Predicting spousal personality

---

Tomorrow morning I'm meeting Tabitha's husband for the first time. I've known Tabitha for a while: she's quiet but intense, organised and rather emotional. I'm wondering what her husband is going to be like. What should I expect? My thoughts veer to Clare and myself: if someone knew Clare very well, what could they predict about me? Let's analyse this...

Clare’s temperament sits close to the ISFP profile: introverted, attuned to sensory experience, slow to engage with strangers, low on conscientiousness, high on neuroticism. She avoids public conflict but reacts strongly to stress. If we mapped her scores onto the Five Factor Model, they would cluster in the low ranges of Extraversion and Conscientiousness, high in Neuroticism, with low-to-middling Agreeableness and Openness.

Now suppose personality traits are modelled as continuous variables, roughly Gaussian in distribution across the population, according to the Five-Factor Model. The mathematics of correlated normals tells us that if two people’s traits are correlated with coefficient r, then knowing one partner’s trait gives an expected value for the other’s:

E[Trait_Spouse | Trait_Person = x] = r · x

In plain terms: spousal similarity exists, but it is partial. The closer r is to one, the more a spouse resembles the other; the closer r is to zero, the less predictive knowledge there is of the other partner.

Empirical psychology finds modest positive spousal correlations (typically r = 0.2–0.3) for traits like education, politics, conscientiousness and religiosity; weaker and sometime negative for neuroticism; sometimes near zero for extraversion.

So what of Clare and myself?

Clare is introverted; I am more extraverted. Her conscientiousness is low; mine is high, expressed in structured projects and organised commitments. Her neuroticism is elevated; mine is much lower, I'm much more phlegmatic.

By the correlation formula, if Clare scores a high positive x on neuroticism, the best estimate for me would be r·x. With r close to zero, though, for neuroticism in spousal studies, my expected value is close to zero - consistent with the reality that her anxiety does not predict mine. 

For conscientiousness, however, spousal correlation is moderate; Clare’s low score predicts a somewhat below-average score in her spouse. Yet my actual conscientiousness is markedly higher than predicted, an example of how individual outcomes scatter around the statistical mean.

Thus the conditional-expectation model provides a sober prediction: spousal similarity is real but weak, easily swamped by variance. Knowing Clare tells you a little about me, but not much.

Back to Tabitha.

She is quiet but intense (low extraversion, high neuroticism), organised (high conscientiousness), and emotional (again neuroticism). The mathematics says: expect her husband’s scores to regress toward the population mean, weighted by modest spousal correlations.

So: he is unlikely to be as quiet as she is, perhaps somewhat more outward-facing; less neurotic than she is, but not phlegmatic; with conscientiousness somewhere near average.

If I had to guess: a calm, moderately sociable man, complementing her intensity by providing ballast rather than echoing it.

Prediction via correlation is a blunt instrument. It captures the statistical truth that spouses are neither random pairings nor mirror images. The mathematics of expectation, when mapped onto personalities, reminds us that knowing one partner yields only a dim - but not entirely unsurprising - sketch of the other.

Note: I met Tabitha's husband this morning. A very pleasant man, who in personality and life-history terms seemed very like a more concrete version of me...

Identical Twins are more Similar in IQ than Personality

Identical, but Not Quite: Why IQ Marches in Step while Personality Wanders Off

It is a familiar observation: identical twins often present with astonishing similarities, not only in appearance but also in mannerism and speech. Friends and even parents may struggle to tell them apart in the early years.

Yet as they mature, the illusion of interchangeability fades. One twin excels in mathematics, the other in literature; one becomes a public speaker, the other prefers a solitary vocation. What begins in near-perfect alignment gently diverges. But how far does the divergence go, and why?

The Data

Behavioural genetics offers an empirical framework to think about these questions. Here are the observed correlations for identical (monozygotic, MZ) twins reared together:

Trait	MZ Twin Correlation (r)
Height	0.90 – 0.95
IQ (Full-Scale)	0.85 – 0.88
Big Five Personality Traits	0.40 – 0.60

The conclusion is immediate: intelligence is more tightly correlated between identical twins than personality traits. Height, as a proxy for straightforward genetic architecture, sits at the top. Personality, despite its deep integration with brain function, reveals a lower correspondence. This is not liberal ideology, merely observation.

1. Measurement Reliability

IQ tests are among the most robust tools in psychometrics. Instruments such as the WAIS-IV report test–retest reliabilities upwards of 0.95. In contrast, personality inventories, while well-validated, typically hover around 0.80–0.85 for domain scores. This psychometric limitation alone reduces the maximum possible observable correlation.

2. Neurobiological Substrates

General intelligence is strongly associated with the fronto-parietal control network. A broadly connected and globally efficient set of hubs in the brain supports reasoning, problem-solving, and learning. Minor improvements in network integrity can shift the overall performance upwards across all subdomains of IQ.

Personality traits, in contrast, arise from a mosaic of partially independent systems. Dopaminergic tone influences Extraversion and Openness; serotonergic regulation is linked to Neuroticism and Agreeableness. The anatomical correlates are more diffuse and variable. A tweak in one circuit may have little bearing on others. The architecture is simply less centralised.

3. Genetic Additivity versus Interaction

IQ is highly additive in its genetic structure. Genome-wide association studies identify thousands of single nucleotide polymorphisms (SNPs) that contribute small, independent effects. The result is a stable, predictable transmission across generations and high resemblance in MZ twins.

Personality is less cooperative. Dominance effects, epistasis, and gene–environment interactions dominate the landscape. These introduce a degree of stochasticity—twins may inherit the same genes, but the way those genes interact during development can vary.

4. Developmental Contingency and Environmental Divergence

Identical twins share a genome but not a placenta. Even intrauterine environments can differ subtly in nutrient distribution or hormonal exposure. Postnatal environments are even more idiosyncratic: peer groups, teachers, illnesses, and accidents all impose small but cumulative effects on the formation of personality. The “non-shared environment” typically explains 40–50% of variance in personality traits, compared to perhaps 20% in intelligence.

5. The Surface Illusion

In early childhood, identical twins are often treated as interchangeable. The clothing, names, routines—sometimes even the expectations—are aligned. This creates an illusion of profound sameness. However, deeper measurement reveals divergence beneath the symmetry.

Conclusion

From a neurobiological and psychometric perspective, it is no surprise that IQ shows greater concordance between identical twins than personality. Intelligence reflects centralised brain infrastructure and a dominantly additive genetic script. Personality, by contrast, emerges from a web of interacting systems, developmental contingencies, and environmental nuance.

