Pigeon Hour

IntroAt the gracious invitation of AI Safety Twitter-fluencer Sarah Hastings-Woodhouse, I appeared on the very first episode of her new podcast “Consistently Candid” to debate moral realism (or something kinda like that, I guess; see below) with fellow philosophy nerd and EA Twitter aficionado Max Alexander, alongside Sarah as moderator and judge of sorts.What I believeIn spite of the name of the episode and the best of my knowledge/understanding a few days ago, it turns out my stance may not be ~genuine~ moral realism. Here’s my basic meta-ethical take:* Descriptive statements that concern objective relative goodness or badness (e.g., "it is objectively for Sam to donate $20 than to buy an expensive meal that costs $20 more than a similar, less fancy meal”) can be and sometimes are true; but* Genuinely normative claims like “Sam should (!) donate $20 and should not buy that fancy meal” are never objectively true.Of course the label per se doesn’t really matter. But for a bunch of reasons it still seems wise to figure out which label really does work best.Some definitionsStanford Encyclopedia of Philosophy: Moral realists are those who think that, in these respects, things should be taken at face value—moral claims do purport to report facts and are true if they get the facts right. Moreover, they hold, at least some moral claims actually are true. That much is the common and more or less defining ground of moral realism (although some accounts of moral realism see it as involving additional commitments, say to the independence of the moral facts from human thought and practice, or to those facts being objective in some specified way).Wikipedia:The robust model of moral realism commits moral realists to three theses:* The semantic thesis: The primary semantic role of moral predicates (such as "right" and "wrong") is to refer to moral properties (such as rightness and wrongness), so that moral statements (such as "honesty is good" and "slavery is unjust") purport to represent moral facts, and express propositions that are true or false (or approximately true, largely false, and so on).* The alethic thesis: Some moral propositions are in fact true.* The metaphysical thesis: Moral propositions are true when actions and other objects of moral assessment have the relevant moral properties (so that the relevant moral facts obtain), where these facts and properties are robust: their metaphysical status, whatever it is, is not relevantly different from that of (certain types of) ordinary non-moral facts and properties.And to settle the matter, here’s what some LLM have to say.My prompt:Suppose a person believes the following:1: Descriptive statements that concern objective relative goodness or badness (e.g., "it is objectively for Sam to donate $20 than to buy an expensive meal that costs $20 more than a similar, less fancy meal”) can be and sometimes are true; but 2: Genuinely normative claims like “Sam should donate $20 and should not buy that fancy meal” are never objectively true.Is this person best categorized as a moral realist?ChatGPTGiven these two beliefs, the person's stance doesn't align completely with traditional moral realism, which typically asserts that there are objective truths about both moral facts (like the goodness or badness of actions) and moral duties (what one should or should not do). However, it also doesn't fully align with moral anti-realism, since the person believes in some form of objective truth regarding moral value.One possible categorization for this stance could be a form of "value realism" combined with "normative anti-realism" or "normative subjectivism." This would mean that the person believes in objective truths about what is better or worse (value realism) but thinks that what one ought to do (normative claims) is not a matter of objective truth but perhaps of subjective judgment or societal conventions.This position is quite sophisticated and might be best understood as a hybrid or intermediate position in the landscape of moral philosophy, rather than fitting neatly into the category of moral realism or its standard alternatives.Great, so much for trying to fit things into nice little buckets.Claude, fortunately, is more definitive:No, the view described is not best categorized as moral realism. Here's why:Moral realism is the view that there are objective moral facts or truths. A moral realist believes that some moral claims, including normative claims about what one should or shouldn't do, can be objectively and mind-independently true.The view in the example accepts that there can be objective truths about relative degrees of goodness or badness (claim 1). However, it denies that there are objective normative truths about what one should or shouldn't do (claim 2). By rejecting that genuine normative 'should/shouldn't' claims can be objectively true, the view denies a key commitment of moral realism - namely that moral claims can state objective normative facts. At best it allows for objective evaluative facts about goodness/badness, not prescriptive facts about obligations.So this view would be more accurately categorized as a form of moral anti-realism like non-cognitivism or error theory. It does not qualify as moral realism because of its rejection of the existence of objective normative truths that could make strong normative claims justified or true. The commitment to objective evaluative facts alone does not sufficiently qualify the view as realist in the metaethical sense.In summary, the view accepts objective "good/bad" facts but denies objective "should/shouldn't" facts. This combination puts it at odds with core commitments of moral realism, so it is better seen as an anti-realist view.I’m gonna disagree with Claude here, at least in that the bolded claim above (objective normative facts are a key part of moral realism) just seems…wrong? Like all the definitions could replace the term “moral fact” or “moral claim” with “normative fact” and “normative claim” but they do not!So I really don’t have a great answer to which label works best. One of two ~human level chatbots giving me a definitive-sounding “anti-realism” answer is too much evidence for me, whose only formal philosophy training is an undergrad minor, to rule that one out. There are also good arguments, I think, for the “realist label,” as well as for “neither” (i.e., ‘secret third thing’). In fact all of these seem pretty similar in terms of argument convincingness/correctness. So, in sum, 🤷‍♂️.Some tweets on the matter, both of which are images that link to the original:Ok now you can vote:Anyway, long story short, I believe something kinda sorta like moral realism, maybe, and that is what we discuss. Without further ado, here’s the (very imperfect) transcript of the episode. Please note that some of the long blocks of text have been cleaned up a bit via minor rewording. I am too lazy to do that for everything.TranscriptSarah: Hello, and welcome to my first experiment in low effort podcasting. In this episode of the podcast, which I'm now calling Consistently Candid because some people thought that was funny, I talked to Aaron Bergman and Max Alexander about moral realism. Sarah: They kind of debate it. And I, having read the Wikipedia page about five minutes previously, a, occasionally chime in with some opinions that I hadn't thought out very well. So enjoy!Sarah: Anyway, I guess this is my podcast now, but I don't have a name for it yet.Max: That's a good podcast nameSarah: Introduce it.Aaron: Can I broadcast this on Pigeon Hour as well?Sarah: Yeah, sure.Max: Okay, cool.Aaron: Sweet.Sarah: But I also want to make my own thing because people.Aaron: No, totally. But yeah, you can say no, you can copyright it and then sue me.Sarah: No. Well, that's fine. This is totally, like, anyone can broadcast it anywhere they want.Max: You can text or whatever, get on the Trump website.Sarah: Yeah. So you guys have a disagreement, apparently, about moral realism. I have briefly skimmed the Wikipedia page, and I don't have an opinion, but I thought we have it out.Aaron: No, I feel like the format should be that we try to convince you…Sarah: So, yeah, you try and convince me that you each try and convince me you're right, and I will come to a conclusion and let you know who I'm persuaded by. And if at any point I have, like, a thought that's worth articulating, I'll weigh in with that. But I think that's kind of unlikely because I don't really know anything; I'm playing a moderating role here.Max: Well, confusion is worth pointing out or something like that, right?Sarah: Yeah, I can do that at regular intervals. I can tell you how confused I am. That's definitely doable.Aaron: Maybe you should start with, like, do you have an initial take at all, or are you really 50/50?Sarah: I mean, from very briefly reading the Wikipedia, it liked doesn't sound true to me.Max: Oh, hell yeah!Aaron: No. Okay, podcast over.Max: Way over the Wikipedia just to see what says. Did you read actual Wikipedia?Sarah: Wikipedia? Yeah, it says “moral realism (also, ethical realism) is the position that ethical Sentences express propositions that refer to objective features of the world. That is, features independent of subjective opinion.”Aaron: Yeah, facts.Max: Good summary from Wikipedia.Sarah: Fake.Max: My job is going to be easy.Sarah: Then, but I'm totally open to be persuaded.Aaron: Okay. The first thing is that I recognize that it sounds fake, it sounds very sus, but then it actually surprisingly checks out. So I just want to get that on the table.Sarah: Okay, what about if each of you do, like, a little opening spiel about why you think you're right, and then you can yell at each other about it afterwards.Aaron: Yeah. Max, do you want to go first or second?Max: I'll go second.Sarah: Okay.Aaron: Well, the first thing is that. The thing I always say is that I simply deferred to Sharon Hewitt Rawlette, who was on the 80,000 Hours Pod

