There are several reasons why I don’t want a physical CD:

I have no space for it

I don’t want to carry it when I move

It’s a lot of work to sell it

I need to pay shipment around the world to Korea

The production and shipment creates unnecessary CO2, so it’s even bad for the environment

That’s actually a great idea!

Thanks everyone for offering the albums to me. I looked around and I seem to be able to download them from YouTube too.

I was genuenly trying to find something like Bandcamp which would have more bands, because the next one is Paramore which I’d like to get their latest album. I at least hope that some of the money would go to the artists to make more music in the future.

He actually reminds me of Gmork from The Never Ending Story.

I remember I had to close my eyes in the cinema several times during the movie, it was just too scary for a 8 years old me.

We are approaching the use of AI in Firefox — which many, many of you have been asking about

Which one of you was it, who asked for AI in Firefox???

That inspired me to try it too, and it’s really cool! In just 2 hours I got my player running around, jumping, etc. I didn’t expect it would be quite so easy:

I have the assets from a previous attempt to write it in JavaScript from scratch https://chuck-game.tumblr.com/about which failed because of something in the physics engine crashing the whole browser for the players.

I’d like to replace GitHub with something self hosted but I’d still like other people to be able to fork and especially do pull requests. Because everyone already has a GitHub account it’s easy for them to do that. I wish there was some small software which would be easy to install and update and it would be connected to for example ActivityPub to be able to do pull requests. I’m not so keen on making everyone who wants to create a Issue or a Pull Request to make a seperate account on my own website, nobody will do that.

It’s so good that they make sure we can’t harm ourselves.

😢

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.

I guess it’s the year of the Linux desktop!

That is what everyone has been waiting and longing for!

I wonder how they decide what ads to put there

I did for many years. But then I moved to Korea and they don’t allow family plans and paying 4 individual ones is just not in our budget. Then probably just no YouTube for me.

Damn, I got my setup so perfect on the TV with SmartTube. But I will not be able to tolerate ads. Then I’d rather only watch on Firefox with uBlock on my laptop.

I was really dissatisfied that notes are always somehow weirdly shared with a propriatary backend. There is jtx Board which uses your CalDAV calendar (Nextcloud, Radicale, etc.) as a backend which is really cool. The UI is also OK, but there seems to be no (Linux) desktop app for that.

So I started https://github.com/jeena/JNotes because I was curious about developing for GNOME anyway. It’s going very slowly - because I am a stay at home dad with a one year old who demands all my attention :D - but it’s going forward, but I guess it’ll take another year before it’s usable ^^.

Actually I was hoping that there would be more notes apps using standard backends like CalDAV or IMAP, but it’s almost impossible to find something, everyone seems to want to implement their own backend and then charge for the synchronization.

I had to look up on the map where El Salvador is.

Or someone who wanted people to point fingers at someone specific.

For me it’s definitely attractive that it’s written in plain python without much JavaScript stuff, etc. it also seems to load much faster than even my tiny Lemmy instance.