this post was submitted on 31 Aug 2023
540 points (98.0% liked)
Technology
59664 readers
2757 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Because it doesn’t “know” those things in the same way people know things.
Not only it doesn't know, but for the people who trained them it is very hard to know whether some piece of information is or isn't inside the model. Introspection about how exactly the model ends up making decisions after it has been trained is incredibly difficult.
It’s actually because they do know things in a way that’s analogous to how people know things.
Let’s say you wanted to forget that cats exist. You’d have to forget every cat meme you’ve ever seen, of course, but your entire knowledge of memes would also have to change. You’d have to forget that you knew how a huge part of the trend started with “i can haz cheeseburger.”
You’d have to forget that you owned a cat, which will change your entire memory of your life history about adopting the cat, getting home in time to feed it, and how it interacted with your other animals or family. Almost every aspect of your life is affected when you own an animal, and all of those would have to somehow be remembered in a no-cat context. Depending on how broadly we define “cat,” you might even need to radically change your understanding of African ecosystems, the history of sailing, evolutionary biology, and so on. Your understanding of mice and rats would have to change. Your understanding of dogs would have to change. Your memory of cartoons would have to change - can you even remember Jerry without Tom? Those are just off the top of my head at 8 in the morning. The ramifications would be huge.
Concepts are all interconnected, and that’s how this class of AI works. I’ve owned cars most of my life, so it’s a huge part of my personal memory and self-definition. They’re also ubiquitous in culture. Hundreds of thousands to millions of concepts relate to cats in some way, and each one of them would need to change, as would each concept that relates to those concepts. Pretty much everything is connected to everything else and as new data are added, they’re added in such a way that they relate to virtually everything that’s already there. Removing cats might not seem to change your knowledge of quarks, but there’s some very very small linkage between the two.
Smaller impact memories are also difficult. That guy with the weird mustache you saw during your vacation to Madrid ten years ago probably doesn’t have that much of a cascading effect, but because Esteban (you never knew his name) has such a tiny impact, it’s also very difficult to detect and remove. His removal won’t affect much of anything in terms of your memory or recall, but if you’re suddenly legally obligated to demonstrate you’ve successfully removed him from your memory, it will be tough.
Basically, the laws were written at a time when people were records in a database and each had their own row. Forgetting a person just meant deleting that row. That’s not the case with these systems.
The thing is that we don’t compel researchers to re-train their models on a data set if someone requests their removal. If you have traditional research on obesity, for instance, and you have a regression model that’s looking at various contributing factors, you do not have to start all over again if someone requests their data be deleted. It should mean that the person’s data are removed from your data set it it doesn’t mean that you can’t continue to use that model - at least it never has, to my knowledge. Your right to be forgotten doesn’t translate to you being allowed to invalidate the scientific models generated that glom together your data with that of tens of thousands of others. You can be left out of the next round of research on that dataset, but I have never heard of people being legally compelled to regenerate a model based on that.
There are absolutely novel legal questions that are going to be involved here, but I just wanted to clarify that it’s really not a simple answer from any perspective.
No, the way humans know things and LLMs know things is entirely different.
The flaw in your understanding is believing that LLMs have internal representations of memes and cats and cars. They do not. They have no memories or internal facts... whereas I think most people agree that humans can actually know things and have internal memories and truths.
It is fundamentally different from asking you to forget that cats exist. You are incapable of altering your memories because that is how brains work. LLMs are incapable of removing information because the information is used to build the model with which they choose their words, which is then undifferentiatable when it's inside the model.
An LLM has no understanding of anything you ask it and is simply a mathematical model of word weights. Unless you truly believe humans have no internal reality and no memories and simply say things based on what is the most likely response, you also believe humans and LLM knowledge is entirely different to each other.
No, I disagree. Human knowledge is semantic in nature. “A cat walks across a room” is very close, in semantic space, to “The dog walked through the bedroom” even though they’re not sharing any individual words in common. Cat maps to dog, across maps to through, bedroom maps to room, and walks maps to walked. We can draw a semantic network showing how “volcano” maps onto “migraine” using a semantic network derived from human subject survey results.
LLMs absolutely have a model of “cats.” “Cat” is a region in an N dimensional semantic vector space that can be measured against every other concept for proximity, which is a metric space measure of relatedness. This idea has been leveraged since the days of latent semantic analysis and all of the work that went into that research.
For context, I’m thinking in terms of cognitive linguistics as described by researchers like Fauconnier and Lakoff who explore how conceptual bundling and metaphor define and constrain human thought. Those concepts imply that a realization can be made in a metric space such that the distance between ideas is related to how different those ideas are, which can in turn be inferred by contextual usage observed over many occurrences. 
The biggest difference between a large model (as primitive as they are, but we’re talking about model-building as a concept here) and human modeling is that human knowledge is embodied. At the end of the day we exist in a physical, social, and informational universe that a model trained on the artifacts can only reproduce as a secondary phenomenon.