12-28

01:08:17

Note: I can’t seem to edit or remove the “transcript” tab. I recommend you ignore that and just look at the much higher quality, slightly cleaned up one below. Most importantly, follow Sarah on Twitter! Summary (Written by chatGPT, as you can probably tell)In this episode of Pigeon Hour host Aaron delves deep into the world of AI safety with his guest, Sarah Woodhouse. Sarah shares her unexpected journey from fearing job automation to becoming a recognized voice on AI safety Twitter. Her story starts with a simple Google search that led her down a rabbit hole of existential dread and unexpected fame on social media. As she narrates her path from lurker to influencer, Sarah reflects on the quirky dynamics of the AI safety community, her own existential crisis, and the serendipitous tweet that resonated with thousands.Aaron and Sarah’s conversation takes unexpected turns, discussing everything from the peculiarities of EA rationalists to the surprisingly serious topic of shrimp welfare. They also explore the nuances of AI doom probabilities, the social dynamics of tech Twitter, and Sarah’s unexpected viral fame as a tween. This episode is a rollercoaster of insights and anecdotes, perfect for anyone interested in the intersection of technology, society, and the unpredictable journey of internet fame.Topics discussedDiscussion on AI Safety and Personal Journeys:* Aaron and Sarah discuss her path to AI safety, triggered by concerns about job automation and the realization that AI could potentially replace her work.* Sarah's deep dive into AI safety started with a simple Google search, leading her to Geoffrey Hinton's alarming statements, and eventually to a broader exploration without finding reassuring consensus.* Sarah's Twitter engagement began with lurking, later evolving into active participation and gaining an audience, especially after a relatable tweet thread about an existential crisis.* Aaron remarks on the rarity of people like Sarah, who follow the AI safety rabbit hole to its depths, considering its obvious implications for various industries.AI Safety and Public Perception:* Sarah discusses her surprise at discovering the AI safety conversation happening mostly in niche circles, often with a tongue-in-cheek attitude that could seem dismissive of the serious implications of AI risks.* The discussion touches on the paradox of AI safety: it’s a critically important topic, yet it often remains confined within certain intellectual circles, leading to a lack of broader public engagement and awareness.Cultural Differences and Personal Interests:* The conversation shifts to cultural differences between the UK and the US, particularly in terms of sincerity and communication styles.* Personal interests, such as theater and musicals (like "Glee"), are also discussed, revealing Sarah's background and hobbies.Effective Altruism (EA) and Rationalist Communities:* Sarah points out certain quirks of the EA and rationalist communities, such as their penchant for detailed analysis, hedging statements, and the use of probabilities in discussions.* The debate around the use of "P(Doom)" (probability of doom) in AI safety discussions is critiqued, highlighting how it can be both a serious analytical tool and a potentially alienating jargon for outsiders.Shrimp Welfare and Ethical Considerations:* A detailed discussion on shrimp welfare as an ethical consideration in effective altruism unfolds, examining the moral implications and effectiveness of focusing on animal welfare at a large scale.* Aaron defends his position on prioritizing shrimp welfare in charitable giving, based on the principles of importance, tractability, and neglectedness.Personal Decision-Making in Charitable Giving:* Strategies for personal charitable giving are explored, including setting a donation cutoff point to balance moral obligations with personal needs and aspirations.TranscriptAARON: Whatever you want. Okay. Yeah, I feel like you said this on Twitter. The obvious thing is, how did you learn about AI safety? But maybe you’ve already covered that. That’s boring. First of all, do you want to talk about that? Because we don’t have to.SARAH: I don’t mind talking about that.AARON: But it’s sort of your call, so whatever. I don’t know. Maybe briefly, and then we can branch out?SARAH: I have a preference for people asking me things and me answering them rather than me setting the agenda. So don’t ever feel bad about just asking me stuff because I prefer that.AARON: Okay, cool. But also, it feels like the kind of thing where, of course, we have AI. Everyone already knows that this is just like the voice version of these four tweets or whatever. But regardless. Yes. So, Sarah, as Pigeon Hour guest, what was your path through life to AI safety Twitter?SARAH: Well, I realized that a chatbot could very easily do my job and that my employers either hadn’t noticed this or they had noticed, but they were just being polite about it and they didn’t want to fire me because they’re too nice. And I was like, I should find out what AI development is going to be like over the next few years so that I know if I should go and get good at some other stuff.SARAH: I just had a little innocent Google. And then within a few clicks, I’d completely doom pilled myself. I was like, we’re all going to die. I think I found Geoffrey Hinton because he was on the news at the time, because he just quit his job at Google. And he was there saying things that sounded very uncertain, very alarming. And I was like, well, he’s probably the pessimist, but I’m sure that there are loads of optimists to counteract that because that’s how it usually goes. You find a doomer and then you find a bunch of more moderate people, and then there’s some consensus in the middle that everything’s basically fine.SARAH: I was like, if I just keep looking, I’ll find the consensus because it’s there. I’m sure it’s there. So I just kept looking and looking for it. I looked for it for weeks. I just didn’t find it. And then I was like, nobody knows what’s going on. This seems really concerning. So then I started lurking on Twitter, and then I got familiar with all the different accounts, whatever. And then at some point, I was like, I’m going to start contributing to this conversation, but I didn’t think that anybody would talk back to me. And then at some point, they started talking back to me and I was like, this is kind of weird.SARAH: And then at some point, I was having an existential crisis and I had a couple of glasses of wine or something, and I just decided to type this big, long thread. And then I went to bed. I woke up the next morning slightly grouchy and hungover. I checked my phone and there were all these people messaging me and all these people replying to my thread being like, this is so relatable. This really resonated with me. And I was like, what is going on?AARON: You were there on Twitter before that thread right? I’m pretty sure I was following you.SARAH: I think, yeah, I was there before, but no one ever really gave me any attention prior to that. I think I had a couple of tweets that blew up before that, but not to the same extent. And then after that, I think I was like, okay, so now I have an audience. When I say an audience, like, obviously a small one, but more of an audience than I’ve ever had before in my life. And I was like, how far can I take this?SARAH: I was a bit like, people obviously started following me because I’m freFreaking out about AI, but if I post an outfit, what’s going to happen? How far can I push this posting, these fit checks? I started posting random stuff about things that were completely unrelated. I was like, oh, people are kind of here for this, too. Okay, this is weird. So now I’m just milking it for all its worth, and I really don’t know why anybody’s listening to me. I’m basically very confused about the whole thing.AARON: I mean, I think it’s kind of weird from your perspective, or it’s weird in general because there aren’t that many people who just do that extremely logical thing at the beginning. I don’t know, maybe it’s not obvious to people in every industry or whatever that AI is potentially a big deal, but there’s lots of truckers or whatever. Maybe they’re not the best demographic or the most conducive demographic, like, getting on Twitter or whatever, but there’s other jobs that it would make sense to look into that. It’s kind of weird to me that only you followed the rabbit hole all the way down.SARAH: I know! This is what I…Because it’s not that hard to complete the circle. It probably took me like a day, it took me like an afternoon to get from, I’m worried about job automation to I should stop saving for retirement. It didn’t take me that long. Do you know what I mean? No one ever looks. I literally don’t get it. I was talking to some people. I was talking to one of my coworkers about this the other day, and I think I came up in conversation. She was like, yeah, I’m a bit worried about AI because I heard on the radio that taxi drivers might be out of a job. That’s bad. And I was like, yeah, that is bad. But do you know what else? She was like, what are the AI companies up to that we don’t know about? And I was like, I mean, you can go on their website. You can just go on their website and read about how they think that their technology is an extinction risk. It’s not like they’re hiding. It’s literally just on there and no one ever looks. It’s just crazy.AARON: Yeah. Honestly, I don’t even know if I was in your situation, if I would have done that. It’s like, in some sense, I am surprised. It’s very few people maybe like one, but at another level, it’s more rationality than most humans have or something. Yeah. You regret going down that rabbit hole?SARAH: Yeah, kind of. Although I’m enjoying the Twitter thing and it’s kind of fun, and it turns out there’s endless comedic material that you can get out of impending doom. The whole thing i

