I see this post getting trashed in the comments for its overly literal interpretation of personality as a reinforcement learning process, but I think there's some value to it as a mental model of how we operate (which is how the opening sentence describes it).
If you can see past some of the more dubious, overly technical-sounding details and treat it as a metaphor, there is for sure a "behavioral landscape" that we all find ourselves in, filled with local minimal, attractors/basins and steep hills to climb to change our own behaviors.
Thinking about where you are and where you want to be in the behavior landscape can be a useful mental model. Habit changes like exercise and healthy eating, for example, can be really steep hills to climb (and easy to fall back down), but once you get over the hump, you may find yourself in a much better behavioral valley and wonder how you were stuck in the other place for so long.
the essential idea is that personality is malleable, there are concepts in NNs that are analogous to experience we can use to name, deconstruct, orient, and contrast, and as a way to exercise some agency over our own personalities.
you can choose it, and like "the five monkeys experiment"[1] after a while, you don't remember the things you don't believe anymore.
the author used trauma, env change, extreme experiences and psychedelics as examples, but something as simple as reading a book or a comment on a forum can detach us from beliefs and ideas that moored our personality in a local basin. we are the effects of feedback, so change your feedback.
This kind of mental model (some variation of it of course), despite being trashed by the majority, is now becoming the zeitgeist in tech circles. I could have written a very similar blog post (modulo worse writing and more being made fun of), and so could many engineers working on AI. The meta implications of this on the larger society could be interesting.
There's an additional aspect to the dynamics, which is that the social spaces you put yourself in change the landscape to discourage deviancy from the norm. You become like the people you spend time with.
This article approaches human psychology from the perspective that, we are all neural networks and our output (actions) are all a learned function of our inputs (experiences).
This is a common (and convenient) perspective, especially among engineers, but doesn't reflect reality particularly well. We know large swathes of a person's personality is directly linked to their genetics.
The article extrapolates this neural network perspective onto other topics like, mental disorders and depression. The solution is made clear then - just learn how to not be mentally ill! Again, convenient. But not really reflective of reality.
That’s not how I read it, I think you’re missing some nuance here.
The article doesn’t imply genetics have no effect, it just treats them as a baseline which are then adjusted over time according to the person’s lived experiences.
Likewise with mental disorders and depression, the “solution” you claim it states as “not being mentally ill” is the outcome of a process, not the process itself.
The process itself, as far as I can tell from the article, seems to be "increase your learning rate", "change your environment", "meet new people", "take psychedelics".
My point is not that doing these things is never beneficial (well, one may argue about the psychedelics lol), just that it oversimplifies the problem space (and solution space) to the point of not being useful advice.
I've made the jump from physics to neuroscience, so I can talk to the engineers here (I've taken a lot of EE and worked professionally in it too).
The linkages between neurons is somewhat similar to how and RNN looks. But you must remember, there are electrical and chemical elements going on here. It's not just one neuron spiking another. There are many different biochemical processes that modify the behavior of little parts of a neuron, stoichiometrically. And there are many different types of neurons and they all change over time, sometimes drastically so. Most of the goings on is biochem. It's not digital, or even analog. You really need to go down to the field equations at times, finite elements will get you far, but only just so.
RNNs thinking certainly will help you understand better what is going on in a brain, but, like, these things are millions of years old, and optimized just to make more of themselves, not to be understood. It's tough going, and we as a species are only at the very beginning of hundreds of years of study of the brain.
If you'd like to learn more, I can recommend some texts.
> and optimized just to make more of themselves, not to be understood
There is also pressure for it to avoid outputs such are too predictable, as part of a constant arms race against predators and same-species competitors. (For example, how many predators are instinctively key to certain prey behaviors, and when you violate their expectations they might back off.)
That goal doesn't guarantee that the mechanics themselves will be obfuscated, but it does trend in a similar direction.
>The solution is made clear then - just learn how to not be mentally ill! Again, convenient. But not really reflective of reality.
And you know this because?