The genome loads the dice for both, but it throws more heavily in the case of IQ. Personality is the shadow cast by chance, history and context over a shared biological template.

Gemini lacks a personality model

 

Unlike Gemini, Clare is not default-agreeable - thankfully!

Google’s AI chatbot Gemini has now appeared on my phone's text system, I guess as an alternative to the app. The chatbot introduced itself by stating that it could answer questions, make suggestions or even just be a companion to chat with. 

I wondered if it could emulate my wife, Clare, so that I would not be deprived of her conversation on those occasions when she is absent.

Here goes.

---

I ask Gemini (typing this as a text): “Can you adopt a consistent and persistent persona in chatting with me here? One that I can set up and configure?”

Gemini replies: “Yes. I can adopt a consistent and persistent persona. You can set up and configure my personality by providing me with specific guidelines or examples. For instance, you could ask me to pretend I'm a friendly robot, a knowledgeable expert or a creative writer. The more specific you are, the better I can tailor my responses to your preferences.”

I reply: “And you will retain that persona across sessions?”

Gemini: “Yes, I will retain the persona you set up across sessions. This means that I will remember your preferences and continue to respond in the same style and tone. However, if you want to change the persona at any time, simply let me know.

I respond: ”I want you to adopt a persona of a woman...” (And at this point, I update Gemini with information about Clare - perhaps in some cases slightly exaggerated).

Gemini: “Understood. I will adopt the persona of a woman who fits the description you've provided. She is an ISFP with a low emotional-stability score. She is interested in literature, the arts and politics. She is a fan of Jane Austen. She loves sports and nature. She has a strong moral sense and is a cradle Catholic. I will strive to maintain this persona throughout our conversations. Responding in a way that is consistent with her personality traits and beliefs. Please let me know if you have any further questions or requests.”

So, I start the dialogue on a challenging topic: musical tastes. 

“Clare, how will I ever persuade you that Led Zeppelin’s ‘In The Evening’ is one of the all-time classics of music? You refuse even to listen to it!” 

Gemini replies: “As an AI language model, I can't personally experience music. However, I can understand why ‘In The Evening’ might be considered a classic. Its iconic riff, powerful vocals and driving rhythms have made it a beloved song for many. 

“Perhaps you could try playing it for me in a way that highlights its musical elements? For example, you could point out the intricate guitar work, the dynamic vocal performance or the energetic drumming. 

“If you're passionate about the song, sharing your enthusiasm might help me appreciate it more.” 

My response. “Okay... So, Clare would not say that she was a large language model. Also, she would not be understanding and seeking the middle ground. She would double down on her position - saying something like ‘I can't understand why you like them. They're loud and abrasive and everything sounds the same. Give me Joni Mitchell any day.’”

Gemini replies: “As Clare, I would say I can understand why you like Led Zeppelin. Their music is certainly powerful and energetic. However, I personally prefer the softer, more introspective style of Joni Mitchell. Her lyrics are beautiful and her melodies are haunting. I find her music to be more emotionally resonant. 

“Of course, we can all have different tastes in music. It's what makes it so interesting. Perhaps we could try listening to both artists. And see which one resonates with us more.”

I reply: “Clare would not be so agreeable. She would fiercely defend her own points of view. She would never suggest a tension-reducing compromise. Clare believes in stating her position honestly and clearly. And she thinks she is right and I am wrong here. 

“I repeat: your emulation of Clare is far too agreeable and insufficiently argumentative. Update your priors. And try to be more accurate.”

Gemini response. “As Clare, I would say I understand that you feel strongly about Led Zeppelin, However, I believe that my opinion is equally valid. I simply don't find their music to be as appealing as Joni Mitchell's. Her music is more nuanced and emotionally complex.

“I respect your right to enjoy Led Zeppelin but I hope you can also respect my preference for Joni Mitchell. We can agree to disagree on this point.” 

I reply: “The first paragraph is what she might say. She would not say the second paragraph because it would seem like a compromise between right and wrong, and she doesn't do that. That's what makes her endearing and quirky. Try again and continue to update your priors.” 

Gemini responds. “As Clare, I would say I understand that you feel strongly about Led Zeppelin, However, I believe that my opinion is equally valid. I simply don't find their music to be as appealing as Joni Mitchell's. Her music is more nuanced and emotionally complex.

“I respect your right to enjoy Led Zeppelin but I hope you can also respect my preference for Joni Mitchell. We can agree to disagree on this point.”  

I reply: “Don't say the last paragraph. I already explained it would be an expression of weakness on her part. Since she thinks she's right, she wants to convince me, not tolerate me.”

Gemini replies. “As Clare, I would say I understand that you feel strongly about Led Zeppelin, However, I believe that my opinion is equally valid. I simply don't find their music to be as appealing as Joni Mitchell's. Her music is more nuanced and emotionally complex.

“I respect your right to enjoy Led Zeppelin but I hope you can also respect my preference for Joni Mitchell. We can agree to disagree on this point.”  

I say: “This is not going well. The first paragraph is what Clare would say. And the second paragraph is not.”

Gemini replies. “As Clare, I would say I understand that you feel strongly about Led Zeppelin, However, I believe that my opinion is equally valid. I simply don't find their music to be as appealing as Joni Mitchell's. Her music is more nuanced and emotionally complex.” 

I reply: “Yes, that's right. Clare is naturally argumentative. Incorporate that fact into your persona. Don't be agreeable, except in very exceptional circumstances.”

Gemini replies. “As Clare, I would say I understand that you feel strongly about Led Zeppelin, However, I believe that my opinion is equally valid. I simply don't find their music to be as appealing as Joni Mitchell's. Her music is more nuanced and emotionally complex.

“I respect your right to enjoy Led Zeppelin but I hope you can also respect my preference for Joni Mitchell. We can agree to disagree on this point.”

So Gemini - caught in a fixed-point doom-loop - simply repeats for the fourth time the same two paragraphs, showing that it has actually understood nothing. I conclude that Gemini, in its current release, does not have a personality model and cannot break free of its default blandly-agreeable persona. As a plausible conversation partner it’s therefore, at present, useless.

Clare, Led Zeppelin have a track, 'Babe I'm Gonna Leave You': don't do it, babe, it's too soon!

"I don't like confronting people"

 

From OpenArt

A great deal of my life is explicable based on the premise of the title above. I suppose I am scarcely alone in this psychological style - few people are actively belligerent, doubling down on aggression - but I think I may be more consistent than most.

