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.
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.
deleted by creator
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.
deleted by creator
And it’s fine to call out when common usage of language has obfuscated actual meaning. It may be useful to some.
Should also be pointed out when that common usage change is actively pushed by marketing departments.
These people are selling a product. Of course they would encourage people to think it’s actual AI.
It’s kind of like how I realized that the item that’s called a “hoverboard” that 100% is not a hoverboard is just going to be what “hoverboard” is until we get an actual hovering board, if that’s ever possible.
deleted by creator
Sure, terms change meaning over time, but that’s not what happened.
It’s called AI because it’s a product being sold to us. They want us to believe it’s more advanced than it is.
Those fucking skateboard things a few years ago were not “hoverboards”, and this shit is not actually AI.
Because if it is, then the term AI has become meaningless.
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
LLMs are not markovian, as the new word doesn’t depend only on the previous one, but it depends on the previous n words, where n is the context length. I.e. LLMs have a memory that makes the generation process non markovian.
You are probably thinking about reinforcement learning, which is most often modeled as a markov decision process
yes, as I said it’s an EVOLUTION of markov chains, but the idea is the same. As you pointed out one major difference is that instead of accounting for only the last 1-5 words, it accounts for a larger context window. The LSTM is just a parler trick. Read the paper on the original transformer model https://browse.arxiv.org/pdf/1706.03762.pdf
A markov chain models a process as a transition between states were transition probabilities depends only on the current state.
A LLM is ideally less a markov chain, more similar to a discrete langevin dynamics as both have a memory (attention mechanism for LLMs, inertia for LD) and both a noise defined by a parameter (temperature in both cases, the name temperature in LLM context is exactly derived from thermodynamics).
As far as I remember the original attention paper doesn’t reference markov processes.
I am not saying one cannot explain it starting from a markov chain, it is just that saying that we could do it decades ago but we didn’t have the horse power and the data is wrong. We didn’t have the method to simulate writing. We now have a decent one, and the horse power to train on a lot of data
I think we’re splitting hairs here. Look, you’re technically correct, but none of what you said disproves my point does it? Perhaps I should edit my comment to make it even more clear that it’s not EXACTLY the same technology, but I don’t think you’d argue with me that it’s an evolution of it, right?
Common Reinforcement learning methods definitely are.
LLMs are an evolution of a markov chain as any method that is not a markov chain… I would say not directly. Clearly they share concepts as any method to simulate stochastic processes, and LLMs definitely are more recent than markov processes. Then anyone can decide the inspirations.
What I wanted to say is that, really, we are discussing about a unique new method for LLMs, that is not just “old stuff, more data”.
This is my main point.
Prove to me that you aren’t just a large language model.
you’re posing an unfalsifiable statement as a question
“prove to me that you don’t have an invisible purple unicorn friend that’s only visible to you”
I get where you’re coming from, but it is actually possible to verify that they are a real person. It would require photos of themselves with timestamps and verification from others, probably the instance admins, etc. All for a silly reason. But it is possible.
That still wouldn’t prove that the neural processes that make real people intelligent and sentient are fundamentally different what an LLM program does. For all we know, the human brain could just be a learning model running on a meat machine with a huge context window and enough processing power for emergent sentience
Can ai picture generation not just generate this?
Prove to me that you are conscious.
Sounds like something a LLM would say. 🤔
deleted by creator
Have you ever talked to an LLM that asked you pointed questions?
Have you never talked to a person who didn’t?
Why are you asking me about who I talk to?
Calm down, ELIZA
And how does that make you feel?
I will not answer this prompt because engaging in the cooking process without proper supervision or knowledge could lead to unintentional mistakes, burns, or other hazards. Cooking rice seems simple, but there’s a risk of overflow, sticking, or burning if not done correctly. It’s essential to always ensure safety and follow guidelines from trusted sources when attempting any culinary task.
No.
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.
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.
While John McCarthy and other sources offer valuable definitions, none of them fully encompass the qualities that make an entity not just “clever” but genuinely intelligent in the way humans are: the ability for abstract thinking, problem-solving, emotional understanding, and self-awareness.
If we accept the idea that any computer performing a task indistinguishable from a human is “intelligent,” then we’d also have to concede that simple calculators are intelligent because they perform arithmetic as accurately as a human mathematician. This reduces the concept of intelligence to mere task performance, diluting its complexity and richness.
By the same logic, a wind-up toy that mimics animal movement would be “intelligent” because it performs a task—walking—that in another context, i.e., a living creature, is considered a sign of basic intelligence. Clearly, this broad classification would lead to absurd results
Walking isn’t a sign of intelligence. Starfish walk, using hundreds to thousands of feet uder each arm, and sometimes the arms themselves. Sea pigs also walk, and neither have a brain.
Besides, you’re strawmanning their definition;
is very different from
A good calculator can compute arithmetic better than a mathematician, but it cannot even parse the work of a high school student. Wolfram Alpha on the other hand gets pretty close.
A wind up toy can propel itself using as few as one appendage, but fails at actually traversing anything. Some machines with more legs can amble across some terrain, but are still beaten by a headless chicken. Meaningful travel needs a much more complex system of object avoidance and leg positioning, which smells more like AI.