Cutting edge theories of depression link it to alterations in the reward learning system. There is some evidence that training persons with depression to attend to certain aspects of the reward learning mechanism can reduce depressive symptomology [I am involved in this research]. But speaking more broadly, cognitive behavioral therapy, one of the most successful non-pharmaceutical treatments for depression, involves people "learning how not to be depressed" by unlearning problematic patterns of negative thinking and coping with negative events: first by recognizing what those problematic thoughts and behaviors are, and working to adjust those ... to move you out of that basin.
The main issue with this article imo is that it does not consider the meta-problem: how the reinforcement learning system can be altered by experience as well.
CBT can work, sure. It can also not work. As with any treatment.
And depression is only one mental illness, there are countless others. And there are also many different forms and causes of even depression itself.
As I mentioned in another comment, my point isn't that the article's advice is necessarily harmful, just that it oversimplifies a lot of things by assuming that all psychology can be boiled down to learning and unlearning. Ignoring the role of biology may also cause one to ignore possible paths to progress.
you can also learn to cope with mental illness with more or less self-destructive responses. not everybody gets a chance to learn healthier coping mechanisms.
Not everyone can just learn such coping mechanisms. Some people have physical problems that need physical help/remediation. Of course, our current psychiatric drugs are their risky attempts to help such folks. It is all very tricky, but we should all learn how to have better attitudes and behaviors.
> This is a common (and convenient) perspective, especially among engineers, but doesn't reflect reality particularly well. We know large swathes of a person's personality is directly linked to their genetics.
I really am not an expert in any of this. Just my quick thoughts of the idea about genetics and "being born with it".
If we're attempting to create a mental model of how machine neural networks relate to human brains, would it be useful to think of genetics as the basis that determines your neural network's architecture? Maybe there's even some pre-trained weights that are communicated through genetics.
I think it would be oversimplification to say we're all born with the same neural network and pre-trained weights because like you've mentioned: large swathes of a person's personality is directly linked to their genetics.
This is noted and considered out of scope:
>Obviously some traits are more genetic, and thus inherent, than others, but that is not the scope of this post as even highly-heritable traits will result in a large distribution of outcomes.
But what if it's possible to alter your influential genes, through some powerful mechanism? Whether it be through insane willpower or anything else. In that case, you have an analogy like something like artificial general intelligence or recursive self-improvement. We get to approach the discussion of questioning natural values and instinctive goals with this line of inquiry. We get to eventually question the metaphysics of God, morality, and aesthetics, by introducing fantastic elements like radical self-modification.
Natural selection encodes adaptive responses to the environment in DNA (and other molecules), so memories can be encoded to the extent that they are adaptive and can be encoded (i.e., mechanisms may not exist to encode everything using only standing natural variation).
> A common mistake in life is to let your personality basin solidify too early. Your parents and schooling environment have a disproportionately large influence on who you become as an adolescent.
> But as soon as you gain the freedom to act independently as an adult, it’s usually a good idea to force yourself to try as many new things as you can, including moving cities (or countries!) and considering drastically different lines of work. ...
Oh dear, I'm beginning to fear that the author's personality has been captured by global capital...
And what if it's personality capture all the way down, i.e. that you've got to be personality captured by someone? In that case, the closest you can get to a choice is whether it's your parents, religion, or someone/something else. While the integrity of your parents may vary, there is a subjective argument that they've got a better incentive to steer you into an optimal basin than anybody, relatively speaking.
> there is a subjective argument that they've got a better incentive to steer you into an optimal basin than anybody, relatively speaking
Many parents do not have their kids best interest at heart; from religious fanatics to divorced parents using their kids as pawns to failed athletes living vicariously through their "he'll be in the NHL someday" fantasies to just parents who didn't want have kids and don't care at all.
Then there a whole slew of parents who genuinely want what is best for their kids but won't succeed due to incompetence or their own issues with drug addition or passing on generational trauma.
The quotation in the GP’s post does seem to evince little appreciation (if not outright disdain) for ties to family and local community across the generations. But what if the potential harm caused to some kids by bad parents, is an unavoidable part of the social-cohesion benefits to all society that would be caused by young people not moving far away?
