I mean, that is the fundamental architecture of the model and how it's explicitly designed: given an input embedding and output embedding, the model is trained over a massive corpus of text to optimize the probability for generating the next token in the sequence. Any other interpretation is secondary to that, no matter how impressive the results are.
There is no rule that implies the explicit design dominates the emergent effect.
Evolutionary biology strives to make us logical creatures to fulfill the singular goal of passing on genetic material. Your sentience and your humanity is a side effect of this singular goal.
So what dominates the description of who YOU are? Human or vessel for genetic material?
I'll say that YOU are human and therefore more then just a vessel for ferreting your genetic material into the future... just like how I'll go with the fact that LLMs are more then just statistical word generators.
They really aren't more than just statistical word generators because we can and do build what are exactly statistical word generators and get the behavior of ChatGPT (because that is what ChatGPT is).
For what it's worth, this isn't a knock on ChatGPT, but more just how amazing how far you can get with straightforward concepts.
It's also a specific choice of label though, and one which in the context of current discourse favors a particular side.
It's like insisting on calling anything physical "atom collections". Yes, we get it, it's true (under a certain interpretation)—but it's clearly pointless to say except as an attempt at devaluing through reduction. (And it takes a particular stance on what it means to "be" something: to say it's literally the truth that anything physical is "just atoms" isn't the only way of looking at it.)
There were things we could've called "statistical word generators" decades ago; insisting on using a term directed at that level of generality implies a belief that nothing significant has happened since. Printing press? Just atoms. Cars? Just atoms. Computers? Just atoms.
I think its because it's sort of gone in the opposite way that science usually goes. Science traditionally been the process of physical phenomena that we don't understand => falsifiable theory that helps describe that phenomena.
Meanwhile, we started at stuff like the perceptron. The starting point was that we knew everything about that equation/classifier. Now we have a thing that we built from the ground up, and we don't fully grasp how it all comes together.
> insisting on using a term directed at that level of generality implies a belief that nothing significant has happened since. Printing press? Just atoms. Cars? Just atoms. Computers? Just atoms.
It's very context-dependent but I don't read this as dismissive reduction, I read it as a statement of the incredible generalisability of atoms under the current laws of physics.
Pfft more useless text written by a giant pile of atoms. Pointless.
Kidding aside, in the current context of human communication etiquette, to even refer to something as atoms outside of a demonstration or example is a deliberate dismissive reduction.
I think the fact that it's a technical discussion highlights why it's problematic: it might be appropriate for a total outsider who needs some kind of grasp of the basic underlying principle it operates on; but in discussion by a bunch of people with CS backgrounds, calling it merely a statical language generator erases distinction between it and other software of a prior age known not to be world-changing, overlooks recent innovations we don't yet have simple ways of referring to (largely because we don't understand emergent properties of LLMs)
The output of LLMs implies a higher level structure. You can't solely discuss the lower level underpinning unless you deliberately do not acknowledge that the output of LLMs are implying something else.
We've spent years building tools that generate sequences with probable statistical distributions, but none of them ever developed anything that vaguely resembled a "world model" before. I think it might be useful to disambiguate these transformer models from previous statistical text generators, in the same way it's useful to disambiguate a human brain from a calculator (even if they're both trained to perform arithmetic.)
Except the paper in the OPs comment literally talks about how these LLM's are building actual models of the real world. Literally. The root parent post links a research paper that categorically falsifies your statement.
No need to be worried about knocking chatGPT. I have no pride invested in the thing. But I do think that people who view it solely as statistical word generators are biased.
You can imagine that the embedding for the token “boat” includes wood, steel, water and so forth in some set of probabilistic paths as learnt by autorgressive training since the words appear together in the past N tokens. So they are directly in frame. A question is how to connect out of frame elements and are overlapping tokens sufficient to do “that”. Specifically is the token “that” sufficiently trained to reveal what it refers to? I think this depends on the fine tuning q/a task which adds in a layer of alignment rather than being an emergent property of the LLM in general.
Still alignment tasks are autoregressive (I think)… they could be masked or masked part of speech potentially.. but if autoregressive then I suspect you’re looking at regularities in positioning to identify things.
Except the paper in the OPs comment literally talks about how these LLM's are building actual models of the real world.
No need to be worried about knocking chatGPT. I have no pride invested in the thing. But I do think that people who view it solely as statistical word generators are biased.