11-15

01:14:47

* Follow ⁠Max on Twitter⁠* And read his ⁠blog⁠* Listen here or on Spotify or Apple Podcasts * RIP Google Podcasts 🪦🪦🪦SummaryIn this philosophical and reflective episode, hosts Aaron and Max engage in a profound debate over the nature of consciousness, moral realism, and subjective experience. Max, a skeptic of moral realism, challenges Aaron on the objective moral distinction between worlds with varying levels of suffering. They ponder the hard problem of consciousness, discussing the possibility of philosophical zombies and whether computations could account for consciousness. As they delve into the implications of AI on moral frameworks, their conversation extends to the origins of normativity and the nonexistence of free will.The tone shifts as they discuss practical advice for running an Effective Altruism group, emphasizing the importance of co-organizers and the balance between being hospitable and maintaining normalcy. They exchange views on the potential risks and benefits of being open in community building and the value of transparency and honest feedback.Transitioning to lighter topics, Max and Aaron share their experiences with social media, the impact of Twitter on communication, and the humorous side of office gossip. They also touch on the role of anonymity in online discussions, pondering its significance against the backdrop of the Effective Altruism community.As the episode draws to a close, they explore the consequences of public online behavior for employment and personal life, sharing anecdotes and contemplating the broader implications of engaging in sensitive discourses. Despite their digressions into various topics, the duo manages to weave a coherent narrative of their musings, leaving listeners with much to reflect upon.TranscriptAARON: Without any ado whatsoever. Max Alexander and I discuss a bunch of philosophy things and more.MAX: I don't think moral realism is true or something.AARON: Okay, yeah, we can debate this.MAX: That's actually an issue then, because if it's just the case that utilitarianism and this an axiology, which is true or something, whether or not I'm bothered by or would make certain traits personally doesn't actually matter. But if you had the godlike AI or like, I need to give it my axiological system or something, and there's not an objective one, then this becomes more of a problem that you keep running into these issues or something.AARON: Okay, yeah, let's debate. Because you think I'm really wrong about this, and I think you're wrong, but I think your position is more plausible than you think. My position is probably. I'm at like 70%. Some version of moral realism is true. And I think you're at, like, what? Tell me. Like, I don't know, 90 or something.MAX: I was going to probably 99% or something. I've yet to hear a thing that's plausible or something here.AARON: Okay, well, here, let's figure it out once and for all. So you can press a button that doesn't do Nick. The only thing that happens is that it creates somebody in the world who's experiencing bad pain. There's no other effect in the world. And then you have to order these two worlds. There's no normativity involved. You only have to order them according to how good they are. This is my intuition pump. This isn't like a formal argument. This is my intuition pump that says, okay, the one without that suffering person and no other changes. Subjectively, not subjectively. There's a fact of the matter as to which one is better is, like, not. I mean, I feel like, morally better and better here just are synonyms. All things considered. Better, morally better, whatever. Do you have a response, or do you just want to say, like, no, you're a formal argument.MAX: What makes this fact of the matter the case or something like that?AARON: Okay, I need to get into my headspace where I've done this or had this debate before. I do know. I'll defer to Sharon Roulette not too long ago, like ADK podcast guest who basically made the case for hedonic moral realism and hedonic value being the one thing that intrinsically matters and a moral realist view based on that. And I basically disagree with her. Okay. It's like settling in now. Yeah. So it is just the fact of the matter that pleasure is moral is good. And if you say that's not true, then you're wrong and pain is bad. And if you say that that's not true, you're just wrong. That's kind of the argument. That's it. And then I can build on top of it. Where do you get ordering of the world from? But that's the core of the argument here.MAX: Yeah. I think you need an explanation for why this is the fact of the matter or something.AARON: Okay. I mean, do I need an explanation for why one equals one or something like that? Do you need an explanation?MAX: Yes, I think yes. Really? Because we take this to be the case or something, but the symbols one plus one equals two or something is like by itself not true or something. It's like just a bunch of lines, really, or something. Like there's all these axioms and things we build on with the mathematical system and you could do other ones. There are like a bunch of other systems.AARON: I guess if you're a true epistemological nihilist and you think there are no statements that are true, then I'm probably not going to convince you. Is that the case for you?MAX: I don't think it's the case that there aren't things that are true or something.AARON: Do you think there's anything that is true? Can you give me an example? Is there a bed behind you?MAX: I'll say yes, but that's probably couched. You could probably, I think, represent the universe or something as a bunch of a matrix of atom positions or subatomic particle positions and these things, and maybe the rules that govern the equations that govern how they interact or something.AARON: Yeah, I agree.MAX: Make claims that are truth valuable based on that matrix or something. And then you could be like, we can then draw fuzzy concepts around certain things in this matrix and then say more true and true things or whatever.AARON: So I think our disagreement here is that maybe, I don't know if it's a disagreement, but the hard problem of consciousness introduces the fact that that description of the world is just not complete. You have subjective experience also. Are you a phenomenal realist?MAX: What's the definition of that again?AARON: So you think qualia is like a real legit thing?MAX: Is qualia just experience or something?AARON: I'm sorry, I feel like I'm just depending, assuming that, you know, every single term that has ever been used in philosophy. I feel like the thing that I want to say is qualia is like. Yeah, I'll say it's like subjective experience, basically. But then people will say, like, oh, qualia exists, but not in the sense that people normally think. And. But I want to use the strong version of qualia that people argue about. It's real. It's, like, genuine. There's no illusions going on. There's no such thing as functional qualia. If there's functional pain, it is like a different thing than what people mean when they say pain. Most people mean when they say pace and pain. Most of the time, there's, like, a real, genuine, legit subjective experience going on. Do you think this thing is real?MAX: I would say yes, but it does seem like what I would say subjective experiences or something is like a type of computation or something.AARON: I actually lean towards functionalism. Are you familiar with functionalism and theory of philosophy of mind or whatever?MAX: Yeah. Wouldn't that just be the. I think that's what I said. Right. It's just computations or whatever.AARON: So I'm actually not super sure about this. So I apologize to the philosophical community if I'm getting this wrong, but my sense is that when people say functionalism, sometimes they mean that, as in not exactly empirical, but sort of empirical fact of the world is that if you have some computations, you get Qualia, and other people mean that they are just identical. They are just the same thing. There's no, like, oh, you get one and you get the other. They're just the same thing. And I think to say that computations are identical just mean the same thing as qualia is just not true, because it's at least conceivable that. Tell me if you disagree with this. I claim that it's at least conceivable that you have computers that do some sort of computation that you hypothesize might be conscious, but they are not, in fact, conscious. And I think this is conceivable.MAX: Yeah, I agree. Though I would say when it is the case, something, it doesn't seem that means there's something besides just computations going on, or, like, the specific type of computations, like, really, what you said there is. It's conceivable you could have computations that.AARON: Look like we want. Okay, yeah, sorry. You're right. Actually, what I mean is that. Sorry, not what I mean, but what I should have said is that it is conceivable that functionalism is false. Meaning that you can get. Meaning that you can have two sets of systems doing computations, and one of them has qualia and the other one does not. One of them is conscious, the other one is not. Do you think this is conceivable?MAX: Well, do you mean like identical computations or something? I think that'd be the necessary thing or something, because my computer is doing computations right now, but I don't think it's conscious. And I'm doing computations right now, and I do think I'm conscious.AARON: So if you think that you could run your brain's program on an arbitrarily powerful large computer, do you think it's conceivable that that hypothetical computer would not have conscious experience?MAX: I do, but I think this is like the real question. Or the reason I would say it's conceivable that's not having conscious experience is because I would think your simulation just isn't doing the right sort of thing. You think it is, but it's not. For whatever reason, carbon and a