I don’t necessarily want to have a dog in this fight myself. But I immediately thought of how that quotation would jar with some cultures represented on HN, where children stay close to parents all their lives and it is widely felt that the West is doing it wrong.
I’m reasonably sure that religious fanatics usually have their children’s best interest at heart. Their value function is just different from that of less religious people.
One of the more depressing things of the AI boom is watching engineers and “atheists” get hoodwinked by mystic gibberish like this blog. There is nothing here but astrology: even Myers-Briggs is more scientific.
I think 30% of atheists bothered to think carefully about the Flying Spaghetti Monster and recognized Pastafarianism as a funny commentary on epistemic uncertainty. The remaining 70% said “heh, stoopid Christians believe in a spaghetti monster!” and took it as confirmation of their tribe’s superiority.
It's an application of chaos mathematics to personality development. It isn't a rigorous treatment of such, it's a blog post, but it seems fairly reasonable.
Being a blog post and not necessarily intended to end up on Hacker News, shorn of any other context, the author never even used the term "attraction basin", which is the term you'd want to Google if you want to figure out what the author is saying.
If you don't know what an attraction basin is, then yeah, this definitely comes off sounding bad, but if you know what it is it makes sense. Attraction basins are one of those basic concepts from chaos mathematics that, once you realize what they are and why they are, you realize that the world can't help but be full of them in all sorts of places, including human personalities. The world is fundamentally iterative, so patterns that arise in all iterations are relevant all over the place.
Attraction basins are a good reason to expect in advance, sight unseen, that human personalities can actually be fit into a relatively small number of buckets relative to the conceivable number of buckets that could exist. In fact this is true of any generally similar set of entities living in a generally similar environment, including AIs (of similar architectures, not the entire space of possible AIs) and aliens, assuming they also have some sort of "species" categorization as we do. (Which doesn't have to be "DNA genetics", just, a bunch of similar being for whatever reason.) It doesn't tell you what those will be in advance by any means; it just gives you reason to believe that you won't in fact be looking at an "unbiased", uniformly random distribution of personality parameters, but that they will collect around certain attraction basins in general.
I have not read this blog except the linked blog post, but could you be more specific on what you think is mystic gibberish?
Speaking as someone who works in clinical neuroscience, the basic picture being presented is similar in many respects to the informal model I carry around. It may be lacking in certain details, but big picture seems to me that it has a lot going for it as a guide to intuitions.
Personally I've always found, ironically, some of my most ardent atheist friends to essentially treat the topic with a level of intensity you might expect from a religious evangelist. Often there's also a level of religious fervor they carry over to politics as well.
I don't really care what other peoples religion/non-religion is anymore than what type of underwear they prefer, and yet...
Feeling strongly about lack of belief in something wild without evidence is not congruent to strong belief in something wild without evidence. Even if the people in the former camp can be equally passionate or annoying.
Suddenly there's this big unnamed (or is it named and I don't know it?) cognitive error that I see everywhere that is believing in an automatic symmetry between two opposing viewpoints. Sometimes one idea is better than another. No, you don't get "objectivity" points for virtue signaling that you're above the whole debate.
We already know that our science can simply not explain/understand what happened in the first 10e-33s after the Big Bang, which is just established science.
There is nothing more "negatively religious" than believing that nothing caused that primal explosion of all that is. Unfortunately, they then proceed to throw out the positive aspects of some religious teachings concerning, e.g., compassionate concern for our fellow human beings.
Regardless, religion is a personal thing; forcing any beliefs on others is always a problem and must be prevented. We are all free to choose our attitudes and behaviors. Behaviors that harm others, however, must -- in a just system -- be dealt with by the society, for the benefit of the whole, irrespective of belief system of perpetrator or victim. Using compassion to make such decisions is always the best way, for varying values of compassion.
i agree with your sentiment, but it bears pointing out that no one brandishes their underwear in people's faces screaming that they must wear the same ones, or use the political system to privilege people of the same underwear and punish others etc etc
fwiw me personally i'm all in on uniqlo airism, there is no better underwear and if i could force everyone to wear them i would (for their own good, of course)
I agree that it can be helpful to think of identity as a trajectory shaped by interactions along the way. However, we also continually shape our environments in large and small ways. TFA ignores this completely. Can this be effectively modeled in RL?
