Artificial-intelligence systems such as large language models (LLMs) can exhibit behaviour that seems strikingly intelligent. This has led many people, including some experts, to wonder whether these systems could have some form of consciousness — the capacity for subjective experience. However, we think that existing AI systems are not conscious, and that, along current trajectories of development, they are not likely to become conscious. Greater clarity about whether AI could become consciousness will be crucial as society grapples with the challenges posed by this increasingly powerful technology.
Ok, I’ll ask. What are these decent scientific definitions for consciousness and how can we use them to construct a test for consciousness?
You are free to search the web, there’s lots of information out there. You might start with the Wikipedia article on consciousness.
Oh, I thought you might have something new to say. If you’re just using the normal definition and not bringing any sort of testability (which imo is impossible) or new arguments, how exactly does the common definition prove anything must be non-conscious? That seems like the main claim of your comment, yet it seems like an unsupported assertion; if the common definition of consciousness could easily prove things not to be conscious as you seem to imply, this discussion would not be happening at all.
From Wikipedia:
The Cambridge English Dictionary defines consciousness as “the state of being awake, thinking, and knowing what is happening around you”, as well as “the state of understanding and realizing something”.
Most of these are trivially easy to test (not sure why you think that’s impossible). And LLMs have none of those properties.
Later:
“The having of perceptions, thoughts, and feelings; awareness.”
Again, LLMs have none of these things. They simply generate a probable natural-language response based on their training, deterministically.
Feel free to do further research on your own if you’re interested.
Philosophy is one of my hobbies and consciousness one of my fascinations. Respectfully, doing “research” by skimming the wikipedia article would be a waste of our time; as would responding to any particular definition and arguing over the individual words people have used in summaries of the topic. So I’ll skip that phase of the convo.
The fundamental problem with measuring consciousness is that it’s an internal state (a “qualia”*). It is fundamentally an experience, something that exists only as a concept in your mind. This makes it immeasurable.
That’s quite the claim, so I’ll provide a smaller concrete example: color. Obviously you can measure the frequency of a photon and say “ah yes, 700nm, that photon is red”. But strictly speaking, the photon isn’t red, it just causes you to percieve “red”; it has a wavelength which triggers your eyes and brain to produce the subjective experience of the color red. That subjective experience of color is a qualia, and it is not directly measurable; at best you can measure the phenomenon that causes that qualia in you, and assume that that phenomenon would cause the same qualia in someone else when they percieve that photon. Technically, you can’t be sure that this assumption is true-- this leads to the “Inverted Spectrum” thought experiment (another great wiki page if you prefer their explanations to mine), where someone’s subjective experience of color as it relates to the frequency of light could be entirely different to your own.
Anyways, you cannot prove the existence of nonexistence of such an internal experience, and consciousness belongs to this category of qualia. You know that you are conscious because you experience being conscious, not because you can prove it by looking at what you do. You can’t even be sure that I’m conscious, even if you met me in real life; you can’t prove that I am actually thinking, feeling, understanding, knowing, or realizing anything, because you cannot be me. You can only assume that I am doing those things because you observe me doing stuff in physical reality that’s consistent with the way the only entity you can be sure is conscious (you) is acting, and assuming that since I’m made of the same stuff as you and I act kind of like you do that I am probably conscious.
If you could actually prove that it is impossible for a machine to be conscious without that same argument applying to humans, then the philosophy community of the last several millenia would praise you as their messiah. I am interested to see what your argument would be if you want to give it a shot though-- no harm in trying.
* Like “data”/“datum”, technically the singular form is “quale”, but I’m gonna be real, nobody ever says that. Anyways if you like reading wikipedia pages about philosophy, “qualia” is a good one!
Almost none of this is relevant to the discussion here – I’m not interested in philosophical discussions of consciousness when it comes to the question of whether an LLM is conscious. Though I’m already aware of most of what you said here, and the philosophy of consciousness is interesting in general to me!
Quick nitpick: I never said it’s impossible for a machine to be conscious, I said it’s impossible for an LLM to be conscious. We may well invent something new in the future that qualifies as both “machine” and “conscious,” but an LLM is not that thing.
