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:
I’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. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
I mean... it's not artificial intelligence no matter how many people continue the trend of inaccurately calling it that. It's a large language model. It has the ability to write things that look disturbingly close, even sometimes indistinguishable, to actual human writing. There's no good reason to mistake that for actual intelligence or rationality.
It seems to me that you misunderstand what artificial intelligence means. AI doesn't necessitate thought or sentience. If a computer can perform a complex task that is indistinguishable from the work of a human, it will be considered intelligent.
You may consider the classic turing test, which doesn't question why a computer program answers the way it does, only that it is indiscernable from a human response.
You may also consider this quote from John McCarthy on the topic:
There's more on this topic by IBM here.
You may also consider a few extra definitions:
Yep, all those definitions are correct and corroborate what the user above said. An LLM does not learn like an animal learns. They aren't intelligent. They only reproduce patterns similar to human speech. These aren't the same thing. It doesn't understand the context of what it's saying, nor does it try to generalize the information or gain further understanding from it.
It may pass the Turing test, but that's neither a necessary nor sufficient condition for intelligence. It is just a useful metric.
LLMs are expert systems, who's expertise is making believable and coherent sentences. They can "learn" to be better at their expert task, but they cannot generalise into other tasks.
LLMs are no more ai than the enemies in doom were.
The enemies in Doom actually do some pretty dumb things, like letting you force them to stop moving.
What if humans are also just LLMs when they start talking
In a way I agree, it's not human level intelligence but in another way people are also using the term AI to refer to the intelligence of NPCs in video games or for the algorithm that's used for Voice to text or for how a Roomba works and ChatGPT/bing is more intelligent than them. And thing is, I think we need a term for this simpler type of intelligence and since it is some level of intelligence which is artificial, I think AI is fine and Artificial General Intelligence can be used for what you're talking about
we should've have called those things AI either but when it's a cacaodemon in the early 1990s it's more obvious to everyone that the computer isn't actually thinking
We did call those things AI back when they were being developed. It's just that advancements in AI that become immediately useful tend to get a different name.
there was no ambiguity between a tree and AGI like the marketing pukes are pushing today
I could go with that.
Still having a hard time with the idea that a thing could be even "some level of intelligent" without being sentient. But we don't need to continue from there, there's any number of people ready to pile on at that point and say that it's "all semantics anyway" or start deconstructing sentience.