Over 130 years ago, Dewey [1] criticized the model of psychology which looked at human behavior in terms of stimulus -> internal processing -> response. Stimuli don't just come to us; we seek them out and modify the world around us to cause them to occur. Dewey and other pragmatists proposed reframing stimulus/response in terms of "acts" or "habits," or changes to the unified agent+environment. Popper was getting at the same entanglement of agent and environment in "Three Worlds" and Simon in "The sciences of the artificial."
I see RL as an elaboration of the stimulus/response paradigm: the agent is discrete from the environment. Does RL work well in an environment like Minecraft, where the real game is modifying the relationship between actions and future states? What about in contexts like Twitter, where you're also modifying the value function (e.g. by cultivating audiences or by participating in a thread in a way which conditions the value function of future responses)?
"I agree that it can be helpful to think of identity as a trajectory shaped by interactions along the way. However, we also continually shape our environments in large and small ways. TFA ignores this completely. Can this be effectively modeled in RL?"
You don't need to. All that is necessary for an attraction basin to emerge is an iterative system. If you prefer to model the human being and their entire environment rather than the human being and their input, you'll still get attraction basins. You'll just get two views on the same reality, suitable for different uses and different understandings, but it's not like "ah, if we model a human iterations we get these attraction basins but if we include environmental interactions suddenly we get a uniformly random distribution of personalities across the total personality space, it's all totally different once you consider the environment as part of the iterative system too".
Thanks; I agree--both that you could train an agent in these situations, and that "You'll just get two views on the same reality, suitable for different uses and different understandings." I think the latter seriously undercuts the article's attempt to explain these trajectories in terms of personality; they could just as easily be attributed to the power of culture or social structure.
I agree that the discussion in the blog post is incomplete because it does not consider that we shape the environments that shape us, though it does briefly touch on the fact that other RL agents (people) try to shape us, and we them. But it is certainly more than that.
> How do you know if you're in the "right" personality basin
I'm not so sure "right" is the right frame here. I like the multi-dimensional viewpoint you take. My experience would be a healthy personality would be one capable of adaptation in service of your interests at any times. It's dynamic.
This reminds me of Bob Kegan's stage of adult development. Initially, most of us leave adolescence at the "socialized" stage of development, ie our personality basin has primarily been determined by the external factors of our upbringing and environment.
From there, if we choose to continue developing, we eventually reach a "self-authored" mind, where we have transcended our socialized basin in favor of a self-defined and created personality structure, until ultimately, for those who continue evolving, we reach a "self-transforming" mind, or a mind capable of transforming itself.
I like the simplicity of the model, and I also think it reduces personality to an unnecessarily static entity. Things like internal family system/parts work also demonstrate that our personality is not a singular entity, it is represented by a whole slew of parts that show up in different ways and different contexts! I think the broad strokes of it still hold, and also think there are many additional approaches to truth and the awakening path, lying in parts work, embodied transformation, and whole bunch of other experimental modalities (thought perhaps that's just my personality speaking...)
Personality is ~70% determined by genetics, not life experience.[0]
I’m surprised that someone interested enough in the topic to write such a long post wouldn’t put the time in to do a cursory dive into personality psychology. I’m going to assume that the author has a similar definition of personality to mainstream psychology, but if so, they are ignoring accepted studies and evidence that make it pretty clear that personality is not learned through conditioning like AI.
There's no practical point in separating genetics from life experience, as they go hand in hand together.
Someone who has the genetics to be physically attractive/beautiful will have a completely different set of experiences than someone who isn't. Same goes for intelligence.
Also, the source you linked only pertains to IQ (which itself is not a perfect measure of intelligence), and IQ is not personality (although I have met some folks who do treat their IQ as a substitute for such).
The analysis of the data revealed no significant difference between MZA twins (reared apart) and MZT twins (reared together) in regards to personality measures such as temperament, hobbies, interests, career pursuits or social attitudes.