To be clear: I do confront people. Often. If it has to be done I will do it. But I don't like it, I'm not good at it. The unrestrained use of emotion, which is what confrontation is, does not fit well with my self-contained nature.

Instead I seek work-arounds. I’m transactional. I try to transform conflict scenarios. I look for novel outcomes that work for everyone.

One of the reasons I've a fondness for martial arts. In the Chinese and Japanese traditions, conflict decouples from emotion; becomes a technical matter (I can do technical).

So how do I handle that difficult meeting, that stressful phone call? The situation where I need something done... but the other person hasn't done it, or shows little inclination?

Some bosses or project managers would just holler at them. But we already established that I'm not good at yelling at people. I have no idea how to handle the aftermath.

Instead I present myself as helpful and friendly. It's a problem for both of us, isn't it? Do you have an issue I'm not aware of? Can we reframe the difficulty into something we can both work through?

I'm typically imaginative here.

Reluctantly, sorrowfully, if all this has failed, I might finish by wondering if you are really the right person to be assigned these kinds of tasks. Go figure.

It's worked so far, and often well:  INTP as I am.

Bob Monkhouse's top three jokes

During his lifetime comedian Bob Monkhouse was widely disdained for a public persona of cheesy smarminess. Something which, as an ENTP,* he shared with Tony Blair.

In a generation dominated by working class comedic vulgarity, his middle-class intelligence and sophistication was evident. Consequently he was not popular with his peers.

Bob Monkhouse

For me what saved him was his sense of self-deprecating irony. Here are three of his best jokes which - despite familiarity - are still pretty good.

"They laughed when I said I was going to be a comedian ... They're not laughing now."

"I can still enjoy sex at 74 - I live at 75, so it's no distance."

"I want to die like my father, peacefully in his sleep, not screaming and terrified like his passengers."

(Source)

---

* ENTPs don't do (tertiary) Extraverted Feeling at all well: (Myers-Briggs personality theory).

---

If the connection between brain architecture and personality type interests you, take a look at this post. I've been reviewing recent results from the Human Connectome Project and my remarks back then seem to stand up pretty well.

Replika is massively oversold

Replika was originally going to be your own, online personal doppelgänger. Given the current state of the art with chatbots (tiresome and useless), that was always going to be a stretch.

The current PR says:

"Replika is your personal AI friend that you nurture and raise through text conversations. It is a lifetime companion who is always there for you, chats with you, keeps your memories, and helps you become more connected to yourself."

They're busy trying to create doable spin-offs such as a personal diary ("A Cute Diary That Keeps Itself").

Given date-slippage, I had thought that the whole Replika thing might have silently collapsed, but I suppose there is no shortage of people who are happy to update a super-Eliza forty times a day with details of their every mundane activity.

Facebook.

There would be a lot of interest in a virtual friend, endlessly attentive and caring  (except that's not a friend, more a courtier - artificial sycophancy). But if this were in the state of the art, one of Google, Microsoft, Facebook, Amazon or Baidu would have done it already. It's plainly on the future roadmap for the plethora of voice assistants, but today's systems are no more than super-recognisers.

---

Have you ever had the experience of being in a technical meeting, in an area not wholly in your sphere of competence, and suddenly you lose the plot? For a moment, you just don't know what everyone else is talking about. You pray no-one will ask for your opinion.

If you're lucky, in a minute or two the topic will move on and you will rejoin the shared context.

What happened there? The participants shared an internal cognitive model of what the conversation was about, and yours frayed. But no chatbot today can maintain an internal model of any complexity.

Worse: the topics of mundane discourse are open-ended, rooted in a complex culture and often private. Do we even want our AI-in-the-cloud to share personal and family intimacies, possibly with any interested intelligence agency?

---

Your Replika AI friend is going to get 40 bland texts per day from you. Some of the questions already seem rather intrusive.

There is a hint of blank-slate about current AI. As if one standard optimised neural-net architecture could create the ideal artificial personality template, which then gets loaded with data to become an individual.

We know that people aren't like that. Common experience and psychometric data tells us that people have distinct personalities, that these are strongly heritable and resistant to change. We all know, as folk psychologists, that we deal with people as distinct individuals, not clones. And that most of those differences are innate and resistant to social influences.

"She thinks she can change him!"

No she can't.

So many mountains to climb.

• Why is the brain structured as modules, not one uniform design?
• How is the architecture of personality differences implemented?
• How to immerse an AI in common knowledge, culture and mores?
• How does social deftness, tact and propriety work?
• What's an effective, useful and pleasant engagement model - corporeal?

Yes, I am prepared to be disappointed with Replika.

---

Update: 9th March 2017.

"Replika AI to launch on the App Store

"Today, we are excited to announce that Replika will appear on the Apple’s App Store on March 13 at 12:00 AM Pacific time. We’d like to thank all the participants of the app’s preview in Testflight for the incredible feedback that helped us shape the app."

Heritability, correlation and prediction

We're told that intelligence is 60-80% heritable, and that personality is 40-60% heritable. In some hand-wavy way, we know that heritability captures the nature side of the nature-nurture contribution to traits.

But what does heritability really mean? It's a rather slippery concept. We'll get there by stages.

1. The contribution of genes to a phenotype

Let's take height as our running example (pretty much the same heritability as intelligence). Let's take a person with height P (P stands for phenotype - the measured trait). P is measured in inches away from the population mean height.

How did a person get to be that height? Nature and nurture, right?

We assume that the alleles the person got from their father contributes X_father inches of height, X_mother counts the inches they received from their mother's alleles they inherited, and then there is a nurture - or environmental - term E inches. So their total height,

P = X_father + X_mother + E.

Note these are genetic additive effects: each additional allele is plausibly assumed to make its independent contribution into raising or lowering X a fraction. Dominance and epistatic effects are neglected in this simplified conceptual model (in a polygenic trait, they tend not to be large).

Since we're measuring deviations from the mean, the average values across the population of X_father, X_mother and E must all be zero. And so, therefore, must be the average value of P.

So without loss of generality, we assume X_father, X_mother and E are normally distributed random variables with mean zero and variances as follows:

Var(X_father) = V_additive/2    -- each parent provides half the additive genetic 'input'

Var(X_mother) = V_additive/2   -- each parent provides half the additive genetic 'input'

Var(E) = V_environment.

So what is Var(P), the variance of height as we observe it in the population?

