See https://jeena.net/about

  • 16 Posts
  • 217 Comments
Joined 1 year ago
Cake day: June 14th, 2023
  • Jeena@jemmy.jeena.nettoSelfhosted@lemmy.world•‘My whole library is wiped out’: what it means to own movies and TV in the age of streaming servicesEnglish
    38·
    6 months ago

    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.

  • Jeena@jemmy.jeena.nettoSelfhosted@lemmy.world•Is Radicale the way forward?English
    51·
    7 months ago

    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.

  • Jeena@jemmy.jeena.netOPtoTechnology@beehaw.org•What do you personally use AI for?
    1·
    7 months ago

    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.