(Epistemic disclaimer: My understanding of genetics is very limited.)
If additive heritability for all the relevant personality traits was zero, many interventions in this area are pointless, yes.
I might have underestimated this problem but one reason why I haven’t given up on the idea of selecting against “malevolent” traits is that I’ve come across various findings indicating SNP heritabilities of around 10% for relevant personality traits. (See the last section of this comment for a summary of various studies).
SNP heritabilities of ~10% (or even more) for relevant personality traits seem also not implausible on theoretical grounds. If I understand Penke et al. (2007, see Table 1 in particular) correctly, balancing-selection models of personality predict that personality traits should show less additive heritability than, say, cognitive ability, but not (necessarily) zero additive heritability.
Granted, 10% is pretty low, but is it hopelessly low? According to Karavani et al. (2019), a polygenic score for IQ which explains 4% of the variance, would enable an average increase of 3 IQ points (assuming 10 available embryos). I infer from this that a polygenic score which can explain only ~4% of the variance in, say, psychopathy would still enable the reduction of ~ 1⁄5 of a standard deviation in average psychopathy scores, assuming 10 embryos. Polygenic scores explaining ~10% of the variance might thus enable considerably larger average reductions of ⅓ - ½ of a standard deviation or so (numbers pulled out of my posterior).
Again, ⅓ of a SD might seem underwhelming but, as you emphasize in your essay on embryo selection, small changes in the mean of a normal distribution can have large effects out on the tails, so this could still lead to surprisingly large reductions in the frequency of extreme psychopathy or sadism (~psychopathy scores 2-3 SDs above the norm), even in “normal” IVF embryo selection. When applied in iterated embryo selection (IES), this could result in much stronger effects still.
Again, I could easily be wrong about any of the above.
Will SNP heritability estimates increase with larger sample sizes?
This is at least what Tielbeek et al. (2017) suggest: “Recent GWASs on other complex traits, such as height, body mass index, and schizophrenia, demonstrated that with greater sample sizes, the SNP h2 increases. [...] we suspect that with greater sample sizes and better imputation and coverage of the common and rare allele spectrum, over time, SNP heritability in ASB [antisocial behavior] could approach the family based estimates.”
Higher additive heritability for personality disorders?
Another point that makes me somewhat hopeful is that specific personality disorders seem to show larger additive heritabilities than personality traits. For example, the meta-analysis by Polderman et al. (2015, Table 2) suggests that 93% of all studies on specific personality disorders “are consistent with a model where trait resemblance is solely due to additive genetic variation”. (Of note, for “social values” this fraction is still 63%).
And a lot of the benefits in this area might come from selecting against, say, antisocial or narcissistic personality disorder (sadly, sadistic personality disorder is not a thing anymore but it was included in the appendix of DSM-II).
But it’s been a while since I read the Polderman paper and I’m also a bit confused by how there can be high additive heritability for, say, narcissistic personality disorder but very low additive heritability for narcissism as a trait, so the above might be wrong.
Some interventions in this area don’t require additive heritability
There are also interventions that work, even if additive heritability is zero though they assume that the non-additive genetic variance is at least partly due to dominance and not solely due to epistasis; I think. For example, ensuring that the parents of the first generation of IES embryos score low on dark tetrad traits or influencing the first genome synthesis projects to make their first genomes as similar to those of people scoring low on dark tetrad traits as possible (alongside edits to achieve substantial IQ increases, of course).
Lastly, there are interventions that have nothing to do with genetic enhancement but would benefit from more research on and advocacy for screening against malevolent traits and are thus somewhat related to the above. For example, it seems valuable to develop better measures of malevolent traits, potentially ones that are impossible to game such as neuroimaging techniques. Such measures could then be used in various high-impact settings to. For example, they would enable decision makers to better screen for highly elevated dark tetrad traits in government officials, humans whose brains will be used to create the first ems, and human overseers in AI projects. (Currently, all measures of malevolence seem to be self-report questionnaires or interviews which seem easily gameable by smart psychopaths.)
Is non-additive genetic variance really useless?
(No need to reply to the questions in this section.)
Assume that all of the genetic variance in trait A is due to dominance. Wouldn’t it still be possible to achieve non-zero increases/decreases in trait A via (iterated) embryo selection?
And what about epistasis? Is it just that there are quadrillions of possible combinations of interactions and so you would need astronomical sample sizes to achieve sufficient statistical power after correcting for multiple comparisons?
