kman

Karma: 1,174

kman Feb 21, 2025, 4:13 PM
5 points
2
in reply to: RichardJActon’s comment on: How to Make Superbabies
I’m curious about the basis on which you are assigning a probability of causality without a method like mendelian randomisation, or something that tries to assign a probability of an effect based on interpreting the biology like a coding of the output of something like SnpEff to an approximate probability of effect.
Using finemapping. I.e. assuming a model where nonzero additive effects are sparsely distributed among SNPs, you can do Bayesian math to infer how probable each SNP is to have a nonzero effect and its expected effect size conditional on observed GWAS results. Things like SnpEff can further help by giving you a better prior.

kman Feb 21, 2025, 4:07 PM
7 points
1
in reply to: lumire’s comment on: How to Make Superbabies
The SNP heritability estimates for IQ of (h^2 = ~0.2) are primarily based on a low quality test that has a test-retest reliability of 0.6, compared to ~0.9 for a gold-standard IQ test. So a simple calculation to adjust for this gets you a predicted SNP heritability of ~~0.2 * (0.9 / 0.6)^2 = 0.45~~ 0.2 * (0.9 / 0.6) = 0.30 for a gold standard IQ test, which matches the SNP heritability of height. As for the rest of the missing heritability: variants with frequency less than 1% aren’t accounted for by the SNP heritability estimate, and they might contribute a decent bit if there are lots of them and their effects sizes are larger.
EDIT: the original adjustment for test-retest reliability was incorrect: the correlations shouldn’t be squared.

kman Feb 21, 2025, 2:45 AM
4 points
0
in reply to: RichardJActon’s comment on: How to Make Superbabies
Could you expand on what sense you have ‘taken this into account’ in your models? What are you expecting to achieve by editing non-causal SNPs?
If we have a SNP that we’re 30% sure is causal, we expect to get 30% of its effect conditional on it being causal. Modulo any weird interaction stuff from rare haplotypes, which is a potential concern with this approach.
The first paper I linked is about epistasic effects on the additivity of a QTLs for quantitative trait, specifically heading date in rice, so this is evidence for this sort of effect on such a trait.
I didn’t read your first comment carefully enough; I’ll take a look at this.

kman Feb 21, 2025, 2:42 AM
7 points
6
in reply to: jimrandomh’s comment on: How to Make Superbabies
I definitely don’t expect additivity holds out to like +20 SDs. We’d be aiming for more like +7 SDs.

kman Feb 21, 2025, 12:13 AM
1 point
0
in reply to: Noosphere89’s comment on: How to Make Superbabies
I think I’m at <10% that non-enhanced humans will be able to align ASI in time, and if I condition on them succeeding somehow I don’t think it’s because they got AIs to do it for them. Like maybe you can automate some lower level things that might be useful (e.g. specific interpretability experiments), but at the end of the day someone has to understand in detail how the outcome is being steered or they’re NGMI. Not sure exactly what you mean by “automating AI safety”, but I think stronger forms of the idea are incoherent (e.g. “we’ll just get AI X to figure it all out for us” has the problem of requiring X to be aligned in the first place).

kman Feb 20, 2025, 11:50 PM
3 points
2
in reply to: Noosphere89’s comment on: How to Make Superbabies
Much less impactful than automating AI safety.
I don’t think this will work.

kman Feb 20, 2025, 11:23 PM
2 points
0
in reply to: LWLW’s comment on: How to Make Superbabies
So you think that, for >95% of currently living humans, the implementation of their CEV would constitute an S-risk in the sense of being worse than extinction in expectation? This is not at all obvious to me; in what way do you expect their CEVs to prefer net suffering?

kman Feb 20, 2025, 11:11 PM
1 point
0
in reply to: Noosphere89’s comment on: How to Make Superbabies
Because they might consider that other problems are more worth their time, since smartness changes change their values little.
I mean if they care about solving problems at all, and we are in fact correct about AGI ruin, then they should predictably come to view it as the most important problem and start to work on it?
Are you imagining they’re super myopic or lazy and just want to think about math puzzles or something? If so, my reply is that even if some of them ended up like that, I’d be surprised if they all ended up like that, and if so that would be a failure of the enhancement. The aim isn’t to create people who we will then carefully persuade to work on the problem, the aim is for some of them to be smart + caring + wise enough to see the situation we’re in and decide for themselves to take it on.

kman Feb 20, 2025, 10:44 PM
1 point
0
in reply to: Noosphere89’s comment on: How to Make Superbabies
My interpretation is that you’re 99% of the way there in terms of work required if you start out with humans rather than creating a de novo mind, even if many/most humans currently or historically are not “aligned”. Like, you don’t need very many bits of information to end up with a nice “aligned” human. E.g. maybe you lightly select their genome for prosociality + niceness/altruism + wisdom, and treat them nicely while they’re growing up, and that suffices for the majority of them.

kman Feb 20, 2025, 10:36 PM
2 points
0
in reply to: Amy Johnson’s comment on: How to Make Superbabies
Sure, sounds hard though.

