I value empathy. Unfortunately, it’s a highly packed word in the way I use it.
Attempting a definition, I’d say it involves creating the most accurate mental models of what people want, including oneself, and trying to satisfy those wants. This makes it a recursive and recursively self-improving model (I think), since one thing I want is to know what else I, and others, want. To satisfy that want, I have to constantly get better at want-knowing.
The best way to determine and to satisfy these preferences appears to be through the use of rationality and future prediction, creating maps of minds and chains of causality, so I place high value on those skills. Without the ability to predict the future or map out minds, “what people want” becomes far too close to wireheading or pure selfishness.
Empathy, to me, involves trying to figure out what the person would truly want, given as much understanding and knowledge of the consequences as possible, contrasting with what they say they want.
I would guess “paperclips and things which are paperclippy”, but that still leaves many open questions.
Is 100 paperclips which last for 100 years better than 1 paperclip which lasts for 100,000 years?
How about one huge paperclip the size of a planet? Is that better or worse than a planetary mass turned into millimeter sized paperclips?
Or maybe you could make huge paperclippy-shapes out of smaller paperclips: using paperclip-shaped molecules to form tiny paperclips which you use to make even bigger paperclips. But again, how long should it last? Would you create the most stable paperclips possible, or the most paperclippy paperclips possible?
And how much effort would you put into predicting and simplifying the future (modeling, basic research, increases in ability to affect the universe, active reductions to surrounding complexity, etc.) instead of making paperclips? You could spend your entire existence in the quest for the definition to ultimate paperclippiness...
Well, User:Rain, that’s about the story of my existence right there. What kinds of paperclips are the right ones? What tradeoffs should I make?
However, regarding the specific matters you bring up, they are mostly irrelevant. Yes, there could be some conceivable situation in which I have to trade off paperclips now against paperclips later. But the way it usually works is that once I obtain or make a paperclip, I move it to the safe zone, where I’ll pretty much have it forever. Also, it’s obviously the number of paperclips that matters, and the constraint on bizarre paperclips is obviously that they have to be able to (counterfactually) hold sheets of paper together.
If you want to get past this abstract philosophizing and on to some concrete problems, it would be better to talk about the dilemma that User:h-H posed to me, in which I must consider alternate models of paperclipping that don’t have the shape of standard paperclips. Here’s my recent progress on thinking about the issue.
My current difficulty is extrapolating my values to cover unexpected situations like this, starting from the simplest algorithm I can find which generates my current preference. The problem is that I can’t think of any simple algorithm that would favor larger numbers of paperclips, but not have them used for anything else, like holding paper together, or unbending them to connect objects (please pardon the repulsive imagery).
So, I’m beginning to think that at least some of the universe should be paper, but I find that quite a repugnant conclusion. It’s a work in progress.
once I obtain or make a paperclip, I move it to the safe zone, where I’ll pretty much have it forever.
How much modeling of the universe have you done, or will you do, to ensure that this is the case? How much effort will you put into creating and defending a suitable safe zone? Will you search the stars for invasive self-replicators (green goo) who may be a threat to your paperclip cache, or will you postpone active offense/defense until such time as you receive a credible threat?
It’s a work in progress.
Humankind has been searching for answers for thousands of years. Do you think you’ll have a better time discovering ultimate paperclippiness? Or will you be content with a lesser understanding (“I did my best”)?
1) I will do all things such that they maximize expected paperclip content of the universe, trading off smaller paperclip quantities for larger ones. I can’t express a more specific algorithm than that without knowing the particulars of the situation.
2) I will do much better than humans at finding the ultimate morality* of the universe because I can spend all my resources to make perfect copies of myself that share my values and update knowledge and reflective value equilibria among each other, rather than having to pursue other values like “signaling” (except when I post here, of course).
* Note I said ultimate morality, not ultimate paperclippiness. There’s a strange tendency here to equate everything I like with “paperclippiness”, and everything humans like with “morality” or “friendliness”. Wrong: we all want morality (humans and clippys), we just disagree about what counts as moral. To use the alternate naming scheme of calling my values “paperclippy” and human values “morality” is to assume away the problem. (Certainly, I sometimes fall into the trap of calling good things, either for humans or clippys, “paperclippy”—see here—but this is just when I’m being imprecise with my phrasings.)
Thanks for answering my questions. I think I have a better understanding of your values now.
My empathy circuits are lighting up, telling me I should buy a box of paperclips and keep them safe for you. And that I should put them on display as a warning to myself.