When people ask “is an LLM conscious?” I assume they’re asking from a practical, scientific perspective – does the LLM experience the world in a similar way to the way I (and presumably, others) do? If that is the question, the various definitions I already posted are what we should be using to answer. Since an LLM is a deterministic algorithm whose only purpose is to generate a plausible response to input based on its training data, it cannot possibly think, or have feelings. It does not even exist continuously in time, and it is fixed and unchanging, unable to incorporate any new information at all. We don’t actually need to measure or test anything here; that an LLM lacks all of these things demonstrates that it’s not possible for it to be conscious.
(I apologize in advance for the mountain of text. My main point is about how I don’t think you can cleanly separate the philosophical and scientific approaches to consciousness, and how the line between humans and simpler processes is a lot blurrier than your list of differences makes it seem.)
Hmm. I see what you’re saying, although I will admit this threw me for quite the loop:
Because, IMO, consciousness is almost entirely within the realm of philosophy. I’m not sure how much you can do with a scientific approach to it; I cannot think of many hypotheses to test that could give useful (ie. unambiguous and certain) results about the nature of consciousness. But perhaps you’re right that that’s giving up too easily; we can (and often must) make assumptions and reason by analogy to figure out what the most likely state of reality is, even if technically we cannot be entirely sure.
To avoid the pitfalls of unknowability, you could assume that all humans are conscious (reasonable imo, obviously) and that having certain humanlike properties is a good indicator that something might be conscious (which properties these are is of course a subject of great debate). I do think it’s a mistake to say that lacking these properties means it’s “not possible” for something to be conscious-- just that if we want to have any reasonable chance of accurately guessing what’s conscious, these properties (along with an understanding of said something’s inner workings) can be a useful guide. So, let’s evaluate the similarities and differences.
Humans share some of these properties with LLMs. Humans are only conscious for a period of time (while we are awake (or while dreaming?)) where we are processing information. We too lack full continuity of consciousness. The parallel of this for a neural network of any kind might be during the time they are generating output or training-- in that period of time, they are also processing information. So I think you have narrowed the window in which it is reasonably possible for an LLM to be conscious (“awake”) to just the period of time in which it is running. (Also worth noting is that human brains don’t fully shut down while we are unconscious, not sure how to fit that in here though).
You also mention randomness-- true, maybe randomness plays a part in consciousness (true randomness, not pseudorandomness), and LLMs are deterministic. I think you could relatively easily construct a neural network that does use true randomness, but 1. true randomness is “expensive” to use in terms of computers, usually only being used to seed PRNGs, so it would take FOREVER to run, and 2. it would probably require new training techniques, and at that point maybe you could just skip to the experiment after the end of the next paragraph.
The last difference is that they don’t take input, produce output, and update themselves (train) all at the same time like we do. We also do this continuously, rather than in discrete steps. Therefore you can say that LLMs (or any current neural networks) lack an integrated and locally continuous experience. This is probably the biggest blocker to LLM consciousness that I see being taken seriously, and I’m inclined to agree, because it is the biggest difference between humans and neural networks.
So, what if we construct a machine using an LLM as its core that has these properties? One that could:
Anyways, sorry for getting sidetracked in hypothetical scenario land. I agree that there are enough differences that it is unlikely for an LLM to be conscious in the same way that a human is. But I am curious what makes you so confident that those particular properties are necessary for consciousness to exist at all on some level-- could consciousness not simply be a phenomenon that arises whenever something is being computed, and human brains are just a continuous and very complicated computer with the ability to learn and act simultaneously?
I suppose that line of thinking could quickly be expanded to the “basically everything has a tiny bit of consciousness” philosophy, and then you would have to come up with a more specific term for human-like consciousness; but that only delays the moral dilemmas until we create machines that have more human properties (like the one I proposed above)-- or humans that have more machine ones (brain organoids or whatever they’re called are fucking terrifying philosophically).
