Love in the Time of Teletransporters

Veganism and caring for your pet https://www.astralcodexten.com/p/love-and-liberty Love Essay Summary:

Core Thesis

Marriage as a moral technology for enabling generosity through future-self commitment

Framework

1. Marriage as Gift-Giving

   • Gift = commitment of future self
   • Particularly valuable when young/resource-poor
   • Functions through public vows rather than private commitment

2. Requirements for Effective Commitment

   • Must be enforceable
   • Must have fixed interpretation
   • Needs widespread social recognition

3. Why Traditional/Widespread Practices Matter

   • Small jurisdiction problem: boutique vows are easy to escape
   • Exception: intensely shared small traditions (cults, gangs) work through:
     • High exit costs
     • Visible markers/handicap principle
     • Dense social networks

4. Interpretive Stability

   • Contrast with legal contracts
   • Community interpretation prevents loophole abuse
   • No single group can unilaterally change meaning
   • Prevents “dead hand” problem while maintaining enforceability

Interesting Edge Cases

• Cloning scenarios reveal tension between:
  • Disjunctive commitments (becoming too loose)
  • Conjunctive commitments (losing autonomy)

Key Innovation

Framing marriage as a Schelling point that enhances positive liberty through constraint

Claude:

Marriage can be seen as a way of giving all the days of the rest of your life to someone. It’s a kind of advance or loan. Credit in financial systems is another kind of advance or loan. What are the implications of this analogy for marriage as an institution, what does it enable? Think from first principles only.

Model response: This is a fascinating economic-philosophical analogy that merits careful analysis. Let me think through the key implications:

If we view marriage as a system of “temporal credit,” several interesting properties emerge:

1. Risk and Trust Marriage, like credit, fundamentally enables activities that would be impossible without long-term commitment. Just as credit allows businesses to make investments larger than their current capital, marriage enables people to make life decisions that require long-term stability - having children, buying property, building communities. The trust inherent in this system creates value that wouldn’t exist otherwise.
2. Collateral and Enforcement In financial credit, collateral and legal enforcement create trust. In marriage, social/legal frameworks and emotional investment serve similar functions. The public nature of marriage, like public credit records, helps enforce commitments through reputational effects. This suggests why societies developed formal marriage institutions rather than leaving relationships purely private.
3. Time Value Just as money has time value in finance (a dollar today is worth more than a dollar tomorrow), time and commitment in marriage have different values at different life stages. Young people “lending” their future time are making a particularly valuable commitment because those years have high option value. This helps explain both why marriage age matters culturally and why divorce tends to be more disruptive early in life.
4. Network Effects Credit systems become more valuable as more participants join because they create reliable networks of trust. Similarly, marriage as an institution becomes more valuable when it’s widespread because it creates stable social networks and allows for intergenerational planning. This suggests why marriage tends to be universal across cultures despite varying forms.
5. Information and Uncertainty Like credit decisions, marriage requires predicting long-term compatibility with limited information. Both systems have developed mechanisms to manage this uncertainty - courtship/dating parallels credit checks, while divorce parallels bankruptcy as a costly but necessary escape valve.

With love stuff, theres prior indifference so no incentove to optimise for part ers, but then a deep attachment afterwards. This could be explained by preference change, or maybe lexical ordering, or non-transitive(?) Partial preferences, where two things are neither better nor worse nor equal, theyre just non-comparable. It seems like theres some connections with justifying indifference in population ethics?

Make a note that a hole in the love essay is figuring out how corrigibility actually works, saying they have conditional preferences kinda kicks the can down the road. You can look at stuart armstrongs papers on corrigibility to see how to get indifference to preference revision. You can then link this to weils comments on indifference to love. Korsgaard and Weil on connecting internalist and externalist virtue

Love and Corrigibility are linked

Eva illouz on love very pog

See kierkegaard on love and marriage as a form of security as freedom

Velleman’s love as a moral emotion (footnotes also have lots of cool citations)

Marriage and Love

Wrt finding the one, liking them more and more is good, but being more and more glad to be yourself is important. This has the aspect of feeling lucky but also approving of your own character more.