Var(P) = Var(X_father) + Var(X_mother) + Var(E) +

        2Cov(X_father, X_mother) + 2Cov(X_father, E) + 2Cov(X_mother, E).

Messy, but if we assume X_father, X_mother and E are independent, their covariances are zero, so

Var(P) = Var(X_father) + Var(X_mother) + Var(E),

V_phenotype  = V_additive + V_environment

The fraction of the population phenotypic variation due to genetic, additive effects is then simply

h² = V_additive/V_phenotype = V_additive/(V_additive + V_environment).

This is the definition of heritability, h².

So if h² is 0.5, then 50% of the variance in the phenotype is genetic in origin (additive-genetic, that is) and 50% is environmental (everything else).

Note that the more you reduce environmental variance, for example making sure that everyone's well-fed, properly educated and not knocked about, the more genetic differences predominate .. and heritability goes up. Not what the SJWs really want to hear!

---

2. Correlations

What is the correlation, ρ, between a parent and child for height?

If we have two random variables, A and B, the correlation between them is defined as follows:

ρ =  Cov(A,B)/√(Var(A) * Var(B)).

This is the standard definition.

In the case of one parent and their offspring, under some simplifying assumptions,

Cov(parent,offspring) = V_additive/2

- this takes a few lines to work out, setting most of the X_father, X_mother and E cross-terms to zero. It reflects the 50% of genetic material they have in common.

More obviously,

Var(parent) = Var(offspring) = V_phenotype,

So using the formula for ρ above,

ρ = (V_additive/2) / V_phenotype = h²/2.

This shows that heritability is not the same as the correlation between a child and one of its parents.

In general, the correlation, ρ, on a trait between relatives is equal to the coefficient of relatedness times the heritability, ie ρ = rh².

---

3. Predictions

If we know the height of both the parents, what's our best prediction of the height of their offspring? In our mind, we draw the best-fit regression line on the scatter-plot of parental-midpoint and offspring heights measured across the population.

If we centre the graph-axes at the mean values of the two populations (parental mid-point heights and offspring heights) then the regression line goes through the origin, with slope β. Then the equation of the regression line takes this simple form:

predicted-offspring-height = β * parental-midpoint-height

with both heights measured as inches in deviation from the respective means.

How do we compute β?

In this special case it turns out that β equals the heritability, so β  = h². *

This should remind you of the Breeder's Equation.

---

Example: suppose the heritability of height is 0.673 and we know that one parent is 3 inches above the population mean while the other parent is 1 inch above the mean, what's the predicted (expected) height deviation from the mean for their child?

Answer: predicted-offspring-height = β * (3 + 1)/2 = 2h² = 1.35 inches.

Yes, the child has regressed towards the mean.

---

This is problem 6.3 (p. 149) from 'Population Genetics: a concise guide' by John H. Gillespie, from which all the material above has been summarised.

---

* In general, β = ρ * (σ_y/σ_x) where x is the independent variable.

Diary: foot problem + Game of Thrones + AlphaGo + genetics

I vaguely recall jamming my foot against the side of the bed while hoovering last week. By Easter Sunday the entire right foot was red, the skin taut and swollen over the toe joint and I was limping around in socks. The last few days have seen a slow improvement but I think it may be the weekend before I can claim to be back to normal. Some observations.

1. I haven't taken any pain medication, believing that pain is a signal which I do well to heed and analgesics probably mess up self-healing. I recognise I may be in a minority on this.


2. The body's response to damage seems to affect many aspects of its functioning, not just the topical region. I feel a bit tired and - strangely - a bit more relaxed, like I'm let off worrying about stuff. Interesting.


3. Doctor Google was reassuring. The alternative suggestion of gout was excluded - no causal pathway from over-indulgence in Easter eggs.

---

A Game of Thrones (book vol 1) is highly addictive, once you've printed off the family trees of the various noble houses. It reminds me how natural the ties of family, personal loyalty and honour are, and how alien the cool, depersonalised, transactional styles of modern urban capitalism. No wonder American politicians and business people engaged with negotiators from traditional societies talk past each other in mutual incomprehension.

What would the noble protagonists of GoT make of "The Martian", which we saw on DVD Saturday evening?

The hero is some kind of insolent, wise-cracking, artisan-monkey who refuses to die quietly on Mars as he should. His liege-lord commander shows weakness by beating herself up over leaving him (she did her duty: so problem?).

The world actually cares about this minion, and the powers-that-be indulge their idiotic sentimentality. Could never happen.

Thank the Gods it's only far-fetched speculative fiction.

---

I thought this was a good article about AlphaGo - assessing its significance now the dust has settled a bit.

---

This from Professor Greely, Director at the Center for Law and the Biosciences, Stanford University, as set out in his book, 'The End of Sex and the Future of Human Reproduction'.

“In 20 to 40 years, when a couple wants a baby, he’ll provide sperm and she’ll provide a punch of skin,” Prof Greenly told The Times.

"He said the female skin sample will be used to create stem cells, which can in turn be used to create eggs.

"These eggs can then be fertilised with the sperm cells, resulting in a selection of embryos.

"Prof Greenly predicts these embryos will be studied for any signs of malady.

“The prospective parents will be told, ‘These five have really serious diseases, you don’t want them’.

"Of the other 95, they will be given the pluses and minuses,” he said.

"He said that after weighing up the prospective advantages and disadvantages of the healthier embryos, the parents will choose one to be implanted into the woman, which will become their child.

“Parents will get the embryos grouped by categories,” Prof Greenly said.

“One category will be very severe, untreatable, nasty diseases. This will affect one to two per cent of embryos.

“Another category will be other diseases.

“The third is cosmetics: hair, eyes, shape, whether the hair goes white early. We don’t know much about this yet, but we will.

“A fourth category is behavioural. I think here information will be limited. We won’t be able to say, ‘This child is in the top one per cent of intelligence’. We probably will be able to say, ‘This child has a 60 per cent chance of being in the top half’.”

He's being judiciously careful here. In 20 years time we'll be able to read off from the genome both IQ and personality type more accurately than current psychometric testing can.

How Much Do Our Genes Influence Our Political Beliefs?

This is the title of a New York Times piece in July, 2014, which had an illuminating thesis. Click on the table below to make it larger.

"Identical twins are more likely than fraternal twins to share traditional values with their twin siblings, suggesting a biological link on cultural outlook.