How is red a subjective experience? We can all experience red things, at least, all of us with functioning eyes. What about that is subjective? How is color not directly measurable? Color is very easy to measure, we can even assign it values, like (r,g,b). If you see something red, you have already measured it to have the values (>0,0,0). I don’t know what the term “internal experience” even means. Experience is just something that happens to something else. A rock experiences erosion in the rain. I am experiencing tiredness right now. To say something experiences something is to just say X is happening to Y. I don’t see how it is meaningful to assign adjectives like “internal” or “external” to it. I mean, if the adjective was meaningful, then would it not imply that you are implicitly contrasting “internal experience” with “external experience”? What on earth would external experience be? If you cannot tell me what external experience is, then the adjective “internal” is contrasting it with nothing at all, so it is a useless adjective.
If you don’t understand what I’m trying to explain about qualia or that there is a philosophical distinction between the physical world and your perception, just read the wikipedia article on qualia or any similar introductory material to the philosophy of the mind. It answers like 90% of your questions.
Some specific answers though:
RGB is measuring/defining proportions of different wavelengths of light, even if its goal is to describe that light in a way that is supposed to elicit a particular subjective experience in the viewer. Color spaces are a MASSIVE rabbit hole so I would suggest using the simpler example of how an individual photon has a wavelength that makes us percieve the subjective experience of red, rather than being red itself. Although actually, bringing up RGB gives me an idea for something to point out: qualia and the physical world can “desync”, which is evidence they are different. If you see light with a wavelength of ~600nm, such as that produced by a sodium lamp or banana, you will percieve it as yellow. But that subjective experience of yellow is also triggered by seeing both ~700nm and ~500nm wavelengths of light simultaneously, which you would individually percieve as red and green respectively. This is how your computer screen does it. ||I guess technically you could argue the cone activations in your eye end up the same, so this may be a bad example… regardless, the point is that something like a taste or smell or color has no physical meaning, they are experiences which are caused by physical phenomena rather than being the physical phenomena themselves.||
I am using “internal experience” to mean the subjective way that you percieve the world. If I just used “experience” you could use it more broadly in your sense of “X is happening to you”, which is not what I mean. I guess you could call those things happening in the physical world an “external experience” but I agree, that is a bit confusing and is not my intention. I am using “internal” to make a more specific compound term, not really to contrast it with “external”. But if you are using the word “experience” to mean “C is happening to you” then yes, the external experience is the thing that is physically happening and the internal experience is your perception of it happening to you.
Proof?
We knew about colors long before anyone knew what a “wavelength of light” is. I can tell something is red without needing to measure its photons. There are correlations between red, green, and blue, but they are not exact. Monitors do a lot of weird things with colors and so it is just false to state that there is a direct equivalence to color values and wavelengths of light that the monitor will actually emit.
How do I perceive the world “subjectively”? What does that even mean? Is it possible to perceive the world “objectively”?
So all you mean by “subjective experience” is that the things are happening to me specifically? So, if thing happens to another thing, and one of those things is a subject, then it is subjective? That is a strange way to use the word “subjective.” If I eat a sandwich, is that subjective eating?
What do you mean “proof”? Proof that the field of philosophy considers there to be a distinction? I pointed you to a great resource to learn about this, the proof that philosophers think there is a distinction and the details of how and why they believe that (and common arguments against it if that’s your jam!) are RIGHT THERE in the link I provided. This is not some crackpot theory I am trying to prove to you in a lemmy thread, I am just explaining philosophy of mind 101. Like, this is literally related to “I think, therefore I am”. If you disagree with philosophy in general then I’m not going to spend several hours justifying the entire field of philosophy to you; I’ve pointed you in the right direction, if you want to learn more about it then just read the basics, they can explain it better than I can and it’s much less argumentative that way. Seriously, I recommend it, it’s a good time and it’s a fun way to explore the nature of your mind.
To answer your edits (briefly, again this is covered in the link or any similar resource):
No, by “internal experience” or “subjective experience” I mean that I am referring to your perception of the thing happening. If I coat a rock in honey, it becomes sticky. If I coat your arm in honey, it also becomes sticky. What “subjective experience” refers to is what you feel and percieve when I am coating your arm in honey. It’s what you have that the rock doesn’t-- your thoughts, perceptions, feelings, etc.
Not sure what you’re saying here, but see above.