Buddhist Upeksha or impartiality as a necessary part of love

Chesterton on love loving the world, love makes what is already there a reason for itself

For love in the time of teletransporters

Preference ordering for premature death then clone romance

A person’s preferences
Romantic/passionate sex w/ clone
remarriage w/ others or single forever
Marry clone
Unromantic sex w/ clone

What’s up with parents being able to effectively signal how unpleasant the sacrifices they make for their children are, while a man on a date cant signal the effort he’s putting into the date is super burdensome? It might be because the guy on the date is trying to signal both that (a) he’ll sacrifice resources to woo you, and (b) these are somehow not really sacrifices for him, maybe because wanting to be liked by you becomes a terminal goal of his. If this is the thing he’s trying to signal, then it might be a kind of submission, signalling that the person he is dating has power over him (via their ability to approve or dissaprove of him). This wouldnt be something parents need or want to signal, so it could explain the difference, but there are probably lots of other explanations. Use in love post

Generosity and loyalty are co beneficial think commitment and marriage. How does the benefit of the commitment vary with the publicity of the commitment? Is shame necessary for it to be a real commitment, or is shame only a proto-virtue, a trait of character needed to become virtuous.

How does the benefit vary with how many people you make it to? What the conditions are? What the odds of needing to call on the commitment are (e.g. marrying a terminally I’ll vs healthy spouse). Length of the commitment relative to your life, spouses life, absolute (consider immortals).

A crucial factor is the strength of the disincentive to breaking the contract, since this changes the EV of the marriage for your spouse by shortening the disvalue tail.

Love as federation; lovers form a third unified entity composed of the lovers acting in concert across many situations, but retaining the possibility of individual action

• This explains something of the mutual conditionality of the desires of the besotted, endless chains no you decide, no you decide punctuated by giggles. After a certain amount of time each realise the other will desire what they desire, and they can simply desire unconditionally, and still fulfil their desire that they desire what the other person desires it, (in a sense because they desire it). Love as the will to benefit for their sake; our desires the benefit the beloved in life turn to wishes that they were benefited in death. Love as eros; Lover values the beloved because she is valuable Love as agape; Beloved becomes valuable to the lover because of the lover’s loving her. Thus love is self-justified, and lacks standards of correctness. Once you’re attached and committed to the beloved, they become the sort of object you ought to have robust concern for.
• To intelligibly bestow value on someone, you must first know what kind of thing they are, what their virtues and vices are, have a sense of what effects their wellbeing. Otherwise you don’t really will their benefit nor the benefit of your partnership. There are various incapacities to love, you can’t love a stone in this way, since it has no wellbeing for you to will, you might not be able to love a perfect saint if you can’t make them any better/what can you give them, you probably can’t love someone completely incompatible with you, someone who can be benefited, but you’re not competent to benefit.

Selectivity of love; we ordinarily think we can justify not only my loving you rather than someone else but also and more importantly the constancy of my love: my continuing to love you even as you change in certain fundamental ways (but not others). As Delaney (1996, p. 347) puts the worry about constancy:

while you seem to want it to be true that, were you to become a schmuck, your lover would continue to love you,…you also want it to be the case that your lover would never love a schmuck.

The issue here is not merely that we can offer explanations of the selectivity of my love, of why I do not love schmucks; rather, at issue is the discernment of love, of loving and continuing to love for good reasons as well as of ceasing to love for good reasons. To have these good reasons seems to involve attributing different values to you now rather than formerly or rather than to someone else, yet this is precisely what Velleman denies is the case in making the distinction between love and respect the way he does.

Love doesn’t just involve mirroring the emotions of the other in a unity, it can involve asymmetric interactions like teasing; To a certain extent, such emotional interdependence involves feeling sympathetic emotions, so that, for example, I feel disappointed and frustrated on behalf of my beloved when she fails, and joyful when she succeeds. However, Baier insists, love is “more than just the duplication of the emotion of each in a sympathetic echo in the other” (p. 442); the emotional interdependence of the lovers involves also appropriate follow-up responses to the emotional predicaments of your beloved. Two examples Baier gives (pp. 443–44) are a feeling of “mischievous delight” at your beloved’s temporary bafflement, and amusement at her embarrassment. The idea is that in a loving relationship your beloved gives you permission to feel such emotions when no one else is permitted to do so, and a condition of her granting you that permission is that you feel these emotions “tenderly.” Moreover, you ought to respond emotionally to your beloved’s emotional responses to you: by feeling hurt when she is indifferent to you, for example. All of these foster the sort of emotional interdependence Baier is after—a kind of intimacy you have with your beloved.

• What’s so good about entering a unity, see EVA fanta. What’s so good about gaining a second pair of hands, eyes, or body? Love seems much better than both of these somehow.