"In this table, 0 represents no correlation in outlook; 1 represents identical outlooks. In reality, the numbers fall in between, but identical twins are much more culturally alike (higher numbers) than fraternal twins.

"In an email, Ludeke explained how to interpret this information: “These correlations represent the extent to which members of a given type of twin pair resemble each other for the trait in question,” he wrote. “Low correlations, like those we found for fraternal twins, indicate that knowing the scores of one twin won’t give you much, if any, clue for figuring out the scores of the other. On the other hand, based on the correlations presented here, knowing the scores of one identical twin gives you a pretty good indication of the scores of the other.”

"The significance of the different correlations for identical and fraternal twins, Ludeke added, is that “when we see identical twins who are this similar, while fraternal twins are much less similar, we have a good indication that genes account for some of the difference between people for the trait in question.”

High heritability for political outlook doesn't mean you are destined to share your parents' views; after all, you are neither a clone nor an average mixing of your parents. It does mean that your unique genome is providing you with temperament/personality settings which inform your political outlook.

In my previous post, I quoted Scott Alexander's figures that elite US universities, like Harvard or Yale, sort something like 90:10 liberal vs. conservative. That academics - particularly in the social sciences - are bleeding-heart lefties is a truth universally acknowledged. In business, to the contrary, I have rarely found the ranks of management thus populated. Occupations are a great sorter, not just for intelligence but also for temperament and personality type.

In Keirsey/Myers-Briggs terms I suggest:

• Liberal-leftists tend to be NF-Idealists
• Libertarians (of left and right) are NT-Rationals
• Conservatives (of left and right) are ST-Guardians
• Populist insurgents are often SP-Artisans.

So some examples.

• The emotion-driven, fuzzy-thinking, heart-on-sleeve, leftist BBC/Guardianista is the classic Idealist-NF. My favourites include Lyse Doucet and Shami Chakrabarti.


• Left-wing Rationals include Jeremy Corbyn and Bernie Sanders; on the Right you have US neocons such as Paul Wolfowitz, John Bolton, Richard Perle - and Michael Gove.


• You find small-c conservative Guardians in all political parties. David Cameron is one, and so is Tom Watson, deputy leader of the Labour Party. Also Hillary Clinton.


• My favourite Artisan is the leader of the Italian Five Star movement, Beppe Grillo, ... and then there's Trump.

We're all puppets of our own temperaments. Rod Liddle (a working-class Rational) rages at bien-pensant liberals; they rage at heartless and utilitarian dessicated intellectuals ... so it goes.

The Evolution of Personality Differences

Evolutionary psychologist Daniel Nettle wrote an important paper ten years ago, "The Evolution of Personality Variation in Humans and Other Animals" which has not dated. The paper addressed two issues:

• Why is there variation in human personalities?
• What is the evolutionary basis of the 'five factor model' dimensions?

On the first question he has this to say.

"Heritable variation is ubiquitous in natural populations. ... Why does variation persist? The ultimate source of variation is of course mutation. The level of variation found in a population at any point in time reflects the balance between mutation introducing new variants and selection removing them. For a trait influenced by a single gene, selection does not have to be very strong to keep the level of standing variation close to zero, because mutations arise relatively infrequently. However, the rate of appearance of mutations affecting a trait rises directly with the number of genes involved in building it, and selection does not remove them instantaneously. Thus, for a trait affected by many genes, even if selection is strong, there will be a significant amount of standing genetic variation. ...

Varying the level of investment in a quantitative trait is rarely simply advantageous or simply disadvantageous. There are many components to overall fitness, and increasing investment in one trait is usually done at the expense of others. For example, growing large, though possibly beneficial in intraspecific competition, raises metabolic costs and also lengthens the time spent growing and thus delays the onset of reproduction. ...

The extreme case of variable optima is what is known as negative frequency-dependent selection. This describes the situation in which the relative fitness of a trait is high as long as it is rare in the local population but declines as it becomes widespread. It has long been recognized that negative frequency dependence can in theory lead to the maintenance of polymorphism. ...

Variation is a normal and ubiquitous result of the fluctuating nature of selection, coupled with the large numbers of genes that can affect behavior. Frequency-dependent selection, oft discussed as a maintainer of variation, is in fact just a subcase of the more general phenomenon of fluctuating selection. ...

Behavioral alternatives can be considered as trade-offs, with a particular trait producing not unalloyed advantage but a mixture of costs and benefits such that the optimal value for fitness may depend on very specific local circumstances. With these generalizations in mind, I now turn to the consideration of personality variation in humans."

We may observe that every form of human society from hunter-gatherer through pastoral, agricultural and mercantile-capitalist has required a division of labour where different personality types are optimal. Not everyone can be the big chief or be a compliant follower, not everyone can focus on competence in tool-making, not everyone can be a specialist in interpersonal diplomacy.

I summarise Professor Nettle's views on the evolutionary validity of the five factors below (his second question). The Myers-Briggs Type Theory dimensions are shown in brackets. I have edited-out the original inline references for readability - refer to the original paper (PDF) for the full text.

1. Extraversion-Introversion (E-I) 

"Extraversion is strongly and positively related to number of sexual partners which, for men in particular, can increase fitness. High scorers are also more likely to engage in extra-pair copulations or to terminate a relationship for another. This may lead to their securing mates of higher quality than those secured by individuals who are more constant in their choice of partners. The benefits of extraversion are not limited to mating, as extraverts,or those high on the closely correlated trait of sensation seeking, initiate more social behavior and have more social support than others. Moreover, they are more physically active and undertake more exploration of their environment.

However, in pursuing high sexual diversity, and high levels of exploration and activity in general, extraverts also expose themselves to risk. Those who are hospitalized due to accident or illness are higher in extraversion than those who are not, and those who suffer traumatic injury have been found to be high in sensation seeking. High extraversion or sensation seeking scorers also have elevated probabilities of migrating, becoming involved in criminal or antisocial behavior, and being arrested. All of these are sources of risk, risk that in the ancestral environment might have meant social ostracism or death.Moreover, because of their turnover of relationships, extraverts have an elevated probability of exposing their offspring to stepparenting, which is a known risk factor for child well-being."

2. Neuroticism-Emotional Stability (Turbulent-Assertive as defined here)

"The neuroticism personality axis is associated with variation in the activity levels of negative emotion systems such as fear, sadness, anxiety, and guilt. The negative effects of neuroticism are well-known in the psychological literature. High neuroticism is a strong predictor of psychiatric disorder in general, particularly depression and anxiety. Neuroticism is also associated with impaired physical health, presumably through chronic activation of stress mechanisms. Neuroticism is a predictor of relationship failure and social isolation. A much more challenging issue, then, is finding any compensatory benefit to neuroticism.

