Pretty good essay. On first pass, I don’t feel like this post manages to communicate the concept of wholesomeness well enough to pin it down for someone who didn’t already know what this post was trying to communicate. I shall give it a quick go.
When I am choosing an action and justifying it as wholesome, what it often feels like is that I am trying to track all the obvious considerations, but some (be it internal or external) force is pushing me to ignore one of them. Not merely to trade off against it, but to look away from it in my mind. And agains that force I’m trying to defend a particular action as the best one call all things considered—the “wholesome” action.
I am having a hard time thinking of examples, in part because I think I’ve been doing better on this axis in recent years, but I think one of the most tempting versions of this to me has been to ignore people’s feelings and my impacts on them when I have a mission that is very important. For instance, I might think someone has done terribly at some work that they’re doing on a project I’m leading. Now, I think it’s good to be straight with people and it’s good communication to give feedback early and clearly. So I want to let them know that the work has been worse than useless and I regret handing it off to them. This will likely cause them some fear and feel destabilizing to their social status and that will cause them stress and who knows how they deal with that. It is tempting here for me to choose not to pay attention to that when I decide to give them feedback, and as I do so, and after. And I have a great justification—because the work is exceedingly important! And if they say “Ben I feel like you’re being hurtful and not caring about my feelings” I can say “But this is what I have to do for the mission! It’s important! We all agree on that!” And nobody around will disagree because it’s often been the core conceit of my social groups that the only reason we’re here, the only reason we do what we do, is because we think it’s important. And your feelings don’t weigh on the scales of making the project hurt.
(That all may be true, but it doesn’t justify me avoiding seeing the direct impacts of my actions. When I notice this, sometimes I have impulses to do other things too—like reassure them in other ways, or show that I still respect them for other things they’ve done, or pick a time and place that is less likely to be embarrassing, or a dozen other things depending on the context. Admitting what’s happening to myself and acting on the subsequent impulses feels more “wholesome” to me.)
Anyway, I used to be much more willing to stop caring about the impact of my behavior directly on people if I felt that it would distract from getting the important things done. Now I aim to be fully aware, even though it’s actually hard and often quite painful to still go ahead with it while doing that.
Writing this out now I even notice a way I’ve not been very wholesome in my interactions with some individuals I’ve interacted with of late. Noticing why, is not sufficient to solve it, alas, because I am quite allergic to some aspects of the relationship and I think it would be counterproductive to just have it naively be present in our interactions, I might easily act poorly and just make things worse. (I want to think on this more.)
Once you look at the whole of your impact on someone, then you can decide for yourself whether or not to do it. Of course, often you will choose to hurt someone. Reporting a violent crime or theft to the police is often the better decision even though it hurts the individual who broke a law. Even if you look directly at the costs it imposes on them (and the benefits it imposes on their future victims as well as the benefits of maintaining a shared rule of law) I typically do not change my mind about whether I will choose to do something that hurts them.
Overall I would ask yourself “What parts of life and the world do I instinctively turn my attention away from when it comes up?”, and then try to expand the things you can look directly at when making decisions. But I think this is probably assuming already a high level of self-awareness that has some other pre-requisites[1].
Perhaps an easier question is “What decisions have I made that really hurt me to a surprising degree and what did information I turn my attention away from when I made those decisions that could have guided me better and why did I ignore it?” And then use that to notice when you’re susceptible from making less wholesome decisions in your life.
(…having now finished reading the post I see you do talk about this aspect of wholesomeness later on, in the section “Wholesome vs virtuous vs right?”)
Added: A pre-requisite being that, when I ask what parts of the world you instinctively turn your attention away from when it comes up, you go “Oh yes, I can think of examples of this I’ve noticed in myself” rather than going “I dunno, I don’t think I do?” or “How could I know that in-principle, surely I’m avoiding thinking about it?”. This requires skills I have not pointed to in this comment.
I really appreciate the example that you spelled out. I think this is solidly pointing at the same concept.
On this paragraph:
When I am choosing an action and justifying it as wholesome, what it often feels like is that I am trying to track all the obvious considerations, but some (be it internal or external) force is pushing me to ignore one of them. Not merely to trade off against it, but to look away from it in my mind. And agains that force I’m trying to defend a particular action as the best one call all things considered—the “wholesome” action.
… I am inclined to try not to use the word “wholesome” to mean “right” (= the thing you should do, all things considered). I’m trying to use “wholesome” to mean “not looking away from any of the considerations”. This then allows “choosing what feels wholesome is a good heuristic for choosing what is right” to be a substantive claim.
Because of this post, I’ve been thinking a little today about people who I consider wholesome, who often seem wiser than those who don’t (I guess due to tracking things that others have pressures to not think about). I think the main thing I find upsetting about these people is that they tend to less often be holy madmen who commit their life to a cause or do something great, and instead they often do more typical human things like tradeoff against their career and impact on the world in order to get married and have kids.