11-06

01:10:41

* Listen on Spotify or Apple Podcasts* Be sure to check out and follow Holly’s Substack and org Pause AI. Blurb and summary from ClongBlurbHolly and Aaron had a wide-ranging discussion touching on effective altruism, AI alignment, genetic conflict, wild animal welfare, and the importance of public advocacy in the AI safety space. Holly spoke about her background in evolutionary biology and how she became involved in effective altruism. She discussed her reservations around wild animal welfare and her perspective on the challenges of AI alignment. They talked about the value of public opinion polls, the psychology of AI researchers, and whether certain AI labs like OpenAI might be net positive actors. Holly argued for the strategic importance of public advocacy and pushing the Overton window within EA on AI safety issues.Detailed summary* Holly's background - PhD in evolutionary biology, got into EA through New Atheism and looking for community with positive values, did EA organizing at Harvard* Worked at Rethink Priorities on wild animal welfare but had reservations about imposing values on animals and whether we're at the right margin yet* Got inspired by FLI letter to focus more on AI safety advocacy and importance of public opinion* Discussed genetic conflict and challenges of alignment even with "closest" agents* Talked about the value of public opinion polls and influencing politicians* Discussed the psychology and motives of AI researchers* Disagreed a bit on whether certain labs like OpenAI might be net positive actors* Holly argued for importance of public advocacy in AI safety, thinks we have power to shift Overton window* Talked about the dynamics between different AI researchers and competition for status* Discussed how rationalists often dismiss advocacy and politics* Holly thinks advocacy is neglected and can push the Overton window even within EA* Also discussed Holly's evolutionary biology takes, memetic drive, gradient descent vs. natural selectionFull transcript (very imperfect)AARONYou're an AI pause, Advocate. Can you remind me of your shtick before that? Did you have an EA career or something?HOLLYYeah, before that I was an academic. I got into EA when I was doing my PhD in evolutionary biology, and I had been into New Atheism before that. I had done a lot of organizing for that in college. And while the enlightenment stuff and what I think is the truth about there not being a God was very important to me, but I didn't like the lack of positive values. Half the people there were sort of people like me who are looking for community after leaving their religion that they grew up in. And sometimes as many as half of the people there were just looking for a way for it to be okay for them to upset people and take away stuff that was important to them. And I didn't love that. I didn't love organizing a space for that. And when I got to my first year at Harvard, harvard Effective Altruism was advertising for its fellowship, which became the Elite Fellowship eventually. And I was like, wow, this is like, everything I want. And it has this positive organizing value around doing good. And so I was totally made for it. And pretty much immediately I did that fellowship, even though it was for undergrad. I did that fellowship, and I was immediately doing a lot of grad school organizing, and I did that for, like, six more years. And yeah, by the time I got to the end of grad school, I realized I was very sick in my fifth year, and I realized the stuff I kept doing was EA organizing, and I did not want to keep doing work. And that was pretty clear. I thought, oh, because I'm really into my academic area, I'll do that, but I'll also have a component of doing good. I took giving what we can in the middle of grad school, and I thought, I actually just enjoy doing this more, so why would I do anything else? Then after grad school, I started applying for EA jobs, and pretty soon I got a job at Rethink Priorities, and they suggested that I work on wild animal welfare. And I have to say, from the beginning, it was a little bit like I don't know, I'd always had very mixed feelings about wild animal welfare as a cause area. How much do they assume the audience knows about EA?AARONA lot, I guess. I think as of right now, it's a pretty hardcore dozen people. Also. Wait, what year is any of this approximately?HOLLYSo I graduated in 2020.AARONOkay.HOLLYYeah. And then I was like, really?AARONOkay, this is not extremely distant history. Sometimes people are like, oh, yeah, like the OG days, like four or something. I'm like, oh, my God.HOLLYOh, yeah, no, I wish I had been in these circles then, but no, it wasn't until like, 2014 that I really got inducted. Yeah, which now feels old because everybody's so young. But yeah, in 2020, I finished my PhD, and I got this awesome remote job at Rethink Priorities during the Pandemic, which was great, but I was working on wild animal welfare, which I'd always had some. So wild animal welfare, just for anyone who's not familiar, is like looking at the state of the natural world and seeing if there's a way that usually the hedonic so, like, feeling pleasure, not pain sort of welfare of animals can be maximized. So that's in contrast to a lot of other ways of looking at the natural world, like conservation, which are more about preserving a state of the world the way preserving, maybe ecosystem balance, something like that. Preserving species diversity. The priority with wild animal welfare is the effect of welfare, like how it feels to be the animals. So it is very understudied, but I had a lot of reservations about it because I'm nervous about maximizing our values too hard onto animals or imposing them on other species.AARONOkay, that's interesting, just because we're so far away from the margin of I'm like a very pro wild animal animal welfare pilled person.HOLLYI'm definitely pro in theory.AARONHow many other people it's like you and formerly you and six other people or whatever seems like we're quite far away from the margin at which we're over optimizing in terms of giving heroin to all the sheep or I don't know, the bugs and stuff.HOLLYBut it's true the field is moving in more my direction and I think it's just because they're hiring more biologists and we tend to think this way or have more of this perspective. But I'm a big fan of Brian domestics work. But stuff like finding out which species have the most capacity for welfare I think is already sort of the wrong scale. I think a lot will just depend on how much. What are the conditions for that species?AARONYeah, no, there's like seven from the.HOLLYCoarseness and the abstraction, but also there's a lot of you don't want anybody to actually do stuff like that and it would be more possible to do the more simple sounding stuff. My work there just was consisted of being a huge downer. I respect that. I did do some work that I'm proud of. I have a whole sequence on EA forum about how we could reduce the use of rodenticide, which I think was the single most promising intervention that we came up with in the time that I was there. I mean, I didn't come up with it, but that we narrowed down. And even that just doesn't affect that many animals directly. It's really more about the impact is from what you think you'll get with moral circle expansion or setting precedents for the treatment of non human animals or wild animals, or semi wild animals, maybe like being able to be expanded into wild animals. And so it all felt not quite up to EA standards of impact. And I felt kind of uncomfortable trying to make this thing happen in EA when I wasn't sure that my tentative conclusion on wild animal welfare, after working on it and thinking about it a lot for three years, was that we're sort of waiting for transformative technology that's not here yet in order to be able to do the kinds of interventions that we want. And there are going to be other issues with the transformative technology that we have to deal with first.AARONYeah, no, I've been thinking not that seriously or in any formal way, just like once in a while I just have a thought like oh, I wonder how the field of, like, I guess wild animal sorry, not wild animal. Just like animal welfare in general and including wild animal welfare might make use of AI above and beyond. I feel like there's like a simple take which is probably mostly true, which is like, oh, I mean the phrase that everybody loves to say is make AI go well or whatever that but that's basically true. Probably you make aligned AI. I know that's like a very oversimplification and then you can have a bunch of wealth or whatever to do whatever you want. I feel like that's kind of like the standard line, but do you have any takes on, I don't know, maybe in the next couple of years or anything more specifically beyond just general purpose AI alignment, for lack of a better term, how animal welfare might put to use transformative AI.HOLLYMy last work at Rethink Priorities was like looking a sort of zoomed out look at the field and where it should go. And so we're apparently going to do a public version, but I don't know if that's going to happen. It's been a while now since I was expecting to get a call about it. But yeah, I'm trying to think of what can I scrape from that?AARONAs much as you can, don't reveal any classified information. But what was the general thing that this was about?HOLLYThere are things that I think so I sort of broke it down into a couple of categories. There's like things that we could do in a world where we don't get AGI for a long time, but we get just transformative AI. Short of that, it's just able to do a lot of parallel tasks. And I think we could do a lot we could get a lot of what we want for wild animals by doing a ton of surveillance and having the ability to make incredibly precise changes to the ecosystem. Having surveillance so we know when something is like, and the capacity to do