Some evidence for non-zero SNP heritabilities of relevant personality traits
Table 4 of Sanchez‐Roige et al. (2018) provides a good summary. Below, I focus on studies examining traits that likely correlate with dark tetrad traits, such as agreeableness and conscientiousness.
The UK biobank (N ≈ 290k) estimates SNP heritabilities of around 10% for various personality traits, some of which probably even correlate with psychopathy, such as the items “do you often feel guilty?” and “Do you worry too long after an embarrassing experience?”. (Don’t get me wrong, I’m not saying that we should select against traits that only correlate with psychopathy while being completely fine in themselves, like e.g. not often feeling guilty. I’m just listing these items to support the hypothesis that as long as we can find SNP heritability for them, we can expect to find SNP heritabilities for related traits as well.) Unfortunately, the UK biobank didn’t seem to measure any personality trait apart from neuroticism (estimated SNP heritability: 11%). Also, they usually didn’t even use likert scales, only dichotomous yes/no responses, which might reduce heritability estimates (??).
A GWAS (N = 46,861) by Warrier et al. (2018) found an additive heritability, explained by all the tested SNPs, for the Empathy Quotient of 11%. (The Empathy Quotient contains items like “I get upset if I see people suffering on news programmes” and “I really enjoy caring for other people” and thus probably correlates negatively with dark tetrad traits.)
Verweij et al. (2012) give a SNP heritability of 6.6% for harm avoidance which likely correlates with dark tetrad traits.
Lo et al. (2017) estimate SNP-based heritabilities of 18% for extraversion, 8.5% for agreeableness and 9.6% for conscientiousness (see supplementary table 2). (N = 59,176).
Granted, Power and Pluess (2015) estimate SNP heritability of agreeableness and conscientiousness as 0%. However, their sample size of 5,011 is much smaller than the sample sizes above and they write: “It is worth noting that the large standard errors around the negative findings suggest increased sample size may identify a low but significant level of heritability.”
“Recent GWASs on other complex traits, such as height, body mass index, and schizophrenia, demonstrated that with greater sample sizes, the SNP h2 increases. [...] we suspect that with greater sample sizes and better imputation and coverage of the common and rare allele spectrum, over time, SNP heritability in ASB [antisocial behavior] could approach the family based estimates.”
I don’t know why Tielbeek says that, unless he’s confusing SNP heritability with PGS: a SNP heritability estimate is unconnected to sample size. Increasing n will reduce the standard error but assuming you don’t have a pathological case like GCTA computations diverging to a boundary of 0, it should not on average either increase or decrease the estimate… Better imputation and/or sequencing more will definitely yield a new, different, larger SNP heritability, but I am really doubtful that it will reach the family-based estimates: using pedigrees in GREML-KIN doesn’t reach the family-based Neuroticism estimate, for example, even though it gets IQ close to the IQ lower bound.
For example, the meta-analysis by Polderman et al. (2015, Table 2) suggests that 93% of all studies on specific personality disorders “are consistent with a model where trait resemblance is solely due to additive genetic variation”. (Of note, for “social values” this fraction is still 63%).
Twin analysis can’t distinguish between rare and common variants, AFAIK.
The SNP heritabilities I’m referring to are https://en.wikipedia.org/w/index.php?title=Genome-wide_complex_trait_analysis&oldid=871623331#Psychological There’s quite low heritabilities across the board, and https://www.biorxiv.org/content/10.1101/106203v2 shows that the family-specific rare variants (which are still additive, just rare) are almost twice as large as the common variants. A common SNP heritability of 10% is still a serious limit, as it upper bounds the PGS which will be available anytime soon, and also hints at very small average effects making it even harder. Actually, 10% is much worse than it seems even if you compare to the quoted IQ’s 30%, because personality is easy to measure compared to IQ, and the UKBB has better personality inventories than IQ measures (at least, substantially higher test-retest reliabilities IIRC).
Dominance...And what about epistasis? Is it just that there are quadrillions of possible combinations of interactions and so you would need astronomical sample sizes to achieve sufficient statistical power after correcting for multiple comparisons?
Yes. It is difficult to foresee any path towards cracking a reasonable amount of the epistasis, unless you have faith in neural net magic starting to work when you have millions or tens of millions of genomes, or something. So for the next decade, I’d predict, you can write off any hopes of exploiting epistasis to a degree remotely like we already can additivity. (Epistasis does make it a little harder to plan interventions: do you wind up in local optima? Does the intervention fall apart in the next generation after recombination? etc. But this is minor by comparison to the problem that no one knows what the epistasis is.) I’m less familiar with how well dominance can work.