This is noted and considered out of scope:
>Obviously some traits are more genetic, and thus inherent, than others, but that is not the scope of this post as even highly-heritable traits will result in a large distribution of outcomes.
Sure, and they even go on to say that the article is about “what helps to explain the differences in outcome between two genetically identical people.” However it’s clear that is not actually what the article is about and they do talk about traits that are highly heritable and not shown to be dependent on environment and life experience.
I enjoy how people are dunking on this by saying “omg this is what happens when engineers dare to have thoughts on other topics” when this is very similar to the theory for CBT in psychology
Readit News
If you can see past some of the more dubious, overly technical-sounding details and treat it as a metaphor, there is for sure a "behavioral landscape" that we all find ourselves in, filled with local minimal, attractors/basins and steep hills to climb to change our own behaviors.
Thinking about where you are and where you want to be in the behavior landscape can be a useful mental model. Habit changes like exercise and healthy eating, for example, can be really steep hills to climb (and easy to fall back down), but once you get over the hump, you may find yourself in a much better behavioral valley and wonder how you were stuck in the other place for so long.
you can choose it, and like "the five monkeys experiment"[1] after a while, you don't remember the things you don't believe anymore.
the author used trauma, env change, extreme experiences and psychedelics as examples, but something as simple as reading a book or a comment on a forum can detach us from beliefs and ideas that moored our personality in a local basin. we are the effects of feedback, so change your feedback.
[1] https://skeptics.stackexchange.com/questions/6828/was-the-ex...
Dead Comment
This is a common (and convenient) perspective, especially among engineers, but doesn't reflect reality particularly well. We know large swathes of a person's personality is directly linked to their genetics.
The article extrapolates this neural network perspective onto other topics like, mental disorders and depression. The solution is made clear then - just learn how to not be mentally ill! Again, convenient. But not really reflective of reality.
The article doesn’t imply genetics have no effect, it just treats them as a baseline which are then adjusted over time according to the person’s lived experiences.
Likewise with mental disorders and depression, the “solution” you claim it states as “not being mentally ill” is the outcome of a process, not the process itself.
My point is not that doing these things is never beneficial (well, one may argue about the psychedelics lol), just that it oversimplifies the problem space (and solution space) to the point of not being useful advice.
So like the randomization process that seeds the values for RNN weights?
The linkages between neurons is somewhat similar to how and RNN looks. But you must remember, there are electrical and chemical elements going on here. It's not just one neuron spiking another. There are many different biochemical processes that modify the behavior of little parts of a neuron, stoichiometrically. And there are many different types of neurons and they all change over time, sometimes drastically so. Most of the goings on is biochem. It's not digital, or even analog. You really need to go down to the field equations at times, finite elements will get you far, but only just so.
RNNs thinking certainly will help you understand better what is going on in a brain, but, like, these things are millions of years old, and optimized just to make more of themselves, not to be understood. It's tough going, and we as a species are only at the very beginning of hundreds of years of study of the brain.
If you'd like to learn more, I can recommend some texts.
There is also pressure for it to avoid outputs such are too predictable, as part of a constant arms race against predators and same-species competitors. (For example, how many predators are instinctively key to certain prey behaviors, and when you violate their expectations they might back off.)
That goal doesn't guarantee that the mechanics themselves will be obfuscated, but it does trend in a similar direction.
And you know this because?
Cutting edge theories of depression link it to alterations in the reward learning system. There is some evidence that training persons with depression to attend to certain aspects of the reward learning mechanism can reduce depressive symptomology [I am involved in this research]. But speaking more broadly, cognitive behavioral therapy, one of the most successful non-pharmaceutical treatments for depression, involves people "learning how not to be depressed" by unlearning problematic patterns of negative thinking and coping with negative events: first by recognizing what those problematic thoughts and behaviors are, and working to adjust those ... to move you out of that basin.
The main issue with this article imo is that it does not consider the meta-problem: how the reinforcement learning system can be altered by experience as well.
And depression is only one mental illness, there are countless others. And there are also many different forms and causes of even depression itself.
