Experiences, mechanisms, behaviors and LLMs

This is another post that sat in the attic for a few years.  It overlaps a bit with some later posts, but I thought it was still worth dusting off and publishing.  By "dusting off", I mean "re-reading, trying to edit, and then rewriting nearly everything but the first few paragraphs from scratch, making somewhat different points."

Here are some similar-looking questions:

• Someone writes an application that can successfully answer questions about the content of a story it's given.  Does it understand the story?
• Other primates can watch each other, pick up cues such as where the other party is looking, and react accordingly.  Do they have a "theory of mind", that is, some sort of mental model of what the other is thinking, or are they just reacting directly to where the other party is looking and other superficial clues (see this previous post for more detail)?
• How can we tell if something, whether it's a person, another animal, an AI or something else,  is really conscious, that is, having conscious experiences as opposed to somehow unconsciously doing everything a conscious being would do?
• In the case of the hide-and-seek machine learning agents (see this post and this one), do the agents have some sort of model of the world?
• How can you tell if something, whether it's a baby human, another animal or an AI, has object permanence, that is, the ability to know that an object exists somewhere that it can't directly sense?
• In the film Blade Runner, is Dekker a replicant?

These are all questions about how things, whether biological or not, understand and experience the world (the story that Blade Runner is based on says this more clearly in its title, Do Androids Dream of Electric Sheep?).  They also have a common theme of what you can know about something internally based on what you can observe about it externally.  That was originally going to be the main topic, but the previous post on memory covered most of the points I really wanted to make, although from a different angle.

In any case, even though the questions seem similar, some differences appear when you dig into and try to answer them.

The question of whether something is having conscious experiences, or just looks like it, also known as  the "philosophical zombie" problem, is different from the others in that it can't be answered objectively, because having conscious experiences is subjective by definition.   As to Dekker, well, isn't it obvious?

There are several ways to interpret the others, according to a distinction I've already made in a couple of other posts:

• Does the maybe-understander experience the same things as we do when we feel we understand something (perhaps an "aha ... I get it now" sort of feeling).  As with the philosophical zombie problem, this is in the realm of philosophy, or at least it's unavoidably subjective.  Call this the question of experience.
• Does the maybe-understander do the same things we do when understanding something (in some abstract sense).  For example, if we read a story that mentions "tears in rain", does the understander have something like memories of crying and of being in the rain, that it combines into an understanding of "tears in rain" (there's a lot we don't know about how people understand things, but it's probably roughly along those lines).  Call this the question of mechanism.
• Does the maybe-understander behave similarly to how we do if we understand something?  For example, if we ask "What does it mean for something to be washed away like tears in rain?" can it give a sensible answer?  Call this the question of behavior.

The second interpretation may seem like the right one, but it has practical problems.  Rather than just knowing what something did, like what answer it gave to your questions, you have to be able to tell what internal machinery it has and how it uses it, which is difficult to do objectively (I go into this from a somewhat different direction in the previous post).

The third interpretation is much easier to answer rigorously and objectively, but, once you've decided on a set of test cases, what does a "yes" answer actually mean?  At the time of this writing, chatbots can give a decent answer to a question like the one about tears in rain, but it's also clear that they don't have any direct experience of tears, or rain.

Over the course of trying to understand AI in general, and the current generation in particular, I've at least been able to clarify my own thinking concerning experience, mechanism and behavior: It would be nice to be able to answer the question of experience, but that's not going to happen.  It's not even completely possible when it comes to other people, much less other animals or AIs, even if you take the commonsense position that other people do have the same sorts of experiences as you do.

You and I might look at the same image or read the same text and say similar things about it, but did you really experience understanding it the way I did?  How can I really know?  The best I can do is ask more questions, look for other external cues (did you wrinkle your forehead when I mentioned something that seemed very clear to me?) and try to form a conclusion as best I can.

Even understanding of individual words is subjective in this sense.  The classic question is whether I understand the word blue the same way you do.  Even if some sort of functional MRI can show that neurons are firing in the same general way in our brains when we encounter the word blue, what's to say I don't experience blueness in the same way you experience redness and vice versa?