----
So to summarize: the SNP heritabilities are all strikingly low, often <10%, and pretty much always <20%. These are real estimates and not anomalies driven by sampling error, nor largely deflated by measurement error. The PGSes, accordingly, are often near-zero and have no hits. The affordable increases in sample sizes using common SNP genotyping will push it up to the SNP heritability limit, hopefully; but for perspective, recall that IQ PGSes 2 years ago were *already* up to 11% (Allegrini et al 2018) and still have at least 20% to go, and IQ isn’t even that big a GWAS success story (eg height is >40%). The ‘huge success’ story for personality research is that with another few million samples years and years from now, they can reach where a modestly successful trait was years ago before they hit a hard deadend and will need much more expensive sequencing technology in generally brandnew datasets, at which point the statistical power issues become far more daunting (because rare variants by definition are rare), and other sources of predictive power like epistatic variants will remain inaccessible (barring considerable luck in someone coming up with a method which can actually handle epistasis etc). The value of the possible selection for the foreseeable future will be very small, and is already exceeded by selection on many other traits, which will continue to progress more rapidly, increasing the delta, and making selection on personality traits an ever harder sell to parents since it will largely come at the expense of larger gains on other traits.
Could you select for personality traits? A little bit, yeah. But it’s not going to work well compared to things selection does work well for, and it will continue not working well for a long time.
I don’t know why Tielbeek says that, unless he’s confusing SNP heritability with PGS: a SNP heritability estimate is unconnected to sample size. Increasing n will reduce the standard error but assuming you don’t have a pathological case like GCTA computations diverging to a boundary of 0, it should not on average either increase or decrease the estimate… Better imputation and/or sequencing more will definitely yield a new, different, larger SNP heritability, but I am really doubtful that it will reach the family-based estimates: using pedigrees in GREML-KIN doesn’t reach the family-based Neuroticism estimate, for example, even though it gets IQ close to the IQ lower bound.
Thanks, all of that makes sense, agree. I also wondered why SNP heritability estimates should increase with sample size.
To summarize, my sense is the following: Polygenic scores for personality traits will likely increase in the medium future, but are very unlikely to ever predict more than, say, ~25% of variance (and for agreeableness maybe never more than ~15% of variance). Still, there is a non-trivial probability (>15%) that we will be able to predict at least 10% of variance in agreeableness based on DNA alone within 20 years, and more than >50% probability that we can predict at least 5% of variance in agreeableness within 20 years from DNA alone.
Or do you think these predictions are still too optimistic?
But couldn’t one still make use of rare variants, especially in genome synthesis? Maybe also in other settings?
The value of the possible selection for the foreseeable future will be very small, and is already exceeded by selection on many other traits, which will continue to progress more rapidly, increasing the delta, and making selection on personality traits an ever harder sell to parents since it will largely come at the expense of larger gains on other traits.
I agree that selecting for IQ will be much easier and more valuable than selecting for personality traits. It could easily be the case that most parents will never select for any personality traits.
However, especially if we consider IES or genome synthesis, even small reductions in dark personality traits—such as extreme sadism—could be very valuable from a long-termist perspective.
For example, assume it’s 2050, IES is feasible and we can predict 5% of the variance in dark traits like psychopathy and sadism based on DNA alone. There are two IES projects: IES project A only selects for IQ (and other obvious traits relating to e.g. health), IES project B selects for IQ and against dark traits, otherwise the two projects are identical. Both projects use 1-in-10 selection, for 10 in vitro generations.
According to my understanding, the resulting average psychopathy and sadism scores of the humans created by project B could be about one SD* lower compared to project A. Granted, the IQ scores would also be lower, but probably by no more than 2 standard deviations (? I don’t know how to calculate this at all, could also be more).
It depends on various normative and empirical views whether this is worth it, but it very well might be: 180+IQ humans with extreme psychopathy or sadism scores might substantially increase all sorts of existential risks, and project A would create almost 17 times** as many such humans compared to project B, all else being equal.
The case for trying to reduce dark traits in humans created via genome synthesis seems even stronger.
One could draw an analogy with AI alignment efforts: Project A has a 2% chance of creating an unaligned AI (2% being the prevalence of humans with psychopathy scores 2 SDs above the norm). Project B has only a 0.1% chance of creating an unaligned AI. Project B is often preferable even if it’s more expensive and/or its AI is less powerful.