How do you evaluate your actions as proper or improper, good or bad, right or wrong?
I don’t fully understand how I tell good from bad. A query goes in, an answer pops out in the form of a feeling. Many of the criteria probably come from my parents, from reading books, and from pleasant/unpleasant interactions with other people. I can’t boil it down to any small set of rules that would answer every moral question without applying actual moral sense, and I don’t believe anyone else can.
It’s easier to give a diff, to specify how my moral sense differs from that of other people I know. The main difference I see is that some years ago I deeply internalized the content of Games People Play) and as a result I never demonstrate to anyone that I feel bad about something—I now consider this a grossly immoral act. On the other hand, I cheat on women a lot and don’t care too much about that. In other respects I see myself as morally average.
I value my physical human needs, similarly to Maslow.
I endeavor to value larger, long-term contributions to my needs more than short term ones.
I often act as though I value others’ needs approximately in relation to how well I know them, though I endeavor to value others’ needs equally to my own. Specifically I do this when making a conscious value calculation rather than doing what “feels right.”
I almost always fulfill my own basic needs before fulfilling the higher needs of others; I justify this by saying that I would be miserable and ineffective otherwise but it’s very difficult to make my meat-brain go along with experiments to that end.
My conscious higher order values emerge from these.
Getting pleasure and avoiding pain, just like everyone else. The question isn’t, “What do I value?” but “When do I value it?” (And also, “What brings you pleasure and pain?” But do you really want to know that?)
Getting pleasure and avoiding pain, just like everyone else.
It’s not as simple as that.
Happiness/suffering might be a better distinction. Some people get happiness (and even pleasure) from receiving physical sensations that can be classed as painful (people who like spicy foods, people who are into masochism, etc.). Using happiness/suffering makes it clear that we’re talking about mental states, not physical sensations.
And, of course, there are some people who claim to actually value suffering, e.g. religious leaders who preach it as a means to spiritual cleanliness, though it’s arguable that they’re talking more about pain than suffering, if they find it spiritually gratifying. Or it might behoove us to clarify it further as anticipated happiness/suffering — “What do you value?” meaning “What do you anticipate will maximize your long-term happiness and minimize your long-term suffering?”.
Further, talking about values often puts people in full-force signaling mode. It might actually expand to “What do you want people to think you anticipate will maximize your long-term happiness and minimize your long-term suffering?” So answering “What is your utility function?” (what’s the common pattern behind what you actually do?) or “What is your moral system?” (what’s the common pattern behind how you wish you and others would act?) might be best.
Happiness/unhappiness vs. pleasure/pain—whatever you want to call it. All these sorts of words carry extra baggage, but pleasure/pain seems to carry the least. In particular, if someone asked me, “How do you know you’re happy right now?” I would have to say, “Because I feel good feelings now.”
Re: your second paragraph, I suggest that you’re driving toward my “When do you value?” question above.
As for what I want to signal, that’s a more mundane question for me, but I suppose I want people to see me as empathetic and kind—people seeing me that way gives me pleasure / makes me feel happy.
I value time spent in flow times the amount of I/O between me and the external world.
“Time spent in flow” is a technical term for having a good time.
By I/O (input/output) I mean both information and actions. Talking to people, reading books, playing multiplayer computer games, building pyramids, writing software to be used by other people are examples of high impact of me on the world and/or high impact of the world on me. On the other hand, getting stoned (or, wireheaded) and daydreaming has low interaction with the external world. Some of it is okay though because it’s an experience I can talk to other people about.
I value individual responsibility for one’s own life. As a corollary I value private property and rationality as means to attain the former.
From this I evaluate as good anything that respects property and allows for individual choices. Anything that violates property or impedes choice as bad.
I value individual responsibility for one’s own life. As a corollary I value private property and rationality as means to attain the former.
Are you sure that is your real reason for valuing the latter? I doubt it.
Private property implies responsibility for one’s own life can be taken by your grandfather and those in your community who force others to let you keep his stuff.
Individual responsibility for one’s own life, if that entails actually living, will sometimes mean choosing to take what other people claim as their own so that you may eat.
Private property ensures that you don’t need to take individual responsibility for protecting yourself. Other people handle that for you. Want to see individual responsibility? Find a frontier and see what people there do to keep their stuff.
Always respecting private probability and unimpeded choice guaruntees that you will die. You can’t stop other people from creating a superintelligence in their back yard to burn the cosmic commons. And if they can do that, well, your life is totally in their hands, not yours.