The question of behavior is just the opposite.  It's knowable, but not necessarily satisfying.  The question of mechanism is somewhere in between.  It's somewhat knowable.  For example, the previous post talks about how memory in transformer-based models appears to be fundamentally different from our memory (and that of RNN-based models).  It's somewhat satisfying to know something more about how something works, in this case being able to say "transformers don't remember things in the same sense that we do". [Re-reading, I've had to make a couple of edits for clarity, because words like how can refer to both mechanism and behavior, which is exactly what I'm trying to distinguish. In this particular case, the difference is in both behavior and mechanism -- D.H. Jan 2025]

Nonetheless, as I discussed in a different previous post, the problem of behavior is most relevant when it comes to figuring out the implications of having some particular form of AI in the real world.  There's a long history of attempts to reason "This AI doesn't have X, like we do, therefore it isn't generally intelligent like we are" or "If an AI has Y, like we do, it will be generally intelligent and there will be untold consequences", only to have an AI appear that people agree has Y but doesn't appear to be generally intelligent.  The latest Y appears to be "understanding of natural language".

But let's take a closer look at that understanding, from the point of view of behavior.  There are several levels of understanding natural language.  Some of them are:

• Understanding of how words fit together in sentences.  This includes what's historically been called syntax or grammar, but also more subtle issues like how people say big, old, gray house rather than old, gray, big house 
• Understanding the content of a text, for example being able to answer "yes" to Did the doctor go to the store? from a text like The doctor got up and had some breakfast.  Later, she went to the store.  Questions like these don't require any detailed understanding of what words actually mean. 
• Understanding meaning that's not directly in a text.  If the text is The doctor went to the store, but the store was closed.  What day was it?  The doctor remembered that the regular Wednesday staff meeting was yesterday.  There was a sign on the door: Open Sun - Wed 10 to 6, Sat noon to 6, then to correctly answer Did the doctor go to the store with something like Yes, but it was Thursday and the store was closed, rather than a simple yes without further explanation.

From a human point of view, the stories in the second and third bullet points may seem like the same story in different words, but from an AI point of view one is much harder than the other. But current chatbots can do all three of these, so from a behavioral point of view it's hard to argue that they don't understand text, even though they clearly don't use the same mechanisms.

This is a fairly recent development.  The earlier draft of this post noted that chatbots at the time might do fine for a prompt that required knowing that Thursday comes after Wednesday but completely fail on the same prompt using Sunday and Monday.  Current [Sep 2024] models do much better with this sort of thing, so in some sense they know more and understand better than the ones from 2019, even if it's not clear what the impact of this has been in the world at large.

Chatbots don't have direct experience of the physical world or social conventions.  What they do have is the ability to process text about experiences in the physical world and social conventions.  One way of looking at a chatbot is as a simulation of "what would the internet say about this?" or, a bit more precisely, "based on the contents of the training text, what text would be generated in response to the prompt given?"  Since that text was written (largely) by people with experiences of the physical world and social conventions, a good simulation will produce results similar to those of a person.

From the point of view of behavior, this is interesting.  An LLM is capturing something about the training text that enables behavior that we would attribute to understanding.

It might be interesting to combine a text-based chatbot that can access textual information about the real world with a robot actually embedded in the physical world, and I think there have been experiments along those lines.  A robot understands the physical world in the sense of being able to perceive things and interact with them physically.  In what sense would the combined chatbot/robot system understand the physical world?

From the point of view of mechanism, there are obvious objections to the idea that chatbots understand the text they're processing.  In my view, these are valid, but how relevant they are depends on your perspective.  Let's look at a couple of possible objections.

It's just manipulating text.  This hearkens back to early programs like ELIZA, which manipulated text in very obvious ways, like responding to I feel happy with Why do you feel happy? because the program will respond to I feel X with Why do you feel X? regardless of what X is.  While the author of ELIZA never pretended it was understanding anything, it very much gave the appearance of understanding if you were willing to believe it could understand to begin with, something many people, including the author, found deeply unsettling.

On the one hand, it's literally true that an LLM-based chatbot is just manipulating text.  On the other hand, it's doing so in a far from obvious way.  Unlike ELIZA, an LLM is able to encode, one way or another, something about how language is structured, facts like "Thursday comes after Wednesday" and implications like "if a store's hours say it's open on some days, then it's closed on the others" (an example of "the exception proves the rule" in the original sense -- sorry, couldn't help it).