*See the calculation in my above comment: A PGS explaining 4% of variance in a trait can reduce this trait by 0.2 standard deviations in one generation. This might enable 1 SD (?) in 10 in vitro generations; though I don’t know, maybe one would run out of additive variance long before?
**pnorm(12, mean=10, sd=1, lower.tail=FALSE) / pnorm(12, mean=9, sd=1, lower.tail=FALSE) = 16.85. This defines extreme psychopathy and/or sadism as being 2 SDs or more above the norm, assumes that these traits are normally distributed, and that project B indeed has average scores of 1SD less than project A. (It also assumes IQ means for the two projects are identical, which is not realistic.)
(Epistemic disclaimer: My understanding of genetics is very limited.)
If additive heritability for all the relevant personality traits was zero, many interventions in this area are pointless, yes.
I might have underestimated this problem but one reason why I haven’t given up on the idea of selecting against “malevolent” traits is that I’ve come across various findings indicating SNP heritabilities of around 10% for relevant personality traits. (See the last section of this comment for a summary of various studies).
SNP heritabilities of ~10% (or even more) for relevant personality traits seem also not implausible on theoretical grounds. If I understand Penke et al. (2007, see Table 1 in particular) correctly, balancing-selection models of personality predict that personality traits should show less additive heritability than, say, cognitive ability, but not (necessarily) zero additive heritability.
Granted, 10% is pretty low, but is it hopelessly low? According to Karavani et al. (2019), a polygenic score for IQ which explains 4% of the variance, would enable an average increase of 3 IQ points (assuming 10 available embryos). I infer from this that a polygenic score which can explain only ~4% of the variance in, say, psychopathy would still enable the reduction of ~ 1⁄5 of a standard deviation in average psychopathy scores, assuming 10 embryos. Polygenic scores explaining ~10% of the variance might thus enable considerably larger average reductions of ⅓ - ½ of a standard deviation or so (numbers pulled out of my posterior).
Again, ⅓ of a SD might seem underwhelming but, as you emphasize in your essay on embryo selection, small changes in the mean of a normal distribution can have large effects out on the tails, so this could still lead to surprisingly large reductions in the frequency of extreme psychopathy or sadism (~psychopathy scores 2-3 SDs above the norm), even in “normal” IVF embryo selection. When applied in iterated embryo selection (IES), this could result in much stronger effects still.
Again, I could easily be wrong about any of the above.
Will SNP heritability estimates increase with larger sample sizes?
This is at least what Tielbeek et al. (2017) suggest: “Recent GWASs on other complex traits, such as height, body mass index, and schizophrenia, demonstrated that with greater sample sizes, the SNP h2 increases. [...] we suspect that with greater sample sizes and better imputation and coverage of the common and rare allele spectrum, over time, SNP heritability in ASB [antisocial behavior] could approach the family based estimates.”
Higher additive heritability for personality disorders?
Another point that makes me somewhat hopeful is that specific personality disorders seem to show larger additive heritabilities than personality traits. For example, the meta-analysis by Polderman et al. (2015, Table 2) suggests that 93% of all studies on specific personality disorders “are consistent with a model where trait resemblance is solely due to additive genetic variation”. (Of note, for “social values” this fraction is still 63%).
And a lot of the benefits in this area might come from selecting against, say, antisocial or narcissistic personality disorder (sadly, sadistic personality disorder is not a thing anymore but it was included in the appendix of DSM-II).
But it’s been a while since I read the Polderman paper and I’m also a bit confused by how there can be high additive heritability for, say, narcissistic personality disorder but very low additive heritability for narcissism as a trait, so the above might be wrong.
Some interventions in this area don’t require additive heritability
There are also interventions that work, even if additive heritability is zero though they assume that the non-additive genetic variance is at least partly due to dominance and not solely due to epistasis; I think. For example, ensuring that the parents of the first generation of IES embryos score low on dark tetrad traits or influencing the first genome synthesis projects to make their first genomes as similar to those of people scoring low on dark tetrad traits as possible (alongside edits to achieve substantial IQ increases, of course).