As I mentioned in another comment, my point isn't that the article's advice is necessarily harmful, just that it oversimplifies a lot of things by assuming that all psychology can be boiled down to learning and unlearning. Ignoring the role of biology may also cause one to ignore possible paths to progress.
you can also learn to cope with mental illness with more or less self-destructive responses. not everybody gets a chance to learn healthier coping mechanisms.
I really am not an expert in any of this. Just my quick thoughts of the idea about genetics and "being born with it".
If we're attempting to create a mental model of how machine neural networks relate to human brains, would it be useful to think of genetics as the basis that determines your neural network's architecture? Maybe there's even some pre-trained weights that are communicated through genetics.
I think it would be oversimplification to say we're all born with the same neural network and pre-trained weights because like you've mentioned: large swathes of a person's personality is directly linked to their genetics.
Sounds like epigenetics, where the environment actively influences the genes themselves: https://en.m.wikipedia.org/wiki/Epigenetics
Eg, perhaps some of your genes’ purpose are to encode memories in DNA.
> But as soon as you gain the freedom to act independently as an adult, it’s usually a good idea to force yourself to try as many new things as you can, including moving cities (or countries!) and considering drastically different lines of work. ...
Oh dear, I'm beginning to fear that the author's personality has been captured by global capital...
And what if it's personality capture all the way down, i.e. that you've got to be personality captured by someone? In that case, the closest you can get to a choice is whether it's your parents, religion, or someone/something else. While the integrity of your parents may vary, there is a subjective argument that they've got a better incentive to steer you into an optimal basin than anybody, relatively speaking.
Many parents do not have their kids best interest at heart; from religious fanatics to divorced parents using their kids as pawns to failed athletes living vicariously through their "he'll be in the NHL someday" fantasies to just parents who didn't want have kids and don't care at all.
Then there a whole slew of parents who genuinely want what is best for their kids but won't succeed due to incompetence or their own issues with drug addition or passing on generational trauma.
I don’t necessarily want to have a dog in this fight myself. But I immediately thought of how that quotation would jar with some cultures represented on HN, where children stay close to parents all their lives and it is widely felt that the West is doing it wrong.
Deleted Comment
Deleted Comment
I think 30% of atheists bothered to think carefully about the Flying Spaghetti Monster and recognized Pastafarianism as a funny commentary on epistemic uncertainty. The remaining 70% said “heh, stoopid Christians believe in a spaghetti monster!” and took it as confirmation of their tribe’s superiority.
Being a blog post and not necessarily intended to end up on Hacker News, shorn of any other context, the author never even used the term "attraction basin", which is the term you'd want to Google if you want to figure out what the author is saying.
If you don't know what an attraction basin is, then yeah, this definitely comes off sounding bad, but if you know what it is it makes sense. Attraction basins are one of those basic concepts from chaos mathematics that, once you realize what they are and why they are, you realize that the world can't help but be full of them in all sorts of places, including human personalities. The world is fundamentally iterative, so patterns that arise in all iterations are relevant all over the place.
Attraction basins are a good reason to expect in advance, sight unseen, that human personalities can actually be fit into a relatively small number of buckets relative to the conceivable number of buckets that could exist. In fact this is true of any generally similar set of entities living in a generally similar environment, including AIs (of similar architectures, not the entire space of possible AIs) and aliens, assuming they also have some sort of "species" categorization as we do. (Which doesn't have to be "DNA genetics", just, a bunch of similar being for whatever reason.) It doesn't tell you what those will be in advance by any means; it just gives you reason to believe that you won't in fact be looking at an "unbiased", uniformly random distribution of personality parameters, but that they will collect around certain attraction basins in general.
Speaking as someone who works in clinical neuroscience, the basic picture being presented is similar in many respects to the informal model I carry around. It may be lacking in certain details, but big picture seems to me that it has a lot going for it as a guide to intuitions.
like astrology with extra steps for dorks
I don't really care what other peoples religion/non-religion is anymore than what type of underwear they prefer, and yet...
Suddenly there's this big unnamed (or is it named and I don't know it?) cognitive error that I see everywhere that is believing in an automatic symmetry between two opposing viewpoints. Sometimes one idea is better than another. No, you don't get "objectivity" points for virtue signaling that you're above the whole debate.