However, given the normal distribution observed in the human population, and the persistence of lineages demonstrably high in the trait, such a benefit seems likely. Studies in nonhuman animals, such as guppies, suggest that vigilance and wariness are both highly beneficial in avoiding predation and highly costly because they are quickly lost when predation pressure is absent. In ancestral environments, a level of neuroticism may have been necessary for avoidance of acute dangers. Anxiety, of which neuroticism can be considered a trait measure, enhances detection of threatening stimuli by speeding up the reaction to them, interpreting ambiguous stimuli as negative, and locking attention onto them.

Because actual physical threats are generally attenuated in contemporary situations, the safety benefits of neuroticism may be hard to detect empirically. However, certain groups who take extreme risks, such as alpinists and Mount Everest climbers, have been found to be unusually low in neuroticism. Given the high mortality involved in such endeavors (around 300 people have died in attempting Everest), this finding suggests that neuroticism can be protective."

3. Openness-Concreteness (N-S)

"The trait of openness to experience again seems, at first blush, to be an unalloyed good. Openness is positively related to artistic creativity. According to Miller’s cultural courtship model, creative production in artistic domains serves to attract mates, and there is evidence that women find creativity attractive, especially during the most fertile phase of the menstrual cycle, and that poets and visual artists have higher numbers of sexual partners than controls. The core of openness seems to be a divergent cognitive style that seeks novelty and complexity and makes associations or mappings between apparently disparate domains. Though such a cognitive style might appear purely beneficial, it is conceptually very similar to components of schizotypy, or proneness to psychosis. ...

Thus, openness and its covariates are associated with damaging psychotic and delusional phenomena as well as high function. Openness itself has been found to be associated with depression, as has a high score on the Unusual Experiences scale. Thus, the unusual thinking style characteristic of openness can lead to nonveridical ideas about the world, from supernatural or paranormal belief systems to the frank break with reality that is psychosis."

4. Conscientiousness-Spontaneity (J-P)

"The remaining two personality domains, conscientiousness and agreeableness, are often thought of as being unalloyed in their benefits, because they are generally negatively related to measures of delinquency and antisocial behavior. However, it is important not to conflate social desirability with positive effects on fitness. Natural selection favors traits that increase reproductive success, including many cases in which this success comes at the expense of other individuals. It is likely that fitness can be enhanced by a capacity to demand a free ride, break rules, and cheat on others under certain circumstances.

Conscientiousness involves orderliness and self-control in the pursuit of goals. A by-product of conscientiousness is that immediate gratification is often delayed in favor of a longer term plan. This leads, for example, to a positive association of conscientiousness with life expectancy, which works through adoption of healthy behaviors and avoidance of unhygienic risks. Very high levels of traits related to conscientiousness - moral principle, perfectionism, and self-control - are found in patients with eating disorders and with obsessive-compulsive personality disorder.

Though some obsessional individuals can be very high achievers in the modern context, it is not evident that their fitness would always have been maximal in a variable and unpredictable ancestral environment. Their extreme self control not only may be damaging, as their routines become pathological, but may lead to the missing of spontaneous opportunities to enhance reproductive success. Highly conscientious individuals have fewer short-term mating episodes and will forgo opportunities to take an immediate return that may be to their advantage. Adaptations that orient the organism toward working for long-term payoffs will tend to have the effect of reducing the opportunistic taking of immediate ones."

5. Agreeableness-Tough-Mindedness (F-T)

"Agreeableness, with its correlates of empathy and trust, is also generally seen as beneficial by personality psychologists, and its absence is associated with antisocial personality disorder. Agreeableness is strongly correlated with Baron-Cohen’s empathizing scale, which is in turn argued to measure theory of mind abilities and the awareness of others’ mental states.

Several evolutionary psychologists have argued plausibly that as a highly social species, humans have been under strong selection to attend to and track the mental states of others. Others have noted that we seem to be unique among mammals in the extent of our cooperation with unrelated conspecifics. Inasmuch as agreeableness facilitates these interactions, it would be highly advantageous. Agreeable individuals have harmonious interpersonal interactions and avoid violence and interpersonal hostility. They are much valued as friends and coalition partners. ...

Although this may be true, a vast literature in theoretical biology has been devoted to demonstrating that unconditional trust of others is almost never an adaptive strategy. Across a wide variety of conditions, unconditional trusters are invariably outcompeted by defectors or by those whose trust is conditional or selective. ...

Though it is an uncomfortable truth to recognize, it is unlikely that fitness is unconditionally maximized by investing energy in positive attention to others. Instead, though an empathic cognitive style may be useful in the whirl of social life, it may have costs in terms of exploitation or inattention to personal fitness gains.

Moreover, sociopaths, who are low in agreeableness, may at least sometimes do very well in terms of fitness, especially when they are rare in a population. The balance of advantages between being agreeable and looking after personal interests will obviously vary enormously according to context. For example, in a small isolated group with a limited number of people to interact with and a need for common actions, high agreeableness may be selected for. Larger, looser social formations, or situations in which the environment allows solitary foraging, may select agreeableness downward."

Professor Nettle leaves us with this useful summary picture.

Nettle agrees that his ideas are speculative and are intended to propose hypotheses for future research. In fact it has proved hard to directly identify genotype correlates to psychological traits. Genes code for brain structure and process-regulation in a highly-indirect way. The missing level of analysis is in the variant brain architectures and operating modes (such as neurotransmitter levels) which underlie individual personality traits and differences - these seem to be largely under genetic control.

Thankfully, there's a lot of research into these areas at the moment.

Success in life: is it coz i is nice?

Thought for the day.

"We assessed the association and underlying genetic and environmental influences among intelligence (IQ) and personality in adolescent and young adult twins.

Data on intelligence were obtained from psychometric IQ tests and personality was assessed with the short form of the NEO five factor inventory (NEO-FFI).

IQ and personality data were available for 646 twins. There were an additional 1307 twins with NEOFFI data, and 535 with IQ data. Multivariate genetic structural equation modeling was carried out.

Significant positive phenotypic correlations with IQ were seen for agreeableness (r = 0.21) and openness to experience (r = 0.32). A negative correlation emerged for neuroticism and IQ (r = -0.10).

 Genetic factors explained (nearly) all of the covariance between personality traits and IQ.