Lastly, there are interventions that have nothing to do with genetic enhancement but would benefit from more research on and advocacy for screening against malevolent traits and are thus somewhat related to the above. For example, it seems valuable to develop better measures of malevolent traits, potentially ones that are impossible to game such as neuroimaging techniques. Such measures could then be used in various high-impact settings to. For example, they would enable decision makers to better screen for highly elevated dark tetrad traits in government officials, humans whose brains will be used to create the first ems, and human overseers in AI projects. (Currently, all measures of malevolence seem to be self-report questionnaires or interviews which seem easily gameable by smart psychopaths.)
Is non-additive genetic variance really useless?
(No need to reply to the questions in this section.)
Assume that all of the genetic variance in trait A is due to dominance. Wouldn’t it still be possible to achieve non-zero increases/decreases in trait A via (iterated) embryo selection?
And what about epistasis? Is it just that there are quadrillions of possible combinations of interactions and so you would need astronomical sample sizes to achieve sufficient statistical power after correcting for multiple comparisons?
Some evidence for non-zero SNP heritabilities of relevant personality traits
Table 4 of Sanchez‐Roige et al. (2018) provides a good summary. Below, I focus on studies examining traits that likely correlate with dark tetrad traits, such as agreeableness and conscientiousness.
The UK biobank (N ≈ 290k) estimates SNP heritabilities of around 10% for various personality traits, some of which probably even correlate with psychopathy, such as the items “do you often feel guilty?” and “Do you worry too long after an embarrassing experience?”. (Don’t get me wrong, I’m not saying that we should select against traits that only correlate with psychopathy while being completely fine in themselves, like e.g. not often feeling guilty. I’m just listing these items to support the hypothesis that as long as we can find SNP heritability for them, we can expect to find SNP heritabilities for related traits as well.) Unfortunately, the UK biobank didn’t seem to measure any personality trait apart from neuroticism (estimated SNP heritability: 11%). Also, they usually didn’t even use likert scales, only dichotomous yes/no responses, which might reduce heritability estimates (??).
A GWAS (N = 46,861) by Warrier et al. (2018) found an additive heritability, explained by all the tested SNPs, for the Empathy Quotient of 11%. (The Empathy Quotient contains items like “I get upset if I see people suffering on news programmes” and “I really enjoy caring for other people” and thus probably correlates negatively with dark tetrad traits.)
Verweij et al. (2012) give a SNP heritability of 6.6% for harm avoidance which likely correlates with dark tetrad traits.
Lo et al. (2017) estimate SNP-based heritabilities of 18% for extraversion, 8.5% for agreeableness and 9.6% for conscientiousness (see supplementary table 2). (N = 59,176).
Granted, Power and Pluess (2015) estimate SNP heritability of agreeableness and conscientiousness as 0%. However, their sample size of 5,011 is much smaller than the sample sizes above and they write: “It is worth noting that the large standard errors around the negative findings suggest increased sample size may identify a low but significant level of heritability.”
I don’t know why Tielbeek says that, unless he’s confusing SNP heritability with PGS: a SNP heritability estimate is unconnected to sample size. Increasing n will reduce the standard error but assuming you don’t have a pathological case like GCTA computations diverging to a boundary of 0, it should not on average either increase or decrease the estimate… Better imputation and/or sequencing more will definitely yield a new, different, larger SNP heritability, but I am really doubtful that it will reach the family-based estimates: using pedigrees in GREML-KIN doesn’t reach the family-based Neuroticism estimate, for example, even though it gets IQ close to the IQ lower bound.
Twin analysis can’t distinguish between rare and common variants, AFAIK.
The SNP heritabilities I’m referring to are https://en.wikipedia.org/w/index.php?title=Genome-wide_complex_trait_analysis&oldid=871623331#Psychological There’s quite low heritabilities across the board, and https://www.biorxiv.org/content/10.1101/106203v2 shows that the family-specific rare variants (which are still additive, just rare) are almost twice as large as the common variants. A common SNP heritability of 10% is still a serious limit, as it upper bounds the PGS which will be available anytime soon, and also hints at very small average effects making it even harder. Actually, 10% is much worse than it seems even if you compare to the quoted IQ’s 30%, because personality is easy to measure compared to IQ, and the UKBB has better personality inventories than IQ measures (at least, substantially higher test-retest reliabilities IIRC).
Yes. It is difficult to foresee any path towards cracking a reasonable amount of the epistasis, unless you have faith in neural net magic starting to work when you have millions or tens of millions of genomes, or something. So for the next decade, I’d predict, you can write off any hopes of exploiting epistasis to a degree remotely like we already can additivity. (Epistasis does make it a little harder to plan interventions: do you wind up in local optima? Does the intervention fall apart in the next generation after recombination? etc. But this is minor by comparison to the problem that no one knows what the epistasis is.) I’m less familiar with how well dominance can work.