“Are you sure that is your real reason for valuing the latter? I doubt it.”
Why do you think you know my valuations better than me? What evidence do you have?
As for your bullet points, if I eat a sandwich nobody else can. That’s inevitable. Taking responsibility for my own life means producing the sandwich I intend to eat or trade something else I produced for it. If I simply grab what other people produced I shift responsibility to them.
And on the other hand if I produced a sandwich and someone else eats it, I can no longer use the sandwich as I intended. Responsibility presupposes choice because I can not take on responsibility for something I have no choice over. And property simply is the right to choose.
Why do you think you know my valuations better than me? What evidence do you have?
Only the benefit of the doubt.
If you actually value private property because you value individual responsibility then your core value system is based on confusion. Assuming you meant “I value personal responsibility, I value private property, these two beliefs are politically aligned and here is one way that one can work well with the other” puts your position at least relatively close to sane.
And property simply is the right to choose.
No more than Chewbacca is an Ewok. He just isn’t, even if they both happen to be creatures from Star Wars.
No more than Chewbacca is an Ewok. He just isn’t, even if they both happen to be creatures from Star Wars.
So, there’s the problem. I was using property as “having the right to choose what is done with something”. I looked it up in a dictionary but that wasn’t helpful. So what is your definition of property?
Edit:
Wikipedia seems to be on my side: “Depending on the nature of the property, an owner of property has the right to consume, sell, rent, mortgage, transfer, exchange or destroy their property, and/or to exclude others from doing these things.” I think this boils down to “the right to choose what is done with it”.
On a side note it seems that “personal property” is closer to what I meant than “private property”.
Laws pertaining to personal property give me the reasonable expectation that someone else will take, indeed, insist on taking responsibility for punishing anyone who chooses to take my stuff. If I take too much responsibility for keeping my personal property I expect to be arrested. I have handed over responsibility in this instance so that I can be assured of my personal property. This is an acceptable (and necessary) compromise. Personal responsibility is at odds with reliance on social norms and laws enforced by others.
I am all in favor of personal property, individual choice and personal responsibility. They often come closely aligned, packaged together in a political ideology. Yet they are sometimes in conflict and one absolutely does not imply the other.
What do you value?
Here are some alternate phrasings in an attempt to find the same or similar reasoning (it is not clear to me whether these are separate concepts):
What are your preferences?
How do you evaluate your actions as proper or improper, good or bad, right or wrong?
What is your moral system?
What is your utility function?
Here’s another article asking a similar question: Post Your Utility Function. I think people did a poor job answering it back then.
I value empathy. Unfortunately, it’s a highly packed word in the way I use it.
Attempting a definition, I’d say it involves creating the most accurate mental models of what people want, including oneself, and trying to satisfy those wants. This makes it a recursive and recursively self-improving model (I think), since one thing I want is to know what else I, and others, want. To satisfy that want, I have to constantly get better at want-knowing.
The best way to determine and to satisfy these preferences appears to be through the use of rationality and future prediction, creating maps of minds and chains of causality, so I place high value on those skills. Without the ability to predict the future or map out minds, “what people want” becomes far too close to wireheading or pure selfishness.
Empathy, to me, involves trying to figure out what the person would truly want, given as much understanding and knowledge of the consequences as possible, contrasting with what they say they want.
Take a wild, wild guess.
No rush—I’ll wait.
I would guess “paperclips and things which are paperclippy”, but that still leaves many open questions.
Is 100 paperclips which last for 100 years better than 1 paperclip which lasts for 100,000 years?
How about one huge paperclip the size of a planet? Is that better or worse than a planetary mass turned into millimeter sized paperclips?
Or maybe you could make huge paperclippy-shapes out of smaller paperclips: using paperclip-shaped molecules to form tiny paperclips which you use to make even bigger paperclips. But again, how long should it last? Would you create the most stable paperclips possible, or the most paperclippy paperclips possible?
And how much effort would you put into predicting and simplifying the future (modeling, basic research, increases in ability to affect the universe, active reductions to surrounding complexity, etc.) instead of making paperclips? You could spend your entire existence in the quest for the definition to ultimate paperclippiness...
Well, User:Rain, that’s about the story of my existence right there. What kinds of paperclips are the right ones? What tradeoffs should I make?
