jeena
@jeena@jemmy.jeena.net
See jeena.net/about
- Comment on Solve a puzzle for me 1 day ago:
Here is my attempt:
A man and a goat are on one side of the river. They have a boat which can carry both of them at the same time. How do they get to the other side?
The man and the goat can both get to the other side of the river together using the boat since the boat can carry both of them at the same time. Here’s how they can do it:
- The man and the goat both get into the boat.
- The man rows the boat, carrying himself and the goat across the river.
- They both disembark on the other side.
Since the boat can carry both the man and the goat simultaneously, there are no restrictions preventing them from crossing together in one trip.
- Comment on Bytom, Poland 1 day ago:
Damn, ale sie poli.
- Comment on bugs 6 days ago:
You wouldn’t say that if you ever tried those tomatoes …joins.com/…/20210117130800678.html
I’d even call them candy.
- Comment on How do passkeys work across devices? 1 week ago:
I’ve used it on a iPhome once with a Syncthing alternative client and some alternative Keepass app. It worked very well but it was only for a month or two and I don’t change passwords often so I might not realized that syncing doesn’t work well.
- Comment on How do passkeys work across devices? 1 week ago:
I would suggest to move to KeepassXC, which already shown that even when KeepassX was too slow to implement features the community was healthy enough to fork it and make it the main fork.
- Comment on Clenching fists 2 weeks ago:
Can someone explain if there is a joke here?
- Comment on A photography depicting the construction of the Great Pyramid of Giza - 2565 BCE. 2 weeks ago:
Amen 🙏.
- Comment on What do you personally use AI for? 2 weeks ago:
Oh yeah, I found out the hard way and forgot to mention it here. jeena.net/llama3-phoning-home
- Comment on What do you personally use AI for? 2 weeks 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:
- 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.
- Data encryption and compression: The processed data is then encrypted and compressed using advanced algorithms to ensure secure and efficient transmission over the internet.
- Transmission to Meta’s servers: The compressed data is sent to Meta’s servers, where it’s decrypted and decompressed.
- 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.
- 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!
- Comment on What do you personally use AI for? 3 weeks ago:
Correct.
- Comment on What do you personally use AI for? 3 weeks ago:
Check out llama3 which you can run locally.
- Comment on What do you personally use AI for? 3 weeks ago:
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. Played $5 for the stamp instead $70 for the translation.
- Submitted 3 weeks ago to technology@beehaw.org | 95 comments
- Comment on Google fires 28 workers for protesting $1.2 billion Israel contract 3 weeks ago:
What did they think would happen? Google removed “don’t be evil” a long time ago.
- Comment on Is there a more politically and ideologically diverse alternative for Lemmy? 4 weeks ago:
I see, that En I misunderstood that and OP might have a point?
- Comment on Is there a more politically and ideologically diverse alternative for Lemmy? 4 weeks ago:
Because they are literal Nazis.
- Comment on Is there a more politically and ideologically diverse alternative for Lemmy? 4 weeks ago:
I thought we have quite a diversity here with extreme right wing on hexbear, extreme left wing on lemmygrad, center with lemmy.world, (clasic) liberalism on dbzer0, and everything between like blahaj, beehaw, redhat, slrpnk, etc.
- Comment on i'm DT(DTF) 4 weeks ago:
I guess it’s a screen on which you can watch yourself filmed by the camera behind you?
- Comment on Howdo LLMs like ChatGPT work?Explained by Deep-Fake Ryan Gosling using Synclabs and Eleven Labs 4 weeks ago:
It has limitations, sure, but I got blocked and was in ironically interested. The topic has been explained well on a high level.
- Howdo LLMs like ChatGPT work?Explained by Deep-Fake Ryan Gosling using Synclabs and Eleven Labsyoutu.be ↗Submitted 4 weeks ago to technology@beehaw.org | 5 comments
- Comment on I can see why the laundry used to be a entire day job before washing machines. 4 weeks ago:
- Comment on Ubisoft Is Taking Away Your Games... 4 weeks ago:
“You wouldn’t delete someone elses game from their library!”
- Comment on Face / Off? 4 weeks ago:
I like Cage better tham Manson, so I was dissapointed once I read the title.
- Comment on Discord is nuking Nintendo Switch emulator devs and their entire servers 4 weeks ago:
Especially Open Source stuff.
- Comment on Sorry lemmy but I have to ask? 5 weeks ago:
I followed this github.com/libre-tube/LibreTube/discussions/2351
- Comment on Complete this sentence 5 weeks ago:
… not complete this sente
- Submitted 5 weeks ago to [deleted] | 111 comments
- Comment on I'm working on it, ok? 1 month ago:
In my life it was either I could not save anything or I could save a lot, the expenses are basically the same but the income changed. Once the income was higher than the expenses the saving happened automatically and are steadily growing over time.
- Comment on Crazy how nature be like that 1 month ago:
Aaah, thanks!
- Comment on Crazy how nature be like that 1 month ago:
Can someone explain the joke?