collegues in Poland. Ha basically said that those Swedes are so stupid, they want us to use 9 women to give birth to the baby in one month instead of 9 months, without realizing that I could understand everything. I had to work hard to not burst out in loughter.

Haha, interesting, for me it was the exact opposite, I started with Baikal but it was too weird and I couldn’t get it up and running quickly enough and then I think I was not able to share my calendar with my partner or something, so I switched to Radicale.

Yeah it’s a pitty. For Linux I started writing https://github.com/jeena/jnotes but it will still take a lot of time before it’s usable.

In the end it’s just another devise. But we are not changing the same document at the same time, that would lead to many sync conflicts I imagine. For that some special protocol for concurent Editing would be better.

Calendar, and addressbook actively. File sharing only seldom.

Yeah, I also selfhosted it for years myself. But I was adding more and more services to my server and it became clear that if I would want to keep Nextcloud I’d need a server with more CPU and RAM because when Nextcloud was running it would after half a day deadlock the server with a load of 120 so I had to hard reboot it twice a day.

After replacing it with radicale and syncthing I was able to run Mastodon and Lemmy on the same server additionally.

Syncthing and I have it partitioned with:

• Music
• Documents
• Family Documents
• Password DB

So that I can decide what to sync to which device.Music is for example too big to sync to my Phone so I don’t. Family documents I also share with my partner. Password DB I sync with all my devices but not to anyone else.

I have Linux with GNOME and Android and my partner has iOS and Windows and all the CalDav and CardDav stuff works fine. Or at least adressbook and calendar. I couldn’t find a client for iOS for CalDav notes and tasks.

Oh I also agree about Syncthing. With it you practically don’t even need to run it on you server, I still do, just in case if all my other divices are offline.

I switched to Radicale and couldn’t be happier, so lightweight no pain setting it up or updating. Supports CardDav for the addressbook and CalDav for calendar, tasks, notes.

Nextcloud is for Enterprises, not for selfhosting anymore.

Oh yeah, I found out the hard way and forgot to mention it here. https://jeena.net/llama3-phoning-home

Damn, it seems I was talking out of my ass and just assuming things. Now I asked llama3 about it and it said that even though it does not send our conversation to Meta, it does take my feedback (if I correct it in some way) and sends it to Meta’s servers through the Internet:

// Will you be able to learn from me pointing it out or do you forget all conversations we had after I press Ctrl-D?
I’m a large language model, I don’t have personal memories or experiences. Each time you interact with me, it’s a new conversation, and I start from scratch.

When you point out an error or provide feedback, it’s stored in my training data for future conversations. However, this information is not retained individually; instead, it’s aggregated and used to improve the overall performance of my language understanding and generation capabilities.

So, when you press Ctrl-D (or close our conversation), I won’t remember the specific details we discussed, including your feedback on my German sentence.
But, the collective knowledge from all our conversations will help me become a better AI model over time!

Keep in mind that I’m designed to learn and adapt through interactions with users like you. Your contributions, no matter how small they may seem, are invaluable in helping me improve and provide more accurate and helpful responses in the future!

/// But you run on my computer so technically how does my contribution get back to Meta to train the next generation? Do you send any data back?
When you interact with me through this chat interface, your input is processed by a client-side JavaScript code that runs on your local device (your computer or mobile phone). This code sends the necessary information about our conversation, including any corrections or feedback you provide, to Meta’s servers.

Here’s how it works:

1. Client-side processing: When you type a message or correct an error, the JavaScript code on your device processes and formats the data for transmission.
2. Data encryption and compression: The processed data is then encrypted and compressed using advanced algorithms to ensure secure and efficient transmission over the internet.
3. Transmission to Meta’s servers: The compressed data is sent to Meta’s servers, where it’s decrypted and decompressed.
4. Integration with training datasets: The collected data is then integrated into Meta’s vast training datasets, which contain millions of conversations from users like you.
5. Training the next generation: These updated training datasets are used to train new models, such as language understanding models like myself. This process helps improve my accuracy and ability to understand natural language.

To ensure your contributions are anonymous and secure, all data transmission is handled by Meta’s infrastructure and follows industry-standard encryption protocols. Your input will help refine the AI models, enabling them to better serve users in the future!