As the processing becomes more sophisticated, the just in It's just manipulating text  does more and more work.  At the present state of the art, a more accurate statement might be It's manipulating text in a way that captures something meaningful about its contents.

It's just doing calculations: Again, this is literally true.  At the core of a current LLM is a whole lot of tensor-smashing, basically multiplying and adding numbers according to a small set of well-defined rules, quadrillions of times (the basic unit of computing power for the chips that are used is the teraflop, or trillion floating-point arithmetic operations per second, single chips can do hundreds of teraflops and there may be many such chips involved in answering a particular query).

But again, that just is doing an awful lot of work.  Fundamentally, computers do two things

• They perform basic calculations, such as addition, multiplication and various logical operations, on blocks of bits
• They copy data from one location to another, based on the contents of blocks of bits

That second bullet point includes both conditional logic (since the instruction pointer is one place to put data) and the "pointer chasing" that together underlie a large swath of current software and were particularly important in early AI efforts.  While neural net models do a bit of that, the vast bulk of what they do is brute calculation.  If anything, they're the least computer science-y and most calculation-heavy AIs [to be clear, there's still a lot of legit CS in making all that work at scale -- D.H. Jan 2025].

Nonetheless, all that calculation is driving something much more subtle, namely simulating the behavior of a network of idealized neurons, which collectively behave in a way we only partly understand.  If an app for, say, calculating the price of replacing a deck or patio does a calculation, we can follow along with it and convince ourselves that the calculation is correct.  When a pile of GPUs cranks out the result of running a particular stream of input through a transformer-based model, we can make educated guesses as to what it's doing, but at in many contexts the best description is "it does what it does".

In other words, it's just doing calculations may look the same as it's just doing something simple, but that's not really right.  It's doing lots and lots and lots of simple things on far too much data for a human brain to understand directly.

All of this is just another way to say that while the question of mechanism is interesting, and we might even learn interesting things about our own mental mechanisms by studying it, it's not particularly helpful in figuring out what to actually do regarding the current generation of AIs.

How natural is nature?

Physics has produced several amazingly elegant theories that reduce a huge variety of phenomena to a few basic causes and concepts.  Even if the basic concepts are just a wee bit math-heavy and the results can be a just a wee bit mind-bending, a great number of important discoveries in physics can be reduced to fairly short descriptions.

• Thermodynamics uses a handful of laws to explain things like why perpetual motion can't happen, how engines work or why Play-Doh™ always ends up looking gray-brown if you mash it together long enough.
• Newton's laws explain things like why the Moon goes around the Earth, how you can tell if a car in an accident was speeding or how to sink the 8-ball in the corner pocket.
• Nöther's theorem demonstrates (in a way I've never quite completely grasped) a deep relation between symmetry and conservation -- if, for example, the equations describing motion don't care about direction then angular momentum is conserved and that figure skater spins faster and faster as the arms come in.
• General relativity holds that, left to themselves, objects travel in a straight line, the simplest possible path.  It just doesn't always look that way because space-time isn't flat, but this is why, for example, Mercury's orbit moves just a bit every time around.
• Quantum physics ... yeah.  Quantum physics.

It's not that quantum physics lacks elegance.  The idea that all matter and energy, basically everything we can measure, can be explained by equations similar in form to those that describe a vibrating string is pretty astounding if you think about it.  The Standard Model of quantum physics has built on this to make a large number of predictions, including predictions of new particles, that have been confirmed with outstanding accuracy.

You'd think this would be good news.  Instead, a certain uneasiness has developed around the Standard Model.  The basic framework is nice enough, but it can't completely describe what we know until you plug in several parameters.  There are 19 in all, ranging from m_e  (the mass of the electron, 511 keV), to θ₂₃ (the "CKM 23-mixing angle", 2.4°) to the recently established m_H, (the Higgs mass, tentatively 125.36±0.41 GeV).  There aren't just infinitely many other ways to tune the knobs, there are not one, not two but 19 knobs to tune.

Tweak a few of them the wrong way and stars can never form, or worse, no kind of solid matter can form at all.  We seem to be in some sort of special regime where the parameters just happen to have the right values for us to be here to observe them.  Even if you adopt the view that there may be infinitely other universes out there where the knobs aren't tuned right, so where else could we be (the "weak anthropic principle"), it's still all pretty unsatisfying.  Our universe is some point in a 19-dimensional space that's suitable for life forms like us to develop?  That's it?