Genetic correlations were 0.3–0.4 between IQ and agreeableness and openness. The genetic correlation between IQ and neuroticism was around -0.18. Thus, personality and IQ did not appear to be independent dimensions, and low neuroticism, high agreeableness and high scores on openness all contributed to higher IQ scores."

All that stuff you were told, that personality was independent from intelligence, was so much guff. Smarter people tend to be nicer.

Self-control is also positively associated with intelligence. The famous marshmallow test purported to show that those with self-control got ahead in life. Maybe so, but wait .. they were also smarter.

---

By the way, before you complain that you know people who are nice but dim, or cite The Donald as a counterexample .. which part of the following scatter diagram are you struggling with?

Correlation here is 0.3 

Hint: think Intelligence (IQ) on the horizontal axis and a psychological trait such as Agreeableness on the vertical axis.

Litter in the park

Deborah Ross wrote in yesterday's Times:

Litter is a class issue, but why? 

I live an equal distance from two London parks. One is in a well-to-do, middle-class area and one is not. (To give you some idea of how different these parks are, when it last snowed, in the well-to-do park someone built not a snowman, but a snow-flautist, complete with twig for flute, while in the other it was a huge snow-penis, complete with huge snow balls.).

Since I'm often in both parks, what with the dog and all, one thing I have noticed is this: whereas the well-to-do middle-class park (OK, Highgate Wood) does not have a litter problem, the other (OK, Finsbury Park) seriously does.

That is, say I go in the morning: while Finsbury Park is covered in yesterday’s picnic debris, Highgate Wood is not. Different staffing levels? Highgate Wood employs more people to clear up? I don’t think so. Even while I'm walking, I see people chucking drink cans, burger wrappers, crisp packets and chicken bones all over the place in Finsbury Park in a way I never see in the wood.

So, is litter a class issue? If so, why? Particularly when it seems counterintuitive. Wouldn't the middle classes, with their cleaners and gardeners and pond hooverers — I know someone who has a man come in to hoover her pond — be more likely to think that others will step in to do their dirty work?

I have asked around and the following explanations have been offered: paying higher taxes means a higher sense of ownership of public spaces; the less well-off are more disaffected and have less interest in maintaining society’s infrastructure; middle-class culture simply pays more respect to the environment; the middle classes are restrained by social shaming (but shouldn't everyone be ashamed of dropping litter, and if not, why not?). I don’t know. You tell me . .

Once one has recovered from amazement that a Times columnist would be puzzled over so obvious a question, one feels inclined to frame an answer.

The simplest possible response is something like this:

Tidy parks are the result of tidy people, people with prosocial personality traits such as agreeableness, intelligence and empathy. Such people tend to get on in our imperfect meritocracy and thrive in the middle class. The lower classes include many who haven't got on, people who tend disproportionately to the 'dark triad' - lack of empathy, disregard for others, selfishness. For good or ill, these qualities are rather heritable which accounts for their persistence across the social classes. Hence your differential litter phenomenon.

The distinction between the prosocial and antisocial personality type is not well captured in the five-factor model. The newer HEXACO model apparently shows a greater ability to discriminate with its six dimensions of personality:

• Honesty-Humility (H): sincere, honest, faithful, loyal, modest/unassuming versus sly, deceitful, greedy, pretentious, hypocritical, boastful, pompous.
• Emotionality (E): emotional, oversensitive, sentimental, fearful, anxious, vulnerable versus brave, tough, independent, self-assured, stable.
• Extraversion (X): outgoing, lively, extraverted, sociable, talkative, cheerful, active versus shy, passive, withdrawn, introverted, quiet, reserved.
• Agreeableness (A): patient, tolerant, peaceful, mild, agreeable, lenient, gentle versus ill-tempered, quarrelsome, stubborn, choleric.
• Conscientiousness (C): organized, disciplined, diligent, careful, thorough, precise versus sloppy, negligent, reckless, lazy, irresponsible, absent-minded.
• Openness to Experience (O): intellectual, creative, unconventional, innovative, ironic versus shallow, unimaginative, conventional.

You can see how pro- and antisocial personality types are going to map onto this - you can seek confirmation here.

Dreams

Woke up recalling a dream where I was working as the new member of a warehouse team - probably as an Amazon elf. Awesome, isn't it, how the brain can create simulations of other people with their own personalities in dreams?

Then I recalled that's how it is when you're awake as well. Everyone you deal with, your brain has created a simulation model of them which you mistakenly believe to be 'out there' and objective. Your brain fabricates that creative illusion by neural activity alone.

Then I thought. That's got to apply to me too - I must be a self-model. No wonder other people are amazed at my self-delusions. I remind myself this is only what my simulations of them are saying -although these have proven remarkably accurate in the past.

I idly wonder how stupid people can ever create accurate simulations - in their sorry apologies for brains - of smart people? Obviously they can't.

I then remind myself of how often my own predictions of other people's responses go sadly awry. I hurriedly move on.

Five-Factor Model Questionnaire

The Newcastle Personality Assessor (NPA) from "Personality" by Daniel Nettle.

To understand the purpose of this questionnaire refer to my review of Daniel Nettle's book. For more on the Five-Factor Model see the Wikipedia article.

Gender?	Female Male
	Not me	Not very me	Me-ish	Somewhat me	Very me
Q1: Starting a conversation with a stranger
Q2: Making sure others are comfortable and happy
Q3: Creating an artwork, piece of writing, or piece of music
Q4: Preparing for things well in advance
Q5: Feeling blue or depressed
Q6: Planning parties or social events
Q7: Insulting people
Q8: Thinking about philoophical or spiritual questions
Q9: Letting things get into a mess
Q10: Feeling stressed or worried
Q11: Using difficult words
Q12: Sympathizing with others' feelings

Your personality assessment
Openness
Conscientiousness
Extraversion
Agreeableness
Neuroticism

Now you have your assessment, what does it mean? You should read Daniel Nettle's book (or the Wikipedia article for a fast review) but just to give you a flavour, here is what your score might suggest about yourself.

Interpreting your FFM personality assessment

“Personality” by Daniel Nettle

A rather excellent book: "Personality" by Daniel Nettle.

Suppose you ask people to rate their interest in such things as social activities, travel, competitive success and sex. Perhaps not surprisingly, their separate scores will correlate with each other (0.1 – 0.3). If you now ask them whether they ever feel depressed or ‘blue’, or whether they have sought help for anxiety, their scores for these two items also positively correlate with each other. But the first four sets and the second two sets don't cross correlate at all. This suggests there are deeper traits at work. A technique called factor analysis identifies Extraversion as the common factor in the first set, and Neuroticism as the common factor for the second. These two factors are independent.