10-17

01:37:43

Listen on: * Spotify* Apple Podcasts* Google PodcastsNote: the core discussion on ethics begins at 7:58 and moves into philosophy of language at ~1:12:19Daniel’s stuff:* AI X-risk podcast * The Filan Cabined podcast* Personal website and blogBlurb and bulleted summary from ClongThis wide-ranging conversation between Daniel and Aaron touches on movies, business drama, philosophy of language, ethics and legal theory. The two debate major ethical concepts like utilitarianism and moral realism. Thought experiments around rational beings choosing to undergo suffering feature prominently. meandering tangents explore the semantics of names and references.* Aaron asserts that total utilitarianism does not imply that any amount of suffering can be morally justified by creating more happiness. His argument is that the affirmative case for this offsetting ability has not been clearly made.* He proposes a thought experiment - if offered to experience the suffering of all factory farmed animals in exchange for unlimited happiness, even a perfectly rational being would refuse. This indicates there are some levels of suffering not offsettable.* Aaron links this to experiences like hunger where you realize suffering can be worse than you appreciate normally. This causes his intuition some suffering can't be outweighed.* Daniel disagrees, believing with the right probabilities and magnitudes of suffering versus happiness, rational beings would take that gamble.* For example, Daniel thinks the atomic bombing of Japan could be offset by reducing more suffering. Aaron is less sure given the pain inflicted.* Daniel also proposes offsets for animal farming, but Aaron doesn't think factory farming harm is offsettable by any amount of enjoyment of meat.* They discuss definitions of rationality and whether evolution pressures against suicide impact the rationality of not killing oneself.* Aaron ties his argument to siding with what a perfectly rational being would choose to experience, not necessarily what they would prefer.* They debate whether hypothetical aliens pursuing "schmorality" could point to a concept truly analogous to human morality. Aaron believes not.Transcript(Very imperfect)AARONO'how's, it going it's going all right.DANIELYeah, I just so yesterday I saw Barbie and today I saw Oppenheimer, so it's good to oh, cool. That cultural.AARONNice, nice.DANIELDo you have takes? Yeah, I thought it was all right. It was a decent view of Oppenheimer as a person. It was like a how? I don't know. I feel like the public can tend to be taken in by this physicist figures you get this with quotes, right? Like, the guy was just very good at having fun with journalists, and now we get these amazing nuggets of wisdom from Einstein. I don't know. I think that guy was just having good I don't know. The thing that I'm coming away from is I thought I only watched Barbie because it was coming out on the same day as Oppenheimer, right? Like, otherwise it wouldn't have occurred to me to watch it. I was like, yeah, whatever. Barbie is, like, along for the ride, and Oppenheimer is going to be amazing, but in like, maybe Oppenheimer was a bit better than Barbie, but I'm not even sure of that, actually.AARONYeah, I've been seeing people say that on Twitter. I haven't seen either, but I've been seeing several people say that I'm following, say, like, Barbie was exceptional. And also that kind of makes sense because I'm following all these EA people who are probably care more about the subject matter for the latter one. So it's like, I kind of believe that Barbie is, like, aesthetically better or something. That's my take. Right.DANIELGuess. Well, if you haven't seen them, I guess I don't want to spoil them for you. They're trying to do different things aesthetically. Right. Like, I'm not quite sure I'd want to say one is aesthetically better. Probably in some ways, I think Barbie probably has more aesthetic blunders than Oppenheimer does. Okay. But yeah, I don't know if you haven't seen it, I feel like I don't want to spoil it for you.AARONOkay. No, that's fine. This isn't supposed to be like probably isn't the most important the most interesting thing we could be talking about is that the bar?DANIELOh, jeez.AARONOh, no, that's a terrible bar. That was like an overstatement. That would be a very high bar. It would also be, like, kind of paralyzing. I don't know. Actually know what that would be, honestly. Probably some social juicy gossip thing. Not that we necessarily have any.DANIELYeah, I think your interestingness. Yeah, I think I don't have the know, the closest to gossip thing I saw was like, do you see this bit of Carolyn Elson's diaries and letters to SBF that was leaked to the.AARONNo, I don't. Was this like today or recently? How recently?DANIELThis was like a few days ago.AARONI've been seeing her face on Twitter, but I don't actually think I know anything about this. And no, I would not have.DANIELBackground of who she is and stuff.AARONYeah, hold on. Let the audience know that I am on a beach family vacation against my will. Just kidding. Not against my will. And I have to text my sister back. Okay, there we go. I mean, I broadly know the FTX story. I know that she was wait, I'm like literally blanking on the Alameda.DANIELThat's the name of research.AARONOkay. Yeah. So she was CEO, right? Yeah. Or like some sort of like I think I know the basics.DANIELThe like, she was one of the OG Stanford EA people and was around.AARONYeah, that's like a generation. Not an actual generation, like an EA generation. Which is what, like six years or.DANIELLike the I don't know, I've noticed like, in the there's like I feel like there's this gap between pre COVID people and post COVID people. No one left their house. Partly people moved