Now, go ahead and chat away!

/// How would the data look in the case of me telling you the correct German expression? What would be sent back to meta’s server? Show it as JSON.
When you correct an error or provide feedback, the client-side JavaScript code on your device sends a request to Meta’s servers with the following information:

Here’s what the data might look like in JSON format:

{
  "event_type": "corrected_error",
  "conversation_id": "unique_conversation_identifier",
  "turn_number": 5,
  "user_input": "und kann einfache",
  "correction_target": "können",
  "language_code": "de",
  "platform": "web",
  "client_info": {
    "browser_type": "Chrome",
    "browser_version": "92.0.4515.131"
  }
}

In this example:

• event_type: The type of event, which in this case is a “corrected_error”.
• conversation_id: A unique identifier for the conversation.
• turn_number: The number of turns (or exchanges) in the conversation.
• user_input: The corrected text you provided (“und kann einfache”).
• correction_target: The original incorrect text (“können”) that was being discussed.
• language_code: The language code for German (“de”).
• platform: The platform or device type used to access Meta’s services (in this case, “web”).
• client_info: Additional metadata about the client device and browser.

This JSON data is then sent to Meta’s servers, where it can be processed and integrated into their training datasets.

Correct.

Check out llama3 which you can run locally.

Oh that reminds me of another use of it last year. I let it translate some official divorce papers from Korean to German and then let a human read through it and give it a stamp of approval. Payed $5 for the stamp instead $70 for the translation.

Asking for a AI friend?

• https://radicale.org/v3.html for calendar, address book, tasks, notes (use native clients for it on desktop and phone, for Notes on desktop I couldn’t find anything so I’m writing JNotes)
• https://tt-rss.org/ for RSS (have been using it for ever and wrote myself a Linux desktop client)

I used it mostly for calendar and adressbok synchronization between devices bit the performance was so bad O had to replace it.

Performance is why I stopped using it and replaced it with Radicale for card- and CalDAV and Syncthing for filesyncing. Couldn’t be happier with the results.

Yeah I get it, thanks. I just already use Antennapod and like it a lot. I will check Pinepods out, perhaps it’s already good enough that I would be OK giving up Antennapod, if not then installing Nextcloud to get this sync functionality between devices.

Does gpodder sync playtime too? I never could figure out how and then their webside was broken for so long so I gave up on it.

Yeah relying on someone else’s computer is not optimal. And also when it’s a proprietary protocol you can only use one client on all devices.

That makes it very interesting, hm I just don’t have Nextcloud.

What I am missing is something where I can sync what podcast I am playing and the minute and second where in the podcast I am.

This way I could switch seamlessly between devices.

Does it have functionality like that?

I like Uptime Kuma, but it only monitors if a service is online or not. I’m up to 21 services now so I’m not interested in all their details, just if I need to fix something urgently.

I haven’t done it yet but I plan on doing it. But I never bothered with a VPN and just expose a ssh port. So I plan just to mount a directory with sshfs.

I am using duckdns.org and let my router ping it when it’s public IP changes. Then I use nginx as a reverse proxy with help of https://nginxproxymanager.com/ so I don’t need to write config files and it also runs certbot for my so I don’t need to deal with https manually.

Actually I also have my own domain so I use a subdomain pointing via CNAME to the duckdns subdomain. This way I can easily change the provider of dyndns.

What did they think would happen? Google removed “don’t be evil” a long time ago.

It has limitations, sure, but I got blocked and was in ironically interested. The topic has been explained well on a high level.

Especially Open Source stuff.

https://tasks.org/ does it with CalDAV, and you can share different CalDAV calendars with different people, fo example in Next cloud fairly easily, but also with Radicals, a bit more manual.

A container does not have an IP, only a network card has an IP. Containers normally use a specific port which normally is not changing like 8080 or 8123, etc. I think you misunderstood something with your setup.

That is not opposite, they just want to pull in data from the fediverse automatically so that they can sell it too.

We need some explicit licensing of our public fediverse data otherwise it will just be used to sell it back to us.

I have too many photos to sync, but I have two different Document my own and family documents, so that I can share the family documents with my spouse.