Particle physicist Sabine Hossenfelder  argues in a piece called The LHC “nightmare scenario” has come true that yep, that's it, get over it.  As I read it she makes two points.  The smaller one is that the Large Hadron Collider which was instrumental in finding the Higgs boson has likely found all the particles it's going to find, and maybe it's time to stop trying to build bigger and bigger particle accelerators.

Fellow particle physicist Matt Strassler argues that there's no nightmare regardless of whether there are any other new particles.  The LHC has produced ridiculous amounts of data which won't be thoroughly examined for years, and it can easily produce more.  There might be, indeed probably are, interesting discoveries to be pulled out of that data now that it's pretty well established that the Higgs exists.

This seems reasonable, but it's more an argument against Hossenfelder's headline than the substance of the article.  Disputes over what experiments to do (and, more to the point, what experiments to fund) are by no means new.  Hossenfelder's and Strassler's are by no means the only views on the subject, and they may not even be particularly divergent, but in any case whether to keep building bigger particle smashers is of greatest concern to particle physicists and those who fund them.

Public policy and the sociology of science are worthy topics, but I won't be conjecturing any further about them here.  I'm more interested in Hossenfelder's larger point, which as I understand it is about what makes a good theory of physics.

When people started taking a close look at Newtonian mechanics, heat transfer and other fields they started to find anomalies under extreme conditions that eventually led to the discovery of relativity and quantum physics.  This is just part of a long history of progress in physics.  For example:

• Ptolemy explained the motions of the planets with a system of cycles and epicycles centered around the Earth.
• Copernicus explained those motions more simply with a system of cycles and epicycles centered around the sun.
• Kepler did away with epicycles using the notion that the planets moved in ellipses, not circles
• Newton explained elliptical orbits in terms of a universal gravitational force following an inverse square law
• and Einstein explained gravitation as a property of space-time itself

(I'm always a bit leery about ascribing a particular landmark result to a particular person, as in "Ptolemy explained ...".  There is more to each of these than a single person making a single discovery even when we know a particular person had a particular key insight.  But this will do for now.)

In all these cases, the new theory didn't just explain everything the old theory did, albeit in a new way.  It either made sense of something that had seemed arbitrary in the old theory, explained new things the old theory couldn't, or both.  Copernicus and Kepler dealt with epicycles, first simplifying them and then doing away with them altogether.  Newton's mechanics explained why the planets followed elliptical orbits as described by Kepler's laws and not some other shape.  It also explained why the Moon doesn't actually follow an exactly elliptical orbit, why the daily tides rise and fall, and much more.

Einstein's theory of relativity did away with gravitation as a force.  Objects under the influence of gravity still follow Newton's first law, just in a more subtle form.  It also gave better predictions for the motions of the planets and made a number of new predictions that were later confirmed, such as the direction and frequency of light being affected by gravity and why the orbits of stars in a binary system containing a pulsar can be seen to be slowing.

It's not just that the new theories were more powerful than the old ones.  That's to be expected.  Otherwise why adopt them?  In all these cases, and many others, the new theory was also, in some sense, more elegant than the old.  Elegant, in this sense, largely means simpler.  Fewer epicycles.  One universal force.  No universal force at all.  There is also a sense of reducing seemingly unrelated things to different aspects of the same thing.  The tides and the motions of the planet are both just effects of gravity.  Space and time are just components of a the space-time continuum.

Which brings us back to the Standard Model.

So far no one has come up with a theory-breaking anomaly for the Standard Model analogous to the precession of Mercury's orbit, or some new phenomenon, say an unpredicted particle or force, that the Standard Model could have been expected to predict but didn't.  There are a few candidates, but even after decades of effort nothing has really panned out.  The experiments at the LHC found the Higgs, at an energy consistent with the Standard Model, and nothing, or at least nothing definitive, inconsistent with it.

So the Standard Model is it, right?  We've described the fundamental forces and elementary particles of the natural world.  There's plenty of work, probably an endless amount, to be done working out the ramifications of that, and how it all fits in with relativity, what exactly it means to "measure" a system described by a wavefunction, and on and on, but as to explaining the basis for particle physics, we're done.  Right?

