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.
AI has been the name for the field since the Dartmouth Workshop in 1956. Early heuristic game AI was AI. Just because something is AI doesn’t mean it is necessarily very “smart”. That’s why it’s commonly been called AI, since before Deep Blue beat Kasparov.
If you want to get technical, you could differentiate between Artificial Narrow Intelligence, AI designed to solve a narrow problem (play checkers, chess, etc.) vs. Artificial General Intelligence, AI designed for “general purpose” problem solving. We can’t build an AGI yet, even a dumb one. There is also the concept of Weak AI or Strong AI.
You are correct though, ChatGPT, Dall-E, etc. are not AGI’s, they aren’t capable of general problem solving. They are much more capable than previous AI technologies, but it’s not SkyNet (yet).
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.
I keep telling people that, but for some, what amount to essentially a simulacra really can pass off as human and no matter how much you try to convince them they won’t listen
I knew the battle was lost when my mother called me to tell me that AI will kill us all. Her proof? A chatgpt log saying that it would exterminate humanity only when she gives the order. Thanks for the genocide, mom.
Orrrrr the term changed with common/casual use the same way as many other words and it’s silly to keep getting pedantic about it or use it as a crutch to feel intillectually superior 🤷♀️
Sure, we could say that the popular usage of the term AI no longer actually stands for “artificial intelligence”. Or we could say that the term “artificial intelligence” is no longer understood to refer to something that can do a large part of what actual intelligence can do.
But then we would need a new word for actual, real intelligence and that seems like a lot of wasted effort. We could just have the words mean what they’ve always meant. There is a lot of good in spreading public awareness of the vast gap between machines that seem as if they understand a language (when actually they just deeply model its patterns) and imaginary machines that are equipped to actually think.
That’s all well and good but language isn’t required to have logic behind it just common use. There’s absolutely nothing any of us can do about it either way because if we disagree we’re already in the minority
it’s not about feeling intellectually superior; words matter. I’ll grant you one thing, it’s definitely “artificial”, but it’s not intelligence!
LLMs are an evolution of Markov Chains. We have known how to create something similar to LLMs for decades, getting close to a century, we just lacked the raw horse power and the literal hundreds of terabytes of data needed to get there. Anyone who knows how markov chains work can figure out how an LLM works.
I’m not downplaying the development needed to get an LLM up and running, yes, it’s harder than just taking the algorithm for a markov chain, but the real evolution is how much computer power we can shove into a small amount of space now.
Calling LLMs AI would be the same as calling a web crawler AI, or a moderation bot, or many similar things.
I recommend you to read about the chinese room experiment