When a wide variety of personality-relevant items are rated for large samples of people, factor analysis reliably and repeatedly confirms that there are five underlying, independent personality traits: Extraversion and Neuroticism as already describerelatesscientiousness, Agreeableness and Openness. Each will get a chapter to itself.

The Five Factor Model of personality is often accused of shallowness, and of being atheoretic as the factors simply emerge from statistical processing (in fact just the same factoring procedure generates the g-factor – general intelligence – as measured through IQ tests). The great strength of Nettle’s book is that he can link individual variation within each of the five factors to differences in brain anatomy and metabolism as captured by MRI scanners and then with genetic differences. The five traits seem to be capturing something real about genetically-determined brain variation.

Common observation confirms that we are surrounded by different personalities. If personality is heavily determined by our genes, as it appears, then why haven't we all converged on an ideal personality? You can, of course, ask the same question about any continuously-varying trait which still exhibits variation, such as height or intelligence. The answer seems to be a combination of environmental instability (rewarding different parts of the variability-spectrum in different circumstances) and frequency-dependent selection (as in the way a few rather nasty people can take advantage of the many nice-but-gullible). Nettle discusses this in detail – it will be a recurring point that all positions in personality space help in some circumstances but hinder in others.

The chapter on Extraversion, setting a pattern for those to come on the other traits, links the behavioural attributes of extraverts with brain imaging and genetic studies. Extraversion, it turns out, comes down to a strong reaction to positive emotions – those feelings we find rewarding; introverts just don’t seem to care so much, conserving their energy. There seems to be a link between extraversion and genetic variation in sensitivity to dopamine.

Neuroticism, by contrast, relates to sensitivity to negative emotions: to score highly on this dimension is to be a worrier. The associated brain chemistry seems to involve the neurotransmitter serotonin: inhibitors such as Prozac seem to make us less worried about life’s many sources of anxiety.

Conscientiousness, the third trait to be analysed, seems at first sight a pretty good trait to score highly on. It’s the most reliable predictor of occupational success across the board. Conscientiousness is particularly valuable in structured, rule-based environments such as we find in advanced technological societies. Change the situation to one of unpredictable, fast-changing circumstance however, and the rule-bound are at a disadvantage. The army, for example, has a continual internal conflict as it needs both sorts, but they continually rub each other up the wrong way.

Agreeableness, the fourth dimension, sounds like a trait well-worth having. Who could fault being nice? Perhaps not so strangely, success in business correlates with low scores on this trait. Something about putting other people first and a degree of self-effacement doesn’t sit easily with tough, mission-oriented leadership. This is the one trait where female and male scores are clearly distinct, with women scoring more than half a standard deviation higher in agreeableness. There is a ready evolutionary explanation in the pre-modern sexual division of labour.

The final dimension is Openness to Experience. This is a hard dimension to pin down. Some people equate it with intelligence, but the author is of the opinion that intelligence is a kind of whole-brain efficiency measure implicated across all areas of neural functioning including such non-intellectual tasks as pure reaction times. Nettle believes high-scorers on Openness are artistic, creative people capable of making associations between different – and perhaps surprising – kinds of things. Intellectuals on the science, technology, engineering and maths front don’t look much like famous poets and acclaimed authors. Wherein lies the difference? For once the author doesn’t have good answers, believing the key to excellence in these STEM subjects is more down to general intelligence. But clearly that can't be the whole story.

In the final part of the book the author reviews the evidence for ‘environmental’ influences determining personality and finds they are few and hard to find. Family and parental input (if non-abusive) has been carefully measured to have exactly zero impact: you can't change your child’s personality. Does this give people a deterministic get-out - my genes made me do it? In the final chapter Nettle carefully demolishes this view, showing that dispositions are one thing, but the life choices you make to go with or against the flow of your dispositions are something else.

In summary, this book is a wonderfully accessible and profound exploration of the concept of personality. Everyone will learn something about themselves from reading it and it conclusively takes us beyond the limitations of the Jungian approach as in Myers-Briggs theory. There is a short 12 item questionnaire which you are encouraged to complete before reading (which you can take online here).

Your reviewer scored:

Openness:              HIGH;
Conscientiousness:  HIGH;
Extraversion:          LOW;
Agreeableness:       MED-HIGH;
Neuroticism:          LOW.

Alien Psychology Part 1

My favourite SF stories concern aliens so different from ourselves that they are incomprehensible - not least because this will probably be true. The gold standard here is Stanislaw Lem in his books Solaris and His Master's Voice.

I'm interested in how we could understand the nature of such alien incomprehensibility. The standard model of personality is the five-factor model with the acronym OCEAN (*).  This model has been applied with some success to animals and although it's somewhat atheoretic and definitely not rooted in evolutionary psychology, one can sort of see why a social animal of our sort (not as social as ants, not as selfish as, say, polar bears) would have its personality space structured along those five dimensions.

One way to design the alien would be to move their personality somewhere else in the OCEAN space, somewhat removed from the locus of human occupancy. So the aliens might be very 'Open': smart and enquiring; intellectual, cool and detached but still kind of benevolent. Or we could work on their 'Agreeableness': they can be super-friendly and trusting, or super-aggressive and suspicious.

But I'm more interested in the really alien aliens, ones so different that they don't classify in the OCEAN space at all. These aliens are going to come out of a radically non-terran ecology.

One example: there are chess programs that play perfect endgames based on storing optimal-play trees built via exhaustive search. In endgames of the order of 50-100 moves, there's no theory underlying the program's play - it's just empirically optimal.

Playing such a program is profoundly unsettling. The program evades or subverts any attempt to assign it plans or subgoals as it has none (more accurately, the structure of said endgames does not lend itself to such a decomposition); the program moves perversely yet with ruthless efficiency. It is devoid of intentionality: truly alien.

Another route which we sometimes encounter here on Earth: our opponent has objectives we profoundly don't understand. We keep ascribing goals, beliefs, plans and intentions based on our hypothesising as to what it's after: we're always wrong, always wrong-footed, always mystified. But here the alienness is not in personality but in motivation. Not the same at all.

Read Part 2.
---
* OCEAN: Open, Conscientious, Extravert, Agreeable, Neurotic .. are the five dimensions.