As I understand it, Hossenfelder's answer to that would be "looks like we could be", but that answer doesn't sit well with everyone.  How can such an inelegant theory, with its 19 arbitrary parameters, be the final answer?  "They just do" can't be an adequate answer to "why do those parameters have the values they do?" can it? Hossenfelder would likely say "sure it can".

In the history of physics, power and elegance seem to go hand in hand.  Or at least, after enough anomalies with ad-hoc descriptions turn up, eventually someone comes up with a new framework where it all makes sense again.  The new theory is both more elegant and more powerful.  Some would even say more "natural" and claim that nature is itself elegant, and if it doesn't seem that way we must not understand it properly.

The Standard Model seems ready to be replaced with something better, except it doesn't seem to be producing the sort of "close, but not quite" results that led us from Newton to Einstein.  There may be more elegant theories around -- string theory gets a lot of attention in this regard -- but nothing, so far, clearly more powerful.  If there's a more "natural" theory, nature doesn't seem keen to lead us to it.


This feeling that the world has to be more elegant than our current theories may just be an occupational hazard of physicists, and not necessarily the majority at that.  Plenty of working particle physicists are content to "shut up and calculate" without worrying too much about what it all might "mean" or whether the universe has some deep hidden simplicity.

Many chemists would shake their heads at the whole business.   There are around a hundred elements one can do meaningful chemistry with, each with its own particular properties.  That's not going to change with a new theory of chemistry.  There is a theory, namely the Standard Model, which explains why those elements are the way they are, and quantum effects definitely come into play in chemistry, but from a chemist's point of view it doesn't matter how many parameters the Standard Model has.  It matters what the electrons are going to do in a particular situation.

In my own field there are several models that can define the behavior of computers, and we do refer to them (particularly state machines and stack machines) from time to time, but there is not and is never likely to be a unified theory of software engineering.  And yet the servers still run.  Mostly.

Even mathematics, which can almost be defined as the relentless pursuit of elegance, is full of quirky, inelegant results.  What's so special about manifolds in four dimensions?  Why are there 26 sporadic groups?  Why is the 3N+1 problem so hard?  And let's not even get started on the prime numbers.



Suppose that everything in the universe could be precisely described by three simple rules ... and a table of three quadrillion quadrillion seven-digit numbers.  Even storing such a table would be completely infeasible using today's technology, but suppose we meet up with an alien race with full access to it.  Our best physicists pose them questions, they consult the table and deliver a verifiable answer every time (how to reduce any measurable question and its answer to an invocation of three simple rules is an interesting question, but roll with it).  Would we say the aliens have a good theory?

On the one hand, of course they do.  The hallmark of a good theory is making testable predictions that hold up.  On the other hand, there's something less than satisfying about a planet-sized table of numbers, each essentially its own arbitrary parameter.  What happens if our aliens go away or decide that we're not worthy of True Knowledge?  Maybe we should start asking questions that will reveal the nature of the magic number table and, ideally, allow us to reduce it to something our puny minds and computers can handle.

A good theory doesn't just have to be true in the sense of making true predictions.  It also has to be comprehensible and usable.  To this end, a theory with a thousand fairly simple rules and three or three hundred parameters with values we just have to accept is far better than the one I just described.  But this is not saying anything about nature.  It says something about us.  Our "natural" theories are the ones that work best for us, not just in aligning with nature, but with our resources and the way our minds work.

From that point of view, 19 is not a prohibitive number of parameters the way three quadrillion quadrillion would be.  If that's really how it is, we can probably live with it.  But the distinction is of degree, not kind.  The problem is not with arbitrary parameters themselves, but with having an intractable number of them.  Consulting our hypothetical aliens with knowledge beyond our ability to process is really just another kind of experiment from our point of view.   Consulting the Standard Model with its human-friendly list of parameters is better, and it would be even if its predictions weren't quite as good as they are.  It's certainly better than a more "elegant" theory that doesn't fit experiment as well as it does.

Nature is what it is.  A theory is only "natural" if it fits with our nature in particular as well as nature at large.