I think the world will probably end soon and most value will be lost to us and I am kind of upset when people choose not to fight against that but instead to live a simpler and smaller life. Especially so when I thought we were fighting it together and then they just… stop. Then I feel kind of betrayed.
I think something that can go poorly when trying to be more wholesome is that, on finding yourself aware of a cost that you’ve been paying, you can also find that you do not have the strength now to choose to continue paying that cost. Now that you see how you’ve been hurting yourself, even though you’ve been getting great results, you cannot continue to inflict that upon yourself, and so you will instead give up on this course of action and do something less personally difficult.
I think this is a fair complaint! I think it’s quite unwholesome, if you think we’re in a crisis, to turn away and not look at that, or not work towards helping. It seems important to think about safety rails against that. It’s less obviously unwholesome to keep devoting some effort towards typical human things while also devoting some effort towards fighting. (And I think there are a lot of stories I could tell where such paths end up doing better for the world than monomania about the things which seem most important.)
BTW one agenda here is thinking about what kinds of properties we might want societies of AI systems to have. I think there’s some slice of worlds where things go better if we teach our AI systems to be something-in-the-vicinity-of-wholesome than if we don’t.
I’m curious if you have any ideas for what to say to someone who isn’t being wholesome in some context—who is avoiding looking at some part of reality. For instance, in the above example, what could someone say to me when I’m ignoring my impacts upon them?
A standard line people say is “you don’t care about hurting my feelings” and that’s not quite the right response, because I would then argue that your feelings are less important than serving the mission.
I’m looking for something like “You don’t seem to be aware of the impacts you’re having on me”. Or maybe “You don’t seem to understand what he impact of your speech”. But I’m not sure either of these would successfully communicate with the self-blinded Ben I describe, and I’d appreciate hearing another’s thoughts on how to communicate here.
Often the effect of being blinded is that you take suboptimal actions. As you pointed out in your example, if you see the problem then all sorts of cheap ways to reduce the harmful impact occur to you. So perhaps one way of getting to the issue could be to point at that: “I know you care about my feelings, and it wouldn’t have made this meeting any less effective to have had it more privately, so I’m surprised that you didn’t”?
I’d be tempted to make it a question, and ask something like “what do you think the impacts of this on [me/person] are?”.
It might be that question would already do work by getting them to think about the thing they haven’t been thinking about. But it could also elicit a defence like “it doesn’t matter because the mission is more important” in which case I’d follow up with an argument that it’s likely worth at least understanding the impacts because it might help to find actions which are better on those grounds while being comparably good—or even better—for the mission. Or it might elicit a mistaken model of the impacts, in which case I’d follow up by saying that I thought it was mistaken and explaining how.
Pretty good essay. On first pass, I don’t feel like this post manages to communicate the concept of wholesomeness well enough to pin it down for someone who didn’t already know what this post was trying to communicate. I shall give it a quick go.
When I am choosing an action and justifying it as wholesome, what it often feels like is that I am trying to track all the obvious considerations, but some (be it internal or external) force is pushing me to ignore one of them. Not merely to trade off against it, but to look away from it in my mind. And agains that force I’m trying to defend a particular action as the best one call all things considered—the “wholesome” action.
I am having a hard time thinking of examples, in part because I think I’ve been doing better on this axis in recent years, but I think one of the most tempting versions of this to me has been to ignore people’s feelings and my impacts on them when I have a mission that is very important. For instance, I might think someone has done terribly at some work that they’re doing on a project I’m leading. Now, I think it’s good to be straight with people and it’s good communication to give feedback early and clearly. So I want to let them know that the work has been worse than useless and I regret handing it off to them. This will likely cause them some fear and feel destabilizing to their social status and that will cause them stress and who knows how they deal with that. It is tempting here for me to choose not to pay attention to that when I decide to give them feedback, and as I do so, and after. And I have a great justification—because the work is exceedingly important! And if they say “Ben I feel like you’re being hurtful and not caring about my feelings” I can say “But this is what I have to do for the mission! It’s important! We all agree on that!” And nobody around will disagree because it’s often been the core conceit of my social groups that the only reason we’re here, the only reason we do what we do, is because we think it’s important. And your feelings don’t weigh on the scales of making the project hurt.
(That all may be true, but it doesn’t justify me avoiding seeing the direct impacts of my actions. When I notice this, sometimes I have impulses to do other things too—like reassure them in other ways, or show that I still respect them for other things they’ve done, or pick a time and place that is less likely to be embarrassing, or a dozen other things depending on the context. Admitting what’s happening to myself and acting on the subsequent impulses feels more “wholesome” to me.)
Anyway, I used to be much more willing to stop caring about the impact of my behavior directly on people if I felt that it would distract from getting the important things done. Now I aim to be fully aware, even though it’s actually hard and often quite painful to still go ahead with it while doing that.
Writing this out now I even notice a way I’ve not been very wholesome in my interactions with some individuals I’ve interacted with of late. Noticing why, is not sufficient to solve it, alas, because I am quite allergic to some aspects of the relationship and I think it would be counterproductive to just have it naively be present in our interactions, I might easily act poorly and just make things worse. (I want to think on this more.)