away, but also you were inside for a while and never saw anyone in person. So it felt like, oh, there's like this crop of new people or something. Whereas in previous years, there'd be some number of new people per year and they'd get gradually integrated in. Anyway, all that is to say that, I don't know, I think SBF's side of the legal battle leaked some documents to The New York Times, which were honestly just like her saying, like, oh, I feel very stressed and I don't like my job, and I'm sort of glad that the thing is blown up now. I don't know. It honestly wasn't that salacious. But I think that's, like, the way I get in the loop on gossip like some of the New York Times.AARONAnd I eventually I love how it's funny that this particular piece of gossip is, like, running through the most famous and prestigious news organization in the world. Or, like, one of them or something. Yeah. Instead of just being like, oh, yeah, these two people are dating, or whatever. Anyway, okay, I will maybe check that out.DANIELYeah, I mean, honestly, it's not even that interesting.AARONThe whole thing is pretty I am pretty. This is maybe bad, but I can't wait to watch the Michael Lewis documentary, pseudo documentary or whatever.DANIELYeah, it'll be good to read the book. Yeah, it's very surreal. I don't know. I was watching Oppenheimer. Right. And I have to admit, part of what I'm thinking is be if humanity survives, there's going to be this style movie about open AI, presumably, right? And I'm like, oh, man, it'll be amazing to see my friend group depicted on film. But that is going to happen. It's just going to be about FTX and about how they're all criminals. So that's not great.AARONYeah, actually, everybody dunks on crypto now, and it's like low status now or whatever. I still think it's really cool. I never had more than maybe $2,000 or whatever, which is not a trivial I mean, it's not a large amount of my money either, but it's not like, nothing. But I don't know, if it wasn't for all the cultural baggage, I feel like I would be a crypto bro or I would be predisposed to being a crypto bro or something.DANIELYeah. I should say I was like joking about the greedy crypto people who want their money to not be stolen. I currently have a Monero sticker on the back of my a big I don't know, I'm a fan of the crypto space. It seems cool. Yeah. I guess especially the bit that is less about running weird scams. The bit that's running weird scams I'm less of a fan of.AARONYeah. Yes. I'm also anti scam. Right, thank you. Okay, so I think that thing that we were talking about last time we talked, which is like the thing I think we actually both know stuff about instead of just like, repeating New York Times articles is my nuanced ethics takes and why you think about talk about that and then we can just also branch off from there.DANIELYeah, we can talk about that.AARONMaybe see where that did. I luckily I have a split screen up, so I can pull up things. Maybe this is kind of like egotistical or something to center my particular view, but you've definitely given me some of the better pushback or whatever that I haven't gotten that much feedback of any kind, I guess, but it's still interesting to hear your take. So basically my ethical position or the thing that I think is true is that which I think is not the default view. I think most people think this is wrong is that total utilitarianism does not imply that for some amount of suffering that could be created there exists some other extremely large arbitrarily, large amount of happiness that could also be created which would morally justify the former. Basically.DANIELSo you think that even under total utilitarianism there can be big amounts of suffering such that there's no way to morally tip the calculus. However much pleasure you can create, it's just not going to outweigh the fact that you inflicted that much suffering on some people.AARONYeah, and I'd highlight the word inflicted if something's already there and you can't do anything about it, that's kind of neither here nor there as it pertains to your actions or something. So it's really about you increasing, you creating suffering that

08-07

02:05:23

Very imperfect transcript: bit.ly/3QhFgEJSummary from Clong: The discussion centers around the concept of a unitary general intelligence or cognitive ability. Whether this exists as a real and distinct thing. Nathan argues against it, citing evidence from cognitive science about highly specialized and localized brain functions that can be damaged independently. Losing linguistic ability does not harm spatial reasoning ability. He also cites evidence from AI, like systems excelling at specific tasks without general competency, and tasks easy for AI but hard for humans. This suggests human cognition isn’t defined by some unitary general ability. Aaron is more open to the idea, appealing to an intuitive sense of a qualitative difference between human and animal cognition - using symbolic reasoning in new domains. But he acknowledges the concept is fuzzy. They discuss whether language necessitates this general ability in humans, or is just associated. Nathan leans toward specialized language modules in the brain. They debate whether strong future AI systems could learn complex motor skills just from textual descriptions, without analogous motor control data. Nathan is highly skeptical. Aaron makes an analogy to the universe arising from simple physical laws. Nathan finds this irrelevant to the debate. Overall, Nathan seems to push Aaron towards a more skeptical view of a unitary general cognitive ability as a scientifically coherent concept. But Aaron retains some sympathy for related intuitions about human vs animal cognition. Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