[Re-reading this, I realize I neglected to say that, although the basic equation of the standard model is fairly compact -- you can get a T-shirt with the Standard Model Lagrangian on it -- actually finding solutions for all but the simplest conditions is generally far beyond our computing ability.  In one sense this is more than a bit like the aliens-with-the-numbers scenario, but instead of a hidden table of numbers we can't begin to access, we have an equation we can barely begin to compute.  Except maybe with quantum computers ... --D.H.]


Re-reading Hossenfelder's piece, I see one more subtle point.  The main argument doesn't seem to be that there can't possibly be an elegant theory unifying quantum physics with relativity, or even a better way of explaining the results of the Standard Model.  Rather, a search for "elegance" or a "natural" theory is no longer a good way -- if it ever was -- of deciding what particle experiments to run next.  If we do find such a unified theory, it's probably not going to be because we found a more elegant replacement for the Standard Model, or because we found an unexpected particle with a new, more powerful accelerator, but because we found something else entirely and a theory to explain it that happens to subsume the Standard Model.

Can we prove a dog is happy?

The previous post talked about qualia, or subjective experiences, but why should we care?  This being a matter of philosophy, there are a variety of answers to that, starting with "Why care about anything?" but nonetheless, there seems to be something significant about the question.  At least from my own subjective point of view.

For one thing, it seems like one of those fundamental questions.  How can we come to a complete understanding of the universe without understanding how we experience it?  Perhaps more than that, there are ethical concerns.  If we wish to increase happiness or we do not wish to cause unnecessary suffering in the world, we should understand what happiness and suffering are.  Outward appearances will only tell us so much.  It would be good to have more reliable indicators, or at least to know how reliable the ones we have are.

The problem with subjective experiences, though, is that they are subjective.  I can be well convinced that my own subjective experience is real.  Sentio ergo sum -- I feel, therefore I am.  There are several reasons for me to believe that someone else's feelings are real: I can see their reactions, they can tell me, and we know that humans have, for the most part, essentially the same neural apparatus.

Nonetheless I cannot know for sure what another person's feelings are in the same way that you and I could both put the same object on a balance scale and agree on its mass.  Each of the common-sense indications I just gave can fail.  Someone may not react visibly to a feeling or experience, or I may not catch the reaction.  They may not be able to tell me for any number of reasons.  Different people can have different ranges of feeling -- what seems intense to me might seem like nothing special to you, or vice-versa.

From a purely philosophical point of view we don't know for sure that having the same kind of neural pathway means having the same kinds of experiences.  Perhaps the ability to experience requires both a certain type of pathway and something else intangible that not everyone has.   Even if there is no such intangible, we're still far from knowing what physical pieces are associated with experience, though we do have some clues.  Without knowing just what pathways gives rise to subjective experience we have no way to be sure everyone has it.

When we go beyond human experience to other species, which react differently, can't verbalize their experiences (or at least not in ways we can presently understand), and have clearly different neural circuitry, we have even less to go on.  We can presume that a dog wagging its tail and barking when its human returns is happy, but it's always possible that dogs have simply co-evolved with us for long enough that they are able to act happy when that would be to their advantage (most people with dogs would dispute this, I expect).

Artificial constructs are even more problematic.  If I build a robot that avoids walls even if you push it toward one, it's easy to say "it doesn't like walls" because it's acting like a sentient being that disliked walls would, but it seems a much bigger step to say "it avoids walls because it experiences negative emotions when it's near one", particularly when we can point to the exact code that causes it to avoid walls.

Even if the code for the control system is extremely complex or has gone through some sort of machine learning process to develop an avoidance of walls, so that we couldn't point to exactly what was making it avoid walls, it still seems hard to argue that the robot is feeling emotions.  If incomprehensible code were the basis of sentience, there would be a lot of sentient software around.

When it comes to what we generally refer to as inanimate objects, the best we can say is that we have no reason to believe that a rock feels pain if we smash it with a hammer.  Nothing in our understanding of how we feel pain seems to apply to something like a rock.  Even so, how can we really know?


But how do we know anything?  We have no way of knowing whether we really live in a universe where the laws of physics hold.  It's possible that tomorrow things dropped will fall up instead of down.  Some theories of cosmology assign a non-zero (but still exceedingly small) chance that we live in such a universe.