The way AI is often used isn’t “do a task that a human has done”, but “replace the need for a human, or at least a specialist human”. Chess AI replaces the need for a second player, as do most game AIs. AI assistants replace much of the need for, well, assistants and underwriters. Auto-pilots replace the need for constantly engaged pilots, allowing bathroom breaks and rest.
Meanwhile, you can’t use a calculator without already knowing how to math, and even GPS guided tractors need a human to set up the route. These things aren’t intelligent in any way; they’re incapable of changing behavior to fit different situations, and can’t deploy themselves.
What if humans are also just LLMs when they start talking
Incorrect, humans have an understanding of the words they use, LLM’s use statistical models to guess what word gets used.
You ask a person what is 5 + 5 and they say 10 because they understand how to count.
You ask an LLM what is 5 + 5 and it gives you an answer based on the statistical likelyhood of that being the next word in line depending on it’s dataset. If you’re dataset has wrong answers you’ll get wrong answers.
I appreciate this, as I have saying this same thing. Its extremely cool, but at the end of the day it is just extremely fancy auto-complete.
It’s a bit like saying a human being is a fancy worm. Technically it is true, we evolved from worms, still we are pretty special compared to worms
We use LLM feature throughout our lives. Often without realizing. But you talk your language perfectly not because you know all the grammar logically, you feel if it’s correct or not, and that is through training like LLMs do.
Mine was a comment to say that llms are not just fancy auto complete. Although technically an evolution, it is a bit like saying humans are fancy worms because evolved from worms
Ah I see 😄 I seem to have misunderstood that a bit
Exactly like children who start learning to talk
Have you ever asked a kid who is starting to talk (1.5 - 3 years old) what 5 + 5 is? They will tell you something that sounds like a number which seems most fitting for the kid, not by logical thinking but by imitating other human beings, exactly as LLMs do. Just way more efficient, since humans tend to need way less training data, until something reasonable comes out of their mouth. Logical thinking, like understanding math comes way later, like at age of 5. source: My son.
Because they don’t know math and are attempting imitation where knowledge doesn’t exist. The LLM has knowledge and a statistical model. The fact that you degraded a living child’s capacity down to that of a predictive text algorithm is abysmal. That child is already learning truth and objectivity and love and hope and so many things that are intangential and out of reach of an LLM.
I reduced to learning talking part of the human development. Of course there are way more mechanisms involved than the way LLMs work to throughly master talking (as we see on the results of todays LMM). But what I wanted to say is that I’m pretty sure that in our subconscious we use a very similar system to LLMs, especially for talking. I sign for that is in my opinion that people tend to acquire the regional tongue if they stay in the region for long enough. 💁🏻♀️ but in means I’m any expert, this is just how this hole LLM feels to me.
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
The nomenclature I’ve heard (from sci-fi) is ‘narrow’ or ‘weak’ AI would be our current day LLMs, Roomba AIs, etc. It’s restricted in capability and lacks true intelligence. ‘Strong’ or ‘General’ AI would be at the level of a human and have true comprehension and the ability to learn. We don’t have this yet, unless Dr. Alfred J. Lanning is out there working on positronics. ‘Super’ AI will be beyond human capability. Probably will kick off the Singularity.
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.
AI has been around a lot longer than LLMs. Intelligence can mean many different things.
deleted by creator
You’re right that it’s not AI, but there are several layers on top of the large language model to do things like manage dialogue and censor output.
“Human brains are not actually conscious. They’re just a bunch of electrochemical discharges.”
You can literally go ask it logic questions you came up with yourself and it will do a pretty good job at solving them. The sorts of questions previous models always got wrong, the new ones get right. It can write working computer code. This talking point hasn’t made sense for years.
By new how new are we talking? Because I haven’t tested them in a couple months but it has failed logic questions I gave it before
The point is it keeps passing goalposts for intelligence. Feels like people want to move those goalposts to wherever we have it and AI does not.
As I was writing the above crossed out comment I did come to see your pov more closely and I guess in a way you’re right, if we consider it narrow intelligence in terms of understanding and using language, because it is really good at language tasks but we expect artificial intelligence to be perfect for some reason and idk if that’s right or not and that also might be what bothers you about the shifting goalposts.
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.
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?
In the thought experiment, the guy in the Chinese room is following exactly the same kind of rules.
I… know?
deleted by creator
But it’s just a guy in a room shoving slips of papers around. He doesn’t actually speak Chinese.
Get it?
deleted by creator
they can’t translate chinese, they receive a bunch of symbols and have a book with a bunch of instructions on how to answer based on the input (I can’t speak chinese, so I will just go with japanese for my example)
imagine the following rule set:
input: 元気ですか？今何をしていますか？
output: うん, 元気. 質問を答えますよ :P
input: 日本語わかりますか？
output: え？もちろん！
With an exhaustive set of, say, 7 billion rules, the algorithm can mechanically map an input to an output, but this does not mean that it can speak Japanese.
Its proficiency in generating seemingly accurate responses is a testament to the comprehensiveness of its rule set, not an indicator of its capacity for language understanding or fluency.
deleted by creator