this post was submitted on 06 Oct 2023
2946 points (98.2% liked)

Piracy: źœ±į“€ÉŖŹŸ į“›Źœį“‡ ŹœÉŖÉ¢Źœ źœ±į“‡į“€źœ±

54577 readers
205 users here now

āš“ Dedicated to the discussion of digital piracy, including ethical problems and legal advancements.

Rules ā€¢ Full Version

1. Posts must be related to the discussion of digital piracy

2. Don't request invites, trade, sell, or self-promote

3. Don't request or link to specific pirated titles, including DMs

4. Don't submit low-quality posts, be entitled, or harass others



Loot, Pillage, & Plunder

šŸ“œ c/Piracy Wiki (Community Edition):


šŸ’° Please help cover server costs.

Ko-Fi Liberapay
Ko-fi Liberapay

founded 1 year ago
MODERATORS
 

Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:

Iā€™m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. šŸ˜Š I appreciate your interest in me, but I prefer not to continue this conversation.

Aaaand I got blocked

you are viewing a single comment's thread
view the rest of the comments
[ā€“] [email protected] 2 points 1 year ago (8 children)

I can disprove what you're saying with four words: "The Chinese Room Experiment".

Imagine a room where someone who doesn't understand Chinese receives questions in Chinese and consults a rule book to send back answers in Chinese. To an outside observer, it looks like the room understands Chinese, but it doesn't; it's just following rules.

Similarly, advanced language models can answer complex questions or write code, but that doesn't mean they truly understand or possess rationality. They're essentially high-level "rule-followers," lacking the conscious awareness that humans have. So, even if these models perform tasks and can fool humans to make them believe they're intelligent, it's not a valid indicator of genuine intelligence.

[ā€“] [email protected] 6 points 1 year ago (2 children)

That argument is no argument since we humans, no matter how advanced our language is, still follow rules. Without rules in language, we would not understand what the other person were saying. Granted, we learn these rules through listening, repeating and using what sounds right. But the exact same thing is happening with LLMs. They learn from the data we feed them. It's not like we give them the rules to english and they can only understand english then. The first time they come into contact with the concept of grammar is when they get data, most often in english, that tells them about grammar. We all follow rules. That's exactly how we work. We're still a lot smarter than LLMs though, so it might seem as if they are vastly inferior. And while I do believe that most complex organisms do have "deeper thought" in that our thought has more layers and is generally fitter for the real world, there is no way I'm not gonna call a neural network that can answer me complex questions, which may have never been asked in the history of mankind, an AI. Because it is very much intelligent. It's just not alive. We humans tend to think of ourselves too favorably. "We" are just a neural network. Just a different kind. Just like a computer is similar to the human brain, but a wire is not. Where do you draw the line?

[ā€“] [email protected] 0 points 1 year ago (1 children)

In the thought experiment, the guy in the Chinese room is following exactly the same kind of rules.

[ā€“] [email protected] 2 points 1 year ago
load more comments (5 replies)