----
So to summarize: the SNP heritabilities are all strikingly low, often <10%, and pretty much always <20%. These are real estimates and not anomalies driven by sampling error, nor largely deflated by measurement error. The PGSes, accordingly, are often near-zero and have no hits. The affordable increases in sample sizes using common SNP genotyping will push it up to the SNP heritability limit, hopefully; but for perspective, recall that IQ PGSes 2 years ago were *already* up to 11% (Allegrini et al 2018) and still have at least 20% to go, and IQ isn’t even that big a GWAS success story (eg height is >40%). The ‘huge success’ story for personality research is that with another few million samples years and years from now, they can reach where a modestly successful trait was years ago before they hit a hard deadend and will need much more expensive sequencing technology in generally brandnew datasets, at which point the statistical power issues become far more daunting (because rare variants by definition are rare), and other sources of predictive power like epistatic variants will remain inaccessible (barring considerable luck in someone coming up with a method which can actually handle epistasis etc). The value of the possible selection for the foreseeable future will be very small, and is already exceeded by selection on many other traits, which will continue to progress more rapidly, increasing the delta, and making selection on personality traits an ever harder sell to parents since it will largely come at the expense of larger gains on other traits.
Could you select for personality traits? A little bit, yeah. But it’s not going to work well compared to things selection does work well for, and it will continue not working well for a long time.
Thanks, all of that makes sense, agree. I also wondered why SNP heritability estimates should increase with sample size.
To summarize, my sense is the following: Polygenic scores for personality traits will likely increase in the medium future, but are very unlikely to ever predict more than, say, ~25% of variance (and for agreeableness maybe never more than ~15% of variance). Still, there is a non-trivial probability (>15%) that we will be able to predict at least 10% of variance in agreeableness based on DNA alone within 20 years, and more than >50% probability that we can predict at least 5% of variance in agreeableness within 20 years from DNA alone.
Or do you think these predictions are still too optimistic?
Interesting, thanks.
But couldn’t one still make use of rare variants, especially in genome synthesis? Maybe also in other settings?
I agree that selecting for IQ will be much easier and more valuable than selecting for personality traits. It could easily be the case that most parents will never select for any personality traits.
However, especially if we consider IES or genome synthesis, even small reductions in dark personality traits—such as extreme sadism—could be very valuable from a long-termist perspective.
For example, assume it’s 2050, IES is feasible and we can predict 5% of the variance in dark traits like psychopathy and sadism based on DNA alone. There are two IES projects: IES project A only selects for IQ (and other obvious traits relating to e.g. health), IES project B selects for IQ and against dark traits, otherwise the two projects are identical. Both projects use 1-in-10 selection, for 10 in vitro generations.
According to my understanding, the resulting average psychopathy and sadism scores of the humans created by project B could be about one SD* lower compared to project A. Granted, the IQ scores would also be lower, but probably by no more than 2 standard deviations (? I don’t know how to calculate this at all, could also be more).
It depends on various normative and empirical views whether this is worth it, but it very well might be: 180+IQ humans with extreme psychopathy or sadism scores might substantially increase all sorts of existential risks, and project A would create almost 17 times** as many such humans compared to project B, all else being equal.
The case for trying to reduce dark traits in humans created via genome synthesis seems even stronger.
One could draw an analogy with AI alignment efforts: Project A has a 2% chance of creating an unaligned AI (2% being the prevalence of humans with psychopathy scores 2 SDs above the norm). Project B has only a 0.1% chance of creating an unaligned AI. Project B is often preferable even if it’s more expensive and/or its AI is less powerful.
*See the calculation in my above comment: A PGS explaining 4% of variance in a trait can reduce this trait by 0.2 standard deviations in one generation. This might enable 1 SD (?) in 10 in vitro generations; though I don’t know, maybe one would run out of additive variance long before?
**pnorm(12, mean=10, sd=1, lower.tail=FALSE) / pnorm(12, mean=9, sd=1, lower.tail=FALSE) = 16.85. This defines extreme psychopathy and/or sadism as being 2 SDs or more above the norm, assumes that these traits are normally distributed, and that project B indeed has average scores of 1SD less than project A. (It also assumes IQ means for the two projects are identical, which is not realistic.)