There is nothing more "negatively religious" than believing that nothing caused that primal explosion of all that is. Unfortunately, they then proceed to throw out the positive aspects of some religious teachings concerning, e.g., compassionate concern for our fellow human beings.
Regardless, religion is a personal thing; forcing any beliefs on others is always a problem and must be prevented. We are all free to choose our attitudes and behaviors. Behaviors that harm others, however, must -- in a just system -- be dealt with by the society, for the benefit of the whole, irrespective of belief system of perpetrator or victim. Using compassion to make such decisions is always the best way, for varying values of compassion.
fwiw me personally i'm all in on uniqlo airism, there is no better underwear and if i could force everyone to wear them i would (for their own good, of course)
Over 130 years ago, Dewey [1] criticized the model of psychology which looked at human behavior in terms of stimulus -> internal processing -> response. Stimuli don't just come to us; we seek them out and modify the world around us to cause them to occur. Dewey and other pragmatists proposed reframing stimulus/response in terms of "acts" or "habits," or changes to the unified agent+environment. Popper was getting at the same entanglement of agent and environment in "Three Worlds" and Simon in "The sciences of the artificial."
I see RL as an elaboration of the stimulus/response paradigm: the agent is discrete from the environment. Does RL work well in an environment like Minecraft, where the real game is modifying the relationship between actions and future states? What about in contexts like Twitter, where you're also modifying the value function (e.g. by cultivating audiences or by participating in a thread in a way which conditions the value function of future responses)?
[1] https://plato.stanford.edu/entries/dewey/#ReflArcDeweRecoPsy...
You don't need to. All that is necessary for an attraction basin to emerge is an iterative system. If you prefer to model the human being and their entire environment rather than the human being and their input, you'll still get attraction basins. You'll just get two views on the same reality, suitable for different uses and different understandings, but it's not like "ah, if we model a human iterations we get these attraction basins but if we include environmental interactions suddenly we get a uniformly random distribution of personalities across the total personality space, it's all totally different once you consider the environment as part of the iterative system too".
I'm not so sure "right" is the right frame here. I like the multi-dimensional viewpoint you take. My experience would be a healthy personality would be one capable of adaptation in service of your interests at any times. It's dynamic.
This reminds me of Bob Kegan's stage of adult development. Initially, most of us leave adolescence at the "socialized" stage of development, ie our personality basin has primarily been determined by the external factors of our upbringing and environment.
From there, if we choose to continue developing, we eventually reach a "self-authored" mind, where we have transcended our socialized basin in favor of a self-defined and created personality structure, until ultimately, for those who continue evolving, we reach a "self-transforming" mind, or a mind capable of transforming itself.
I like the simplicity of the model, and I also think it reduces personality to an unnecessarily static entity. Things like internal family system/parts work also demonstrate that our personality is not a singular entity, it is represented by a whole slew of parts that show up in different ways and different contexts! I think the broad strokes of it still hold, and also think there are many additional approaches to truth and the awakening path, lying in parts work, embodied transformation, and whole bunch of other experimental modalities (thought perhaps that's just my personality speaking...)
I’m surprised that someone interested enough in the topic to write such a long post wouldn’t put the time in to do a cursory dive into personality psychology. I’m going to assume that the author has a similar definition of personality to mainstream psychology, but if so, they are ignoring accepted studies and evidence that make it pretty clear that personality is not learned through conditioning like AI.
0: https://www.themantic-education.com/ibpsych/2019/02/11/key-s...
Someone who has the genetics to be physically attractive/beautiful will have a completely different set of experiences than someone who isn't. Same goes for intelligence.
Also, the source you linked only pertains to IQ (which itself is not a perfect measure of intelligence), and IQ is not personality (although I have met some folks who do treat their IQ as a substitute for such).
Results
The analysis of the data revealed no significant difference between MZA twins (reared apart) and MZT twins (reared together) in regards to personality measures such as temperament, hobbies, interests, career pursuits or social attitudes.
https://theinfinitesimal.substack.com/p/book-review-eric-tur...