kman Feb 20, 2025, 10:33 PM
3 points
0
in reply to: RichardJActon’s comment on: How to Make Superbabies
The SNP itself is (usually) not causal Genotyping arrays select SNPs the genotype of which is correlated with a region around the SNP, they are said to be in linkage with this region as this region tends to be inherited together when recombination happens in meiosis. This is a matter of degree and linkage scores allow thresholds to be set for how indicative a SNP is about the genotype a given region.
This is taken into account by our models, and is why we see such large gains in editing power from increasing data set sizes: we’re better able to find the causal SNPs. Our editing strategy assumes that we’re largely hitting non-causal SNPs.
In practice epistatic interactions between QTLs matter for effects sizes and you cannot naively add up the effect sizes of all the QTLs for a trait and expect the result to reflect the real effect size, even if >50% effect are additive.
I’m not aware of any evidence for substantial effects of this sort on quantitative traits such as height. We’re also adding up expected effects, and as long as those estimates are unbiased the errors should cancel out as you do enough edits.
One thing we’re worried about is cases where the haplotypes have the small additive effects rather than individual SNPs, and you get an unpredictable (potentially deleterious) effect if you edit to a rare haplotype even if all SNPs involved are common. Are you aware of any evidence suggesting this would be a problem?

kman Feb 20, 2025, 7:27 PM
2 points
0
in reply to: TsviBT’s comment on: How to Make Superbabies
This paper found that the heritability of most traits is ~entirely additive, supposedly including IQ according to whatever reference I followed to the paper, though I couldn’t actually find where in the paper it said/implied that.

kman Feb 20, 2025, 6:58 PM
2 points
0
in reply to: kman’s comment on: How to Make Superbabies
IIUC that R = 0.55 number was just the raw correlation between the beta values of the sibling and population GWASes
Actually I don’t think this is correct, it accounted for sampling error somehow. I’ll need to look into this deeper.

kman Feb 20, 2025, 6:51 PM
4 points
0
in reply to: kman’s comment on: How to Make Superbabies
Subtle population stratification not accounted for by the original GWAS could still be an issue, though I don’t expect this would inflate the effects very much. If we had access to raw data we could take into account small correlations between distant variants during finemapping, which would automatically handle assortative mating and stratification.

kman Feb 20, 2025, 6:41 PM
4 points
0
in reply to: Kris Moore’s comment on: How to Make Superbabies
We accounted for inflation of effect sizes due to assortative mating, assuming a mate IQ correlation of 0.4 and total additive heritability of 0.7 for IQ.
IIUC that R = 0.55 number was just the raw correlation between the beta values of the sibling and population GWASes, which is going to be very noisy given the small sample sizes and given that effects are sparse. You can see that the LDSC based estimate is nearly 1, suggesting ~null indirect effects.

kman Feb 20, 2025, 6:35 PM
1 point
0
in reply to: Noosphere89’s comment on: How to Make Superbabies
If they’re that smart, why will they need to be persuaded?

kman Feb 20, 2025, 6:29 PM
1 point
0
in reply to: LWLW’s comment on: How to Make Superbabies
What would it mean for them to have an “ASI slave”? Like having an AI that implements their personal CEV?

kman Feb 20, 2025, 6:18 PM
4 points
2
in reply to: Noosphere89’s comment on: How to Make Superbabies
(And that’s not even addressing how you could get super-smart people to work on the alignment problem).
I mean if we actually succeeded at making people who are +7 SD in a meaningful way, I’d expect that at least good chunk of them would figure out for themselves that it makes sense to work on it.

kman Feb 20, 2025, 6:07 PM
2 points
2
in reply to: LWLW’s comment on: How to Make Superbabies
In that case I’d repeat GeneSmith’s point from another comment: “I think we have a huge advantage with humans simply because there isn’t the same potential for runaway self-improvement.” If we have a whole bunch of super smart humans of roughly the same level who are aware of the problem, I don’t expect the ruthless ones to get a big advantage.
I mean I guess there is some sort of general concern here about how defense-offense imbalance changes as the population gets smarter. Like if there’s some easy way to destroy the world that becomes accessible with IQ > X, and we make a bunch of people with IQ > X, and a small fraction of them want to destroy the world for some reason, are the rest able to prevent it? This is sort of already the situation we’re in with AI: we look to be above the threshold of “ability to summon ASI”, but not above the threshold of “ability to steer the outcome”. In the case of AI, I expect making people smarter differentially speeds up alignment over capabilities: alignment is hard and we don’t know how to do it, while hill-climbing on capabilities is relatively easy and we already know how to do it.
I should also note that we have the option of concentrating early adoption among nice, sane, x-risk aware people (though I also find this kind of cringe in a way and predict this would be an unpopular move). I expect this to happen by default to some extent.

kman Feb 20, 2025, 5:49 PM
2 points
−1
in reply to: Noosphere89’s comment on: How to Make Superbabies
like the fact that any control technique on AI would be illegal because of it being essentially equivalent to brainwashing, such that I consider AIs much more alignable than humans
A lot of (most?) humans end up nice without needing to be controlled / “aligned”, and I don’t particularly expect this to break if they grow up smarter. Trying to control / “align” them wouldn’t work anyway, which is also what I predict will happen with sufficiently smart AI.