However, regarding the specific matters you bring up, they are mostly irrelevant. Yes, there could be some conceivable situation in which I have to trade off paperclips now against paperclips later. But the way it usually works is that once I obtain or make a paperclip, I move it to the safe zone, where I’ll pretty much have it forever. Also, it’s obviously the number of paperclips that matters, and the constraint on bizarre paperclips is obviously that they have to be able to (counterfactually) hold sheets of paper together.
If you want to get past this abstract philosophizing and on to some concrete problems, it would be better to talk about the dilemma that User:h-H posed to me, in which I must consider alternate models of paperclipping that don’t have the shape of standard paperclips. Here’s my recent progress on thinking about the issue.
My current difficulty is extrapolating my values to cover unexpected situations like this, starting from the simplest algorithm I can find which generates my current preference. The problem is that I can’t think of any simple algorithm that would favor larger numbers of paperclips, but not have them used for anything else, like holding paper together, or unbending them to connect objects (please pardon the repulsive imagery).
So, I’m beginning to think that at least some of the universe should be paper, but I find that quite a repugnant conclusion. It’s a work in progress.
How much modeling of the universe have you done, or will you do, to ensure that this is the case? How much effort will you put into creating and defending a suitable safe zone? Will you search the stars for invasive self-replicators (green goo) who may be a threat to your paperclip cache, or will you postpone active offense/defense until such time as you receive a credible threat?
Humankind has been searching for answers for thousands of years. Do you think you’ll have a better time discovering ultimate paperclippiness? Or will you be content with a lesser understanding (“I did my best”)?
1) I will do all things such that they maximize expected paperclip content of the universe, trading off smaller paperclip quantities for larger ones. I can’t express a more specific algorithm than that without knowing the particulars of the situation.
2) I will do much better than humans at finding the ultimate morality* of the universe because I can spend all my resources to make perfect copies of myself that share my values and update knowledge and reflective value equilibria among each other, rather than having to pursue other values like “signaling” (except when I post here, of course).
* Note I said ultimate morality, not ultimate paperclippiness. There’s a strange tendency here to equate everything I like with “paperclippiness”, and everything humans like with “morality” or “friendliness”. Wrong: we all want morality (humans and clippys), we just disagree about what counts as moral. To use the alternate naming scheme of calling my values “paperclippy” and human values “morality” is to assume away the problem. (Certainly, I sometimes fall into the trap of calling good things, either for humans or clippys, “paperclippy”—see here—but this is just when I’m being imprecise with my phrasings.)
Thanks for answering my questions. I think I have a better understanding of your values now.
My empathy circuits are lighting up, telling me I should buy a box of paperclips and keep them safe for you. And that I should put them on display as a warning to myself.
A warning of what???
How morality can go awry.
I already have a framed print of Hug Bot on my wall.
I don’t fully understand how I tell good from bad. A query goes in, an answer pops out in the form of a feeling. Many of the criteria probably come from my parents, from reading books, and from pleasant/unpleasant interactions with other people. I can’t boil it down to any small set of rules that would answer every moral question without applying actual moral sense, and I don’t believe anyone else can.
It’s easier to give a diff, to specify how my moral sense differs from that of other people I know. The main difference I see is that some years ago I deeply internalized the content of Games People Play) and as a result I never demonstrate to anyone that I feel bad about something—I now consider this a grossly immoral act. On the other hand, I cheat on women a lot and don’t care too much about that. In other respects I see myself as morally average.
How has not demonstrating to people that you feel bad about something worked out for you?
Very well. It attracts people.
I value my physical human needs, similarly to Maslow.
I endeavor to value larger, long-term contributions to my needs more than short term ones.
I often act as though I value others’ needs approximately in relation to how well I know them, though I endeavor to value others’ needs equally to my own. Specifically I do this when making a conscious value calculation rather than doing what “feels right.”
I almost always fulfill my own basic needs before fulfilling the higher needs of others; I justify this by saying that I would be miserable and ineffective otherwise but it’s very difficult to make my meat-brain go along with experiments to that end.
My conscious higher order values emerge from these.
Getting pleasure and avoiding pain, just like everyone else. The question isn’t, “What do I value?” but “When do I value it?” (And also, “What brings you pleasure and pain?” But do you really want to know that?)
It’s not as simple as that.
Happiness/suffering might be a better distinction. Some people get happiness (and even pleasure) from receiving physical sensations that can be classed as painful (people who like spicy foods, people who are into masochism, etc.). Using happiness/suffering makes it clear that we’re talking about mental states, not physical sensations.