07-28

01:09:34

Summary (by Claude.ai)This informal podcast covers a wide-ranging conversation between two speakers aligned in the effective altruism (EA) community. They have a similar background coming to EA from interests in philosophy, rationality, and reducing suffering. The main topic explored is reducing s-risks, or risks of extreme suffering in the future.Winston works for the Center for Reducing Suffering (CRS), focused on spreading concern for suffering, prioritizing interventions, and specifically reducing s-risks. He outlines CRS's focus on research and writing to build a moral philosophy foundation for reducing suffering. Aaron is skeptical s-risk reduction is tractable currently, seeing the research as abstract without a clear theory of change.They discuss how CRS and a similar group CLR are trying to influence AI alignment and digital sentience to reduce potential future s-risks. But Aaron worries about identifying and affecting the "digital neural correlates of suffering." Winston responds these efforts aim to have a positive impact even if unlikely to succeed, and there are potential lock-in scenarios that could be influenced.Aaron explains his hesitancy to donate based on tractability concerns. He outlines his EA independent research, which includes an archive project around nuclear war. More broadly, the two find they largely ethically agree, including on a suffering-focused ethics and "lexical negative utilitarianism within total utilitarianism.Some disagreements arise around the nature of consciousness, with Aaron arguing rejecting qualia implies nihilism while Winston disagrees. They also diverge on moral realism, with Aaron defending it and Winston leaning anti-realist.As they wrap up the wide-ranging conversation, they joke about convincing each other and make predictions on podcast listens. They thank each other for the thought-provoking discussion, aligned in ethics but with some disagreements on consciousness and metaethics. The conversation provides an insider perspective on efforts to reduce s-risks through research and outreach.EA Archive: https://forum.effectivealtruism.org/posts/DndmvDGStD3gTfhXk Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

07-17

01:11:48

Summary/specific topics:- Stress Tests and AI Regulation: Nathan elaborates on the concept of stress tests conducted by central banks. These tests assess the resilience of banks to severe economic downturns and the potential for a domino effect if one bank fails. They believe that lessons from this process can be applied to AI regulation. Aaron agrees, but also highlights the need for a proactive approach to AI regulation, as opposed to the reactive measures often seen in banking regulation.- The Role of Central Banks in AI Regulation: Nathan suggests that institutions structured like central banks, staffed with technical experts and independent from government, could be beneficial for AI regulation. They believe such institutions could respond quickly and effectively to crises. However, they acknowledge that this approach may not be effective if AI development leads to rapid, uncontrollable self-improvement.- Compute Governance: The conversation then shifts to compute governance, which Nathan sees as a promising area for AI regulation due to the obviousness of someone using large amounts of compute. They believe that this could provide governments with a control lever over cutting-edge AI labs, similar to how central banks control banking loans and affairs.- AI Regulation and the Role of Public Actors: Nathan acknowledges that the leaders of major AI labs seem sensible and aligned with AI safety principles. However, they argue that regulation and public actors can play a crucial role in creating common knowledge between labs and preventing a race to the bottom. They also discuss the potential benefits and drawbacks of different regulatory approaches.- Financial Regulation as a Model for AI Regulation: Nathan believes that post-crisis financial regulation, such as the Dodd-Frank Act, has generally been effective. They suggest that AI regulation could follow a similar path, especially if AI becomes a significant part of the economy. However, Aaron expresses skepticism about the ability of political processes to produce effective AI regulation.- Regulation Before and After Crises: The speakers agree that pre-crisis regulation has generally been less effective than post-crisis regulation. They discuss the potential for AI regulation to follow a similar pattern, with effective regulation emerging in response to a crisis.- Regulatory Arbitrage: The conversation concludes with a discussion on regulatory arbitrage, where banks shift activities to where it's cheapest to do business. Despite evidence of this behavior, Nathan notes that there was no race to the bottom in terms of regulation during the financial crisis. Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

07-13

50:03

- Follow Arjun on Twitter: https://twitter.com/panickssery- Read and subscribe to his blog: https://arjunpanickssery.substack.com- A mediocre transcription can be found at https://www.assemblyai.com/playground/transcript/6x5h1mcemt-bff1-40fc-a676-9b59c66985f0🦆 👍 Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

06-30

01:02:09

A transcript can be found at assemblyai.com/playground/transcript/6y7e7wz28c-30aa-4e83-ba4f-1bddf2e23dad Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

06-17

01:15:20

For All Good's inaugural episode, we talked to Rob Wiblin and Keiran Harris of 80,000 Hours about how and why they produce their show. This episode first appeared on their new feed "80,000 Hours: After Hours" here: https://80000hours.org/podcast/episodes/80k-after-hours-philosophy-of-the-80000-hours-podcast/ Hope you find it interesting! Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

03-04

01:54:29

Hear EA Georgetown member Aaron Bergman's recent interview as a guest on the Narratives Podcast! During the show, host Will Jarvis talks to Aaron about a key way he thinks people go wrong when choosing a career, how society treats children, how bureaucracy works, whether the FDA should have to approve medications, his interest in psychopharmacology, and a whole lot more. Check out Narratives at narrativespodcast.com or search for it wherever you're listening to this episode! Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

01-05

49:34

Welcome to All Good, a show by Georgetown Effective Altruism. Get full access to Aaron's Blog at www.aaronbergman.net/subscribe