In the absence of certain knowledge all we can do is try to build a coherent framework and constantly test and adjust the assumptions it rests on, a process we call "science".  From a scientific point of view we can figure out what sort of neural structures correspond with the subjective experiences that people report.  We can assess whether other organisms have such structures and even whether a particular combination of hardware and software has something functionally equivalent.

We can tell whether something's reactions to various stimuli are consistent with it having such capabilities, based on what people have reported.  We can conclude from that that it's likely or unlikely that the organism or construct we're examining is experiencing feelings, but we can never know for sure, no matter what philosophical machinery we develop for understanding qualia.

But this is nothing new.  Recently it was announced that gravitational waves had finally been detected, stemming from the collision of two black holes over a billion years ago.  The chain of inferences that rests on is mind-boggling.  A more accurate statement would have been "In two separate places, specially constructed instruments registered a signal that indicated that test masses had moved, over a distance much less than the size of an atom, in a way that indicated that space-time had been distorted in a way consistent with the collision of two black holes over a billion light-years away.  We feel confident about this because we believe that science works in general and we're convinced by a large web of observations and theoretical conclusions that the observable universe is billions of years old and billions of light-years in extent, black holes exist and, consistent with a distinct but overlapping web of observations and theoretical conclusions, in certain cases they should produce detectable gravitational waves.  We have also done extensive measurements to convince ourselves that the detectors are in fact detecting gravitational waves and not just trucks driving by ..."

And that would be the short version.  The full version fills textbooks and takes entire careers to grasp even a small portion of.

If science can accept that, can it come to accept that a dog is happy?

Not exactly.  The sticking point here is not whether we can accept a long chain of inference like "People report feeling happy when certain neurons are firing in certain ways, they behave in certain ways when this is happening, dogs have analogous neural pathways, and these tend to fire when dogs are engaged in behavior analogous to that of happy people, and/or people report that the dogs seem happy."  That's not a problem, particularly not compared to the detection of gravitational waves.

The problem is that science depends fundamentally on objective, repeatable measurements of numbers.  Happiness is subjective, and happiness is not a number.  Science can get quite close to measuring happiness, but it's up to us to decide where to go from there -- just like with any other scientific result.

Qualia, or why do we experience anything at all?

Today I'd like to discuss a topic which has baffled (at least some) philosophers for quite some time and which I am even more ill-qualified to address than usual.  Since I'm giving general impressions from general ignorance I'll be citing a few well-known examples without attribution.  You can find a good summary here, or it least it seemed like a good one to me.  Rest assured I'm not claiming to be doing any original work here, just ... conjecturing.

The term qualia has come to encompass experiences, and in particular subjective experiences.  For example, what is it like to see the color red, or what is it to be a bat.  Such experiences seem to be subjective, in that the experience depends, at least in principle, on who's experiencing it.  To take a very old example, cliche but no less valid for being cliche, I have no obvious way of knowing whether you experience the color red in the way I do.  Perhaps you experience it the way I experience the color blue, and vice versa, or perhaps you experience it some completely different way.

For that matter, how do I know that you experience anything?  If you and I are at an intersection, stopped at a red light, I can see you react to the light turning green, but that doesn't mean that you had the same experience I did of seeing a red light and then a green light.  I assume that you experienced the sensation of something red and then something green, and that the color red seemed essentially the same way to you as it did to me, but how would I know?

Suppose you were actually in a self-driving car browsing the news on your phone.  You didn't see the light at all.  Rather, the car's cameras recorded the light changing and the car's control system caused the car to go when the light turned green.  I'm perfectly comfortable saying "The car saw the light change and drove through the intersection when it turned green", anthropomorphizing the car, but that doesn't mean I think the car experienced the colors red and green in anything like the way you or I would (or at least, I think you would).

Trying to account for distinctions like this in some objective way has been referred to as "the hard problem of consciousness", as opposed to easier, more empirical problems like "How does the brain record memories?" or "To what extent are we conscious of our own decisions?"

In some sense it's quite likely that all experiences are distinct.  If I see a red paint chip today and then again tomorrow, I will almost certainly have different associations each time.  The first time might put me in mind of a stop sign, or blood, or a red apple.  The second time I might be more focused on whether it's the same paint chip I saw yesterday.  Likewise, you will almost certainly have different associations than I will even if we're looking at the same chip.