You don’t want to merely love the properties of a person, or a particular type of person, it must link to a particular person via your relation to them, otherwise it’s rational for you to trade up.

You also don’t want the corollary of this that your lover is fungible, suggesting something must tie to the causal history of the beloved/lover

• To avoid this, you realise the commitment to the lover includes a commitment to revise your values together as you revise your persons, when it comes to each other and our interactions, we agree to abide by our private code in almost all cases, perhaps only switching back to a more universal mode of evaluation when out lover ceases to be a fitting partner in our shared activity, via becoming abusive or dictatorial, (as in these cases the shared activity is destroyed, the mutual conditionality of intentions no longer exists).
• There may be cases that fall short of this, where things go badly in a relationship, but we can’t say they have a rational obligation to leave it, despite the fact that they would’ve been better off had they never joined the relationship.

This is an interesting example of the role society plays in enabling virtue via an idealised version of the marriage institution. Cultural variation of virtue generally

Is there any benefit at all to it being tied to romantic love, or is any tradition of public oath making the same. Maybe if you think romantic love is especially constant in a way other forms of love aren’t? Then the institution guides people to make the most generous commitments since the romantically selected commitments are the most likely to last.

Marriage love and contingency too.

How do these unconditional broad scope monogamous oaths offer a better opportunity for generosity than narrow scope promises? By being more directly tied to benefitting them rather than a contingently instrumental part of benefitting them? Amount of discretion in executing commitment wrt how much you benefit them?

Seems like marriage is a special case of a social norm/institution/ritual appearing as a restriction but actually being a moral technology, something that cheapens and extends our moral agency - in this case generosity. How does this relate to Confucian theories of ritual? See Van Norden?

The interesting thing about benevolence/love is the lack of control you have over what you’re optimising for, since the object of your live (the person) can redefine their own interests by their actions, e.g. they could put themselves in danger, or change their values, or become addicted to something. In this way there’s much more variance in the actions love requires than the actions being a bus ticket collector requires.

Also Shelley’s on love is interesting on how the for their benefit and unity accounts of love might converge - in that you can only model their benefit on your aspirations, so when you love them in the agape sense you kind of want to become unified in the sense of locked in coordination somehow? Nehamas on beauty might clarify.

The test for how much you love someone is the difference between how you’d feel if they died vs how you’d feel if you never saw them again.

Social emotions esp anger are in built enforcement mechanisms for contracts, like mechanism design. If other people expect us to be irrationally angry about theft, we will rarely have to be irrationally angry. So for love and guilt, e.g. marriage. We avoid rational jumping on from marriages by being driven by love anchored to that particular person, not any set of their properties. Love is like a mafia boss. Marriage is a prisoners dilemma where you get to choose the partner. Emotion driven involuntary falling in love both spare recursive over thinking their intentions and change the payoffs to shift us to a better equilibrium, similarly for a capacity for heartbreak makes us a trustworthy partner.

How do the marriage vows hold up with split persons lmao. with both partners splitting? Interesting that G goes different ways with the fission and teletransporter cases.

In loving you absolve them of all flaws and subconciously have accepted them not just as a thing to be obtained but your personal goal of how to be

In absolving the object of your unrequited love of flaws, and consequently seeking to immitate them in various ways, you are taking on the flaws they are most aware of, (their own flaws), thereby in pursuit of their love you are making attaining that love more unlikely

How do conditional preferemces not lead into strategic thought bricking of agents. Are their certain conditions the preferences or agents must satisfy to avoid these situations? Just escape clauses that say if simulation depth exceeds 3 say you default to one partner having a non-conditional preference?

See algorithms to live by game theory chapter?
Other explanations of strategic thought?

To desire friendship is a great fault. Friendship should be a gratuitous joy like those afforded by art or life. Friendship is not to be sought, not to be dreamed, not to be desired: it is to be exercised, (it is a virtue).

Veganism love aeg is about acceptable tradeoff threshold/respect with eating animals, not equal love
How does this apply to monogamy?

Why must we love non accidentally in the sense of not being biased with animals, but we can love accidentally with who we meet?

• is the difference one of special attention, or collective action, or retrospective justification, vs. false beliefs about values, as when you count the taste of meat as more important than animal suffering.

Love and social emotions in ATLB notes

There are two ways a material conditional can be true, by having a false antecedent, or by having a true consequent. But the conditional desires of love cannot be fulfilled in two ways, they have a direction, the beloved comes first. Consider the desire, I want it to be the case that, if my beloved is happy, I want to be happy. Mmmm dunno where this is going.