But that’s world apart from saying that the cross-linking and mutual dependencies in a metric concept-space is not remotely analogous between humans and large models.
It's not a world apart; it is the difference itself. And no, they are not remotely analogous.
When we talk about a "cat," we talk about something we know and experience; something we have a mental model for. And when we speak of cats, we synthesize our actual lived memories and experiences into responses.
When an LLM talks about a "cat," it does not have a referent. There is no internal model of a cat to it. Cat is simply a word with weights relative to other words. It does not think of a "cat" when it says "cat" because it does not know what a "cat" is and, indeed, cannot think at all. Think of it as a very complicated pachinko machine, as another comment pointed out. The ball you drop is the question and it hits a bunch of pegs on the way down that are words. There is no thought or concept behind the words; it is simply chance that creates the output.
Unless you truly believe humans are dead machines on the inside and that our responses to prompts are based merely on the likelihood of words being connected, then you also believe that humans and LLMs are completely different on a very fundamental level.
Could you outline what you think a human cognitive model of “cat” looks like without referring to anything non-cat?
Yes; it is a cat. I can think of what that is. Can an LLM?
Describe it. Imagine I’ve never encountered a cat, because I’m from Mars.
You can't! It's like describing fire to someone that's never experienced fire.
This is the root of experience and memory and why humans are different from LLMs. Which, again, can never understand or experience a cat or fire. But the difference is more fundamental than that. To an LLM, there is no difference between fire and cat. They are simply words with frequencies attached that lead to other words. Their difference is the positions they occupy in a mathematical model where sometimes it will output one instead of the other, nothing more.
Unless you're arguing my inability to express a mental construct to you completely means I myself don't experience it. Which I think you would agree is absurd?
I have absolutely no idea what your model is for how humans understand, relate, and communicate concepts.
How is that germane to this question? Do you agree humans can experience mental phenomena? Like, do you think I have any mental models at all?
If so, then that is the difference between me and an LLM.
I think you have a mental model and that it is analogous to the model created in an LLM in that it is representable by a semantic graph/n-dimensional matrix relating concepts that are realized via terms.
You have never in your life encountered a dodo. You know what a dodo is (using the present these because I’m talking about a concept). It is a bird, so it relates evolutionarily and ecologically to “bird.” It’s flightless, so it relates to “patriarch” and “emu.” It is extinct, so it relates to all of the species extinction ideas you have. Humans perhaps contributed to the extinction, so it links to human-caused ecological change, which in turn links to human-caused climate change. Human-introduced invasive species are are causing ecological change in Australia, and that may have been a major factor in driving the dodo to extinction. People ate them, so maybe in your head it has a relation to wild turkeys. And so on. That’s how minds work. That’s how the human cognitive model of the world works. That’s how LLMs work.
Visualize an n-dimensional space in which these semantic topics are embedded. The interpretation of the dimensions don’t matter. Instead, we’re just worried about the distances between concepts. Dodo is closer to turkey than it is to snake. Dodo is closer to snake than it is to rock. Dodo is closer to rock than it is to the feeling of melancholy I get when listening to Tori Amos. We can grasp this intuitively. We can mathematize it by formally placing the various concepts in a metric space.
There’s a lot more to unpack, from neural correlates of consciousness to cognitive linguistics and embodied learning using metaphorical reasoning, but that’s kind of the gist of it boiled down to an overly long post.
This is not how LLMs work. LLMs do not have complex thought webs correlating concepts birds, flightlessness, extinction, food, and so on. That is how humans work.
An LLM assembles a mathematical model of what word should follow any other word by analyzing terabytes of data. If in its training corpus the nearest word to "dodo" is "attractive," the LLM will almost always tell you that dodos are attractive. This is not because those concepts are actually related to the LLM, because the LLM is attracted to dodos, or because LLMs have any thoughts at all. It is simply the output of bunch of math based on word proximity.
Humans have cognition and mental models. LLMs have frequency and word weights. While you have correctly identified that both of these things can be portrayed as n-dimensional matrixes, you can also use those tools to describe electrical currents or the movement of stars. But those things contain no more thought and have no more mental phenomenon occurring in them than LLMs.
That is exactly how LLMs work. LOMs embed semantic concepts in metric spaces. That is what we’re talking about.
No, they embed word weights in metric spaces. Human thought is more like semantic concepts in a metric space (though I don't think that's entirely unequivocal, human thought is not very well-understood). Even if the space is similar what's in them is definitely not.
Actually it is also impossible to ask people to forget. This is something we share with AI
Yes, but only by chance.
Human brains can't forget because human brains don't operate that way. LLMs can't forget because they don't know information to begin with, at least not in the same sense that humans do.
See my other reply ;)
It's actually not that dissimilar. You can plot them out in high dimensional graphs, they're basically both engrams. Theirs are just much simpler
Theirs are composed of word weights. Ours are composed of thoughts. It’s entirely dissimilar.