And, of course, there are some people who claim to actually value suffering, e.g. religious leaders who preach it as a means to spiritual cleanliness, though it’s arguable that they’re talking more about pain than suffering, if they find it spiritually gratifying. Or it might behoove us to clarify it further as anticipated happiness/suffering — “What do you value?” meaning “What do you anticipate will maximize your long-term happiness and minimize your long-term suffering?”.
Further, talking about values often puts people in full-force signaling mode. It might actually expand to “What do you want people to think you anticipate will maximize your long-term happiness and minimize your long-term suffering?” So answering “What is your utility function?” (what’s the common pattern behind what you actually do?) or “What is your moral system?” (what’s the common pattern behind how you wish you and others would act?) might be best.
Happiness/unhappiness vs. pleasure/pain—whatever you want to call it. All these sorts of words carry extra baggage, but pleasure/pain seems to carry the least. In particular, if someone asked me, “How do you know you’re happy right now?” I would have to say, “Because I feel good feelings now.”
Re: your second paragraph, I suggest that you’re driving toward my “When do you value?” question above.
As for what I want to signal, that’s a more mundane question for me, but I suppose I want people to see me as empathetic and kind—people seeing me that way gives me pleasure / makes me feel happy.
I value time spent in flow times the amount of I/O between me and the external world.
“Time spent in flow” is a technical term for having a good time.
By I/O (input/output) I mean both information and actions. Talking to people, reading books, playing multiplayer computer games, building pyramids, writing software to be used by other people are examples of high impact of me on the world and/or high impact of the world on me. On the other hand, getting stoned (or, wireheaded) and daydreaming has low interaction with the external world. Some of it is okay though because it’s an experience I can talk to other people about.
I value individual responsibility for one’s own life. As a corollary I value private property and rationality as means to attain the former.
From this I evaluate as good anything that respects property and allows for individual choices. Anything that violates property or impedes choice as bad.
Are you sure that is your real reason for valuing the latter? I doubt it.
Private property implies responsibility for one’s own life can be taken by your grandfather and those in your community who force others to let you keep his stuff.
Individual responsibility for one’s own life, if that entails actually living, will sometimes mean choosing to take what other people claim as their own so that you may eat.
Private property ensures that you don’t need to take individual responsibility for protecting yourself. Other people handle that for you. Want to see individual responsibility? Find a frontier and see what people there do to keep their stuff.
Always respecting private probability and unimpeded choice guaruntees that you will die. You can’t stop other people from creating a superintelligence in their back yard to burn the cosmic commons. And if they can do that, well, your life is totally in their hands, not yours.
“Are you sure that is your real reason for valuing the latter? I doubt it.”
Why do you think you know my valuations better than me? What evidence do you have?
As for your bullet points, if I eat a sandwich nobody else can. That’s inevitable. Taking responsibility for my own life means producing the sandwich I intend to eat or trade something else I produced for it. If I simply grab what other people produced I shift responsibility to them.
And on the other hand if I produced a sandwich and someone else eats it, I can no longer use the sandwich as I intended. Responsibility presupposes choice because I can not take on responsibility for something I have no choice over. And property simply is the right to choose.
Only the benefit of the doubt.
If you actually value private property because you value individual responsibility then your core value system is based on confusion. Assuming you meant “I value personal responsibility, I value private property, these two beliefs are politically aligned and here is one way that one can work well with the other” puts your position at least relatively close to sane.
No more than Chewbacca is an Ewok. He just isn’t, even if they both happen to be creatures from Star Wars.
So, there’s the problem. I was using property as “having the right to choose what is done with something”. I looked it up in a dictionary but that wasn’t helpful. So what is your definition of property?
Edit:
Wikipedia seems to be on my side: “Depending on the nature of the property, an owner of property has the right to consume, sell, rent, mortgage, transfer, exchange or destroy their property, and/or to exclude others from doing these things.” I think this boils down to “the right to choose what is done with it”.
On a side note it seems that “personal property” is closer to what I meant than “private property”.
Laws pertaining to personal property give me the reasonable expectation that someone else will take, indeed, insist on taking responsibility for punishing anyone who chooses to take my stuff. If I take too much responsibility for keeping my personal property I expect to be arrested. I have handed over responsibility in this instance so that I can be assured of my personal property. This is an acceptable (and necessary) compromise. Personal responsibility is at odds with reliance on social norms and laws enforced by others.
I am all in favor of personal property, individual choice and personal responsibility. They often come closely aligned, packaged together in a political ideology. Yet they are sometimes in conflict and one absolutely does not imply the other.