> Evolutionary biology strives to make us logical creatures to fulfill the singular goal of passing on genetic material. Your sentience and your humanity is a side effect of this singular goal.
Evolutionary biology is the study of processes that have created widely diverse forms of life on earth through common ancestry. This is actually strictly at odds with the statement that the goal of life is to pass on genetic material (which has changed monumentally over time). Different forms of life have wildly different reproduction strategies with many different dimensions. Logic has practically no impact on an organism's ability to reproduce (it seems limited to a small subset of the animal kingdom - every one else is doing fine without it).
Evolutionary biology has no goals - it's just our observations of how and when (not why) life on earth has changed over time and through the lens of biodiversity.
Tl/Dr: there is no scientific answer about what the goals of life are - heck the definition of life itself is a fun debate. It is a difficult argument to make that a path to general intelligence or consciousness runs thru predicting the next word in a sentence. Generally most people 'believe' it rather than put forth experimental hypothesis let alone attempt to test it.
Until someone does it seems more likely that we're simply uncovering interesting statistical structures underpinning written languages. It's cool that they exist, but frankly it's not surprising that they would.
ME: What is the goal of a biological organism in the context of evolutionary biology?
chatGPT: From an evolutionary biology perspective, the goal of a biological organism is not to achieve any particular objective or purpose, but rather to survive and reproduce successfully. Evolutionary theory suggests that organisms that are better adapted to their environment are more likely to survive and pass on their genes to the next generation, which leads to the evolution of new species over time.
Therefore, the ultimate goal of any biological organism, whether it is a single-celled organism or a complex animal, is to survive long enough to reproduce and pass on its genetic material to the next generation. Organisms that are better suited to their environment, that are able to acquire resources more efficiently, and that can avoid predators and other threats are more likely to achieve this goal and contribute to the ongoing process of evolution.
ME: What is the physical evidence that suggests to scientists that this is the case?
chatGPT: There is a wealth of physical evidence that supports the idea that the ultimate goal of biological organisms is to survive and reproduce. Here are a few examples:
Fossil record: The fossil record provides evidence that species have evolved over time, with many species going extinct and new ones emerging. Fossils also reveal adaptations that allowed species to better survive and reproduce in their environments, such as the development of wings in birds and insects or the evolution of specialized teeth and jaws in carnivorous animals.
Comparative anatomy: Comparative anatomy allows scientists to study the physical structures of different organisms and identify similarities and differences. These similarities and differences can provide insights into how different species have evolved and adapted to their environments. For example, the similarities in the skeletal structures of mammals suggest that they share a common ancestor, while the differences in the beaks of finches on the Galapagos Islands suggest that they have adapted to different food sources.
Genetics: Genetic evidence provides insights into how organisms have evolved and adapted over time. By comparing the genetic sequences of different species, scientists can identify similarities and differences that provide clues to how species are related and how they have evolved. Genetic evidence also reveals the adaptations that have allowed species to survive and reproduce in their environments, such as the evolution of antibiotic resistance in bacteria.
Overall, the physical evidence from fields such as paleontology, comparative anatomy, and genetics supports the idea that the ultimate goal of biological organisms is to survive and reproduce successfully, and that this goal has driven the evolution of new species over time.
ME: Is this fact unequivocal among scientists who study this field?
chatGPT: The idea that the ultimate goal of biological organisms is to survive and reproduce is a fundamental assumption of evolutionary biology, and it is widely accepted among scientists who study this field. While there may be some variation in how different scientists conceptualize or frame this idea, the basic principle that the success of an organism is ultimately measured by its ability to reproduce and pass on its genes to the next generation is well-established and widely accepted.
chatGPT: There is a vast body of evidence from a wide range of fields, including paleontology, comparative anatomy, genetics, and ecology, that supports the idea that natural selection acts to favor traits that increase an organism's ability to survive and reproduce in its environment. This evidence is supported by numerous experiments and observations that have been conducted over many decades, and it is a cornerstone of modern evolutionary theory.
chatGPT: Of course, scientific ideas are always subject to ongoing refinement and revision as new evidence is gathered, and there may be debates and disagreements among scientists about certain aspects of evolutionary theory. However, the general principle that the goal of biological organisms is to survive and reproduce is widely accepted as a foundational idea in the field of evolutionary biology.
I'm well versed in evolutionary biology and the mechanisms behind it. I can assure you that chatGPT is more knowledgeable than you on this topic and that everything it says here is categorically true. Others who know biology can confirm.