And yet, we would probably all agree that we are experiencing seeing something red, and that it feels like something to have that experience.   Even if there's no emotional response, you're still having some sort of experience.  How do we account for that?

Suppose we could account for every firing of every neuron in the nervous system (including the optic nerve, which is actually doing quite a bit of processing before the signal even gets to the brain).  Have we accounted for the experience?  Suppose that after decades of research we compile an exhaustive list of experiences and how they correlate to brain activity.  We bring in a new subject and scan their neural activity.  Pointing at a display, we say "That pattern of firing always occurs in response to seeing the color red".  We can say "that person is experiencing the color red", but how, exactly, do we know that for sure?

It's not hard to imagine what kind of data would back this up.  We hook hundreds of subjects from all over the world and all walks of life up to our highly-advanced brain scanner, flash colors at them and note the results.  We may even ask them to describe what they're experiencing.  When we see the same patterns for our new subject it's a reasonable inference that their brain is processing the color red, and it's reasonable to expect that if we ask them what they're experiencing, their answer will involve the color red.

That's probably good enough for a cognitive scientist, but not a philosopher.  The philosopher may well insist that you don't know what the subject experienced, but only how they would answer a question.  They -- and for that matter any of your other subjects -- might just as well be philosophical zombies who exhibit all the expected behaviors and responses without actually experiencing anything.  We may know intuitively, but we can't prove that the test subjects aren't just like the self-driving car, only on a more elaborate level.


There are a couple of ways out of this.  One is to deny that qualia exist in any well-defined way.  From a logical point of view, this seems quite plausible.  We can talk about the abstract concept of redness, but in real life we don't experience redness in the abstract.  We experience a particular something red at a particular place and time.  That feels a particular way at that place and time, and quite possibly nothing has ever felt quite the same before or ever will.  Maybe we should just stick to our knitting and figure out what happens in real brains in response to real stimuli.  We can still generalize and define abstractions, but if we want an objective description of the world we have to start with objective data.

And yet, we still experience things, subjectively, each of us (or at least I'm pretty sure about me).

So how do we distinguish between a person at a stop light and a self-driving car?  Maybe we don't need to make a strong distinction.  Maybe we're ... not so different.

There's no particular reason, beyond our innate sense of specialness, to assume that only human beings can have experiences.  If we see a hungry dog, our intuition tells us the dog is experiencing hunger.  Our intuition is probably right.  The dog may not be having exactly the same kind of experience we do, but there's no reason to assume it's a philosophical zombie that only looks like it's experiencing hunger.

One way of handling this is to assert that along with the physical properties of the world -- mass, position, velocity and so forth -- there is an experiential component that's completely distinct but which we might still be able to reason about.  Perhaps we will even discover laws that govern it and develop a comprehensive theory of experience.

One objection to this approach is that it seems to imply panpsychism, the idea that everything has consciousness.  There are already schools of thought that believe exactly that, but the concept doesn't sit particularly well in materialist circles (materialist in the philosophical sense).

However, this seems misguided.  If consciousness in the sense of being able to experience qualia is a property in a way similar to mass being a property of things, that doesn't mean that everything has to have that property.  Just as photons are massless, there's no contradiction in saying a rock is unconscious.

Rather than stating that everything has consciousness, we are asserting that objects can have consciousness, and we are trying to investigate under what circumstances that happens.  However, we are explicitly punting on the question of how it has consciousness.  We are saying that when the conditions are right "it just does", just as when a particle interacts with the Higgs field it has mass* (I believe physics has a more detailed account of this than "it just does", but at some point even physics has to make some base assumptions).

From that point of view it's still reasonable to say that a rock has no feelings or consciousness, but a human does, a dog does and just possibly a self-driving car has some limited degree of consciousness as well.  Moreover we may be able to prove that in the scientific sense of having a coherent theory and data to support it.  If so, it seems this theory will look a lot like a purely material explanation of memory, attention and other aspects of consciousness, together with an assertion that when certain of these are present, the thing in which they are present experiences qualia.

What is it to be a self-driving car?  Probably not much, but perhaps something.

* [That's not a really rigorous way to phrase that, but I don't know well enough to give a better one --D.H.]