07-20

00:35

Update Feb 12, 2023: Automated audio experiment with the Automator app no one usesIntroBack in 2016, I got my first job as a summer camp counselor. It was an outdoor adventure day camp, to which the six figure-making lawyers and consultants of Washington, D.C. sent their straight-A getting, lacrosse-playing children for a taste of the great outdoors. The campers ranged from four years of age to 15, with those nine and up able to choose which among the activities—kayaking, rock climbing, horseback riding, and more—to pursue. I, as a typical sheltered suburbanite (though a competitive rock climber rather than a lacrosse player), had attended the camp myself throughout my childhood. We Junior Counselors, or “JCs,” could request which age-activity combinations to supervise. Though I had to do my fair share of toddler-wrangling, I was granted a few weeks in the Big Leagues: the rock climbing program for kids aged 9-15. Each cohort of about 12 campers had 3 staff members: a JC, a head counselor or “HC” at least 18 years old, and an “instructor” to provide technical expertise. As a 16 year old mere months older than some of my campers, it was a little bizarre. I was an Adult, getting paid (barely) to ensure that the youth in my care remained happy and healthy in the rugged Maryland wilderness. By and large, it was a good camp. What I’m about to say doesn’t negate the overall-positive experience of most campers.LyingStaff lied to campers constantly. We were expected to, and generally obliged. Not about important things, either. In fact, the lies generally concerned utterly trivial matters. Child protection is goodNow, I’m not entirely naive. I understand that placing children of all genders in the care of three young adults literally in the woods, including on one overnight campout per week, is a situation tailor-made for abuse. And the camp, to its credit, took this very seriously. We had training after training and rules and guidelines galore designed to ensure that no staff member would ever be tempted to misuse his or her power and status.This was a good thing. Child abuse is bad, and I’m glad we erred on the side of “careful.” I understood that my relationship with the campers was not to be intimate. Staff shouldn’t, and didn’t, reveal the skeletons in their closet to middle schoolers at rock climbing camp. No playing “truth or dare” around the campfire, either. Understood.Casual dishonestyBut did we really have to lie so much? Take my age. Though I don’t recall being explicitly told “you may not reveal your age to campers,” doing just this was an obvious norm among staff. Like any normal human being, the campers wanted to know some basic biographical information about the people they were spending their summers with. This was particularly true for me, a 16 year old who looked about 14 on a good day, whose size-small “counselor” tank top was held up with safety pins to prevent the neck hole from drooping down to my nipples. My fellow counselors, when inevitably asked this question, would say something like “you have to guess” or “six hundred” or “maybe if we win the song competition I’ll tell you at the end of the week” (they wouldn’t). Nobody said “17” or “31” or “sorry, I can’t tell you that.”Though human memory is fallible and it’s been five years, I’m pretty sure I got tired of telling stupid, pointless lies. When campers asked, I made the completely banal decision to answer their question. Our conversations generally went like this:Camper: How old are you?Me: sixteen.Camper: You look like you’re [insert number between 11 and 15].Me: I know.Camper: Ok.And that was that. My authority remained intact. No one stopped listening to me. Maybe I’m indulging myself, but I think the campers might have been pleasantly surprised at, you know, not being lied to for once. I didn’t only do this for the sake of my campers’ dignity. I really did look younger than some of the campers, and it was in my own best interest that they be aware I was not. My fellow counselors didn’t get mad at me. They didn’t bring it up. They just kept on lying to the kids, and I did not. I can’t say for sure I was the only one who told the truth, but I sure never heard anyone else do the same.It wasn’t just my age. They’d ask which school I went to, and (if my memory serves correctly) I told them. I’m sure they asked some things I really couldn’t or shouldn’t have answered, and then I wouldn’t tell them. Ageism Back in my gung-ho veganism days, I remember thinking the term speciesism was really dumb. Damn right, we should treat different species differently. Unlike with, say, racial identity, there really are important differences—moral and otherwise—between dandelions, lobsters, chickens, and humans. I still think the term is ripe for misinterpretation, but I now see the underlying concept as sound. Speciesism is arbitrary differential treatment, rather than differential treatment justified by real differences in underlying traits. Ageism is the same way. We really should treat young kids differently than adults, but only because they have different underlying traits—not because of their age per se. If we don’t think that kids’ have the cognitive capacity or confidence or something to make big life decisions or competently assess risk, fine.I’m not saying we should let infants sign contracts, and I’m not even saying we should never lie to children. Whatever Kant would have you think, dishonesty is sometimes the lesser of two evils and therefore the right thing to do, but the chronological age of the person you’d be lying to isn’t a good enough justification. The socially acceptable prejudiceI guess great minds think alike, because after writing this subheading I came across the AARP’s article “Workplace Age Discrimination Still Flourishes in America.” Under its own subheading, “Ageism: An accepted bias,” it argues thatageism in the workplace occurs every day across America, and it is tolerated or — even worse — unrecognized for what it truly is: discrimination, plain and simple.“Age discrimination is so pervasive that people don’t even recognize it’s illegal,” asserts Kristin Alden, an attorney specializing in employee rights at the Alden Law Group in Washington, D.C. Ageism is most commonly discussed in the context of employment discrimination, but its social acceptability rings just as true in the context of other, non-workplace incarnations. Reasons whyAnyway, I think there are two fundamental reasons why ageism is so common and acceptable:* Age really does correlate with differences in underlying characteristics like mental aptitude.* All adults were once children, and most adults expect to eventually get old.The first reason seems pretty intuitive; it really can be hard to tell what is justified differential treatment (say, not letting toddlers sign legally-binding agreements) and what is straight-up, arbitrary bias.The second point is more subtle. It’s the “I can’t be racist—I have a black friend!” of ageism. “I can’t be biased against children,” we think, “I was a child myself once!” I think there’s a bit of retributive justice going on, too: if I had to endure a childhood of casual, well-meaning disrespect, why shouldn’t I get to enjoy the status-privileges of adulthood?These narratives are rarely made explicit. I’m sure I’ve been disrespectful to children before without saying such things out loud, or even really thinking about them directly. Nor are they malicious. When my fellow counselors and I were lying to the campers, we thought of it as a big joke. We were teasing them, playing a game the campers never agreed to join.This is why ageism is so pernicious. It’s easy to moralize racism and sexism; there are the oppressors and the oppressed. What happens when we’re all on both sides of the power structure, albeit at different times in our lives? This bias, well-intentioned and hidden in plain sight, doesn’t fit well into a compelling moral narrative. Candy-coated contempt If you only read one link in this post, make it the Atlantic’s “There’s a Better Way to Parent: Less Yelling, Less Praise” (warning: uses up one of your monthly free articles), an interview with the author of Hunt, Gather, Parent: What Ancient Cultures Can Teach Us About the Lost Art of Raising Happy, Helpful Little Humans. Part of it reads:Joe Pinsker: Many American parenting strategies, you estimate, are only about 100 years old, and some of them arose more recently than that. What about American parenting sticks out to you as distinctive and particularly strange?Michaeleen Doucleff: One of the craziest things we do is praise children constantly. When I was first working on the book, I recorded myself to see how frequently I praised my little girl, Rosy, and I noticed that I would exaggeratedly react to even her smallest accomplishments, like drawing a flower or writing a letter, with a comment like “Good job!” or “Wow! What a beautiful flower!”This is insane if you look around the world and throughout human history. Everywhere I went, I don’t know if I ever heard a parent praise a child. Yet these kids are incredibly self-sufficient, confident, and respectful—everything we want praise to do, these kids already have it, without the praise.It’s hard to cut back on praise, because it’s so baked in, but later on, I decided to try. It’s not that there’s no feedback, but it’s much gentler feedback—parents will smile or nod if a child is doing something they want. I started doing that, and Rosy’s behavior really improved. A lot of the attention-seeking behavior went away.Doucleff emphasizes how excessive praise induces attention-seeking behavior, but I’d like to draw attention to its direct, first-order effect: children feel disrespected. BaseballI started playing baseball in first grade, and didn’t stop for nearly a decade. During elementary school, I distinctly remember loathing the hollow, meaningless compliments that coach after coach fed to us players (which my fath

06-08

15:44