If you love someone, and they are unhappy, you no more want to be happy than you want to create a happy clone of yourself if youre unhappy yourself. This is something to do with the directionality of the conditionals, they are relations of grounding not material conditionals.

Preserving vows through sub-agent splits, cloning, teletransporters. Corrigibility

• Might it help to create agents that are only sub-agents in a sense? Why does our memory alone not have a utility function, and hence not threaten deception, despite composing part of an agent?
  • How do members of a sports team and legs differ? Presumably because the members of a team will still be agents if the team dissolves or reforms, but legs will not.
  • Worth noting that subagents like dopamine circuits often do try to hijack the i/o channels of humans.
  • Ridiculousness of marriage vows not applying to just part of an agent, like a penis is obvious, but less clear when it comes to clones.

Social emotions esp anger are in built enforcement mechanisms for contracts, like mechanism design. If other people expect us to be irrationally angry about theft, we will rarely have to be irrationally angry. So for love and guilt, e.g. marriage. We avoid rational jumping on from marriages by being driven by love anchored to that particular person, not any set of their properties. Love is like a mafia boss. Marriage is a prisoners dilemma where you get to choose the partner. Emotion driven involuntary falling in love both spare recursive over thinking their intentions and change the payoffs to shift us to a better equilibrium, similarly for a capacity for heartbreak makes us a trustworthy partner.

Notes

Scott alexander on solstice for love essay now!

Also elephant in the brain notes

Avoiding the dead hand problem?

The points about cond. Desire are anti-transhuman, loving forkable copies of software disempowers you over your future self, (disj. Vs conj. Desire different kinds of disempowering? Are they really distinct with not desiring not rly being fundamental?) Since if contracts a4e breakable by forking theyre worthless, if theyre not then you can be overwhelmed by something like democratic magnification of whims. What about interpretation of norms in these worlds?

Many of our desires are socially conditional, (mimetic desire?) w/ forking and stuff it seems like we lose right to sue/be sued in some sense.

Somehow it shifts the choices from game theory to public choice theory.

Can there be desire cascades like information cascades?

This is all a cousin of the right to be sued I guess. Maybe I should just check schelling summaries. 

Humans are more like states, whose preferences are illegible to them, than bayesian agents. Do humans have an incentive to change them into something more legible?

This connects to conditional desires, some desires are only pseudo-conditional, when you can identify the world history to utility pairs, others are truly conditional, where you cant identify these pairs, either because of uncertainty about what world states are picked out by the antecedent and consequent of the conditional, or because its logical form is too complex for a bounded agent to infer.

So how do democratic states act when they have these illegible conditional preferences based on the future votes of their population which changes? HLS’s book might be relevant for C-S relations, so might that SSC book review about geopolitics from the non rational actor pov.

The problem of AI systems decisions not being transparent is that they/the norms governing them cant then be revised in a public or democratic way. This is connected to the underdetermination/open-endedness of norms.

Expanding definitions or vows is compression in cs

Funnel/gate conditions for personal persistence of responsibility plausibly also apply for what kinds of collective agents one can enter into without destroying autonomy.

How do i make funnel gate stuff precise with stats, regressions, etc? 

Playful insults are countersignals for spouses having the highest amount of affection/commitment. (though isn’t signalling only relevant in games where there’s a difference of interests and info asymmetry? Mere epistemic incompetence isn’t enough? I guess ignorance of each other’s interests kind of suffices for a risk of accidental interest divergence)

This happens when background info is enough to distinguish low status from high status, but neither from medium. A high status person may then countersignal in a way that shows them to be either low or high status, (resolving to high status with background info), and a medium status person will aim to be distinguished from low-status people by conspicuous consumption). 

Why do males often do the costly signalling? Is it only in polygamous species?

Vows may be imprecise to preserve plausible deniability/allow vow revision, (by community I guess since it’s public)

Schelling on mixed motive games like chicken and the value of self deception. Ignorance must be publicly believed in order to be useful. Since humans have ToM that works for other people, we cant lie perfectly, so the best way to convince others of our ignorance is to either be bad liars, which may have evolved, or incapable of intentionally successfully deceiving others via already having deceived ourselves.

How might aliens without a ToM lie? How might humans and aliens with very different ToMs interact?

Re moral progress breaking apart concepts that previously went together. Crypto and web3 people like vitalik and Glen weyl, tang, etc. are the best at doing this with social concepts, even if their understanding of human complexity and equilibria is not always so great.