Once you look at the whole of your impact on someone, then you can decide for yourself whether or not to do it. Of course, often you will choose to hurt someone. Reporting a violent crime or theft to the police is often the better decision even though it hurts the individual who broke a law. Even if you look directly at the costs it imposes on them (and the benefits it imposes on their future victims as well as the benefits of maintaining a shared rule of law) I typically do not change my mind about whether I will choose to do something that hurts them.
Overall I would ask yourself “What parts of life and the world do I instinctively turn my attention away from when it comes up?”, and then try to expand the things you can look directly at when making decisions. But I think this is probably assuming already a high level of self-awareness that has some other pre-requisites[1].
Perhaps an easier question is “What decisions have I made that really hurt me to a surprising degree and what did information I turn my attention away from when I made those decisions that could have guided me better and why did I ignore it?” And then use that to notice when you’re susceptible from making less wholesome decisions in your life.
(…having now finished reading the post I see you do talk about this aspect of wholesomeness later on, in the section “Wholesome vs virtuous vs right?”)
Added: A pre-requisite being that, when I ask what parts of the world you instinctively turn your attention away from when it comes up, you go “Oh yes, I can think of examples of this I’ve noticed in myself” rather than going “I dunno, I don’t think I do?” or “How could I know that in-principle, surely I’m avoiding thinking about it?”. This requires skills I have not pointed to in this comment.
I really appreciate the example that you spelled out. I think this is solidly pointing at the same concept.
On this paragraph:
… I am inclined to try not to use the word “wholesome” to mean “right” (= the thing you should do, all things considered). I’m trying to use “wholesome” to mean “not looking away from any of the considerations”. This then allows “choosing what feels wholesome is a good heuristic for choosing what is right” to be a substantive claim.
I’d agree with that.
Because of this post, I’ve been thinking a little today about people who I consider wholesome, who often seem wiser than those who don’t (I guess due to tracking things that others have pressures to not think about). I think the main thing I find upsetting about these people is that they tend to less often be holy madmen who commit their life to a cause or do something great, and instead they often do more typical human things like tradeoff against their career and impact on the world in order to get married and have kids.
I think the world will probably end soon and most value will be lost to us and I am kind of upset when people choose not to fight against that but instead to live a simpler and smaller life. Especially so when I thought we were fighting it together and then they just… stop. Then I feel kind of betrayed.
I think something that can go poorly when trying to be more wholesome is that, on finding yourself aware of a cost that you’ve been paying, you can also find that you do not have the strength now to choose to continue paying that cost. Now that you see how you’ve been hurting yourself, even though you’ve been getting great results, you cannot continue to inflict that upon yourself, and so you will instead give up on this course of action and do something less personally difficult.
I think this is a fair complaint! I think it’s quite unwholesome, if you think we’re in a crisis, to turn away and not look at that, or not work towards helping. It seems important to think about safety rails against that. It’s less obviously unwholesome to keep devoting some effort towards typical human things while also devoting some effort towards fighting. (And I think there are a lot of stories I could tell where such paths end up doing better for the world than monomania about the things which seem most important.)
BTW one agenda here is thinking about what kinds of properties we might want societies of AI systems to have. I think there’s some slice of worlds where things go better if we teach our AI systems to be something-in-the-vicinity-of-wholesome than if we don’t.
I’m curious if you have any ideas for what to say to someone who isn’t being wholesome in some context—who is avoiding looking at some part of reality. For instance, in the above example, what could someone say to me when I’m ignoring my impacts upon them?
A standard line people say is “you don’t care about hurting my feelings” and that’s not quite the right response, because I would then argue that your feelings are less important than serving the mission.
I’m looking for something like “You don’t seem to be aware of the impacts you’re having on me”. Or maybe “You don’t seem to understand what he impact of your speech”. But I’m not sure either of these would successfully communicate with the self-blinded Ben I describe, and I’d appreciate hearing another’s thoughts on how to communicate here.
Often the effect of being blinded is that you take suboptimal actions. As you pointed out in your example, if you see the problem then all sorts of cheap ways to reduce the harmful impact occur to you. So perhaps one way of getting to the issue could be to point at that: “I know you care about my feelings, and it wouldn’t have made this meeting any less effective to have had it more privately, so I’m surprised that you didn’t”?
I’d be tempted to make it a question, and ask something like “what do you think the impacts of this on [me/person] are?”.
It might be that question would already do work by getting them to think about the thing they haven’t been thinking about. But it could also elicit a defence like “it doesn’t matter because the mission is more important” in which case I’d follow up with an argument that it’s likely worth at least understanding the impacts because it might help to find actions which are better on those grounds while being comparably good—or even better—for the mission. Or it might elicit a mistaken model of the impacts, in which case I’d follow up by saying that I thought it was mistaken and explaining how.