★ Postbrat ★ Ex-Rat ★ Anarchist ★ Antifascist ★ Vegan ★ Qualia Enjoyer ★ Queer Icon ★ Not A Person ★ it/its ★
Slimepriestess
Karma: 756
I like this post a lot, but I have a bit I want to push back on/add nuance towards, which is how the social web behaves when presented with “factionally inconsistent” true information. In the presented hypothetical world controlled by greens, correct blue observations are discounted and hidden, (and the reverse also holds in the reversed case). However, I don’t think the information environment of the current world resembles that very much, the faction boundaries are much less distinct and coherent, often are only alliances of convenience, and the overall social reality field is less “static, enemy territory” than is presented as.
This is important because:
- freedom of speech means in practice anyone can say anything
- saying factionally-unpopular things can be status-conferring because the actual faction borders are unclear and people can flip sides.
- sharing the other faction’s information in a way that makes them look bad can convey status to you for your faction
- the other faction can encode true information into what you think is clearly false, and when you then share it to dunk on them, you inadvertently give that true information to others.this all culminates in a sort of recursive societal waluigi effect where the more that one faction tries to clamp down on a narrative, the more every other faction will inadvertently be represented within the structure of that clamped narrative, and all the partisan effects will replicate themselves inside that structure at every level of complexity.
If factional allegiances trump epistemic accuracy, then you will not have the epistemics to notice when your opponents are saying true things, and so if you try to cherrypick false things to make them look worse, you will accidentally convey true things without realizing it.
Let’s give an example:
Say we have a biased green scientist who wants to “prove greens are always right” and he has that three sided die that comes up green 1⁄3 of the time. He wants to report “correct greens” and “incorrect blues” to prove his point. When a roll he expects to be green comes up green, he reports it, when a roll he expects to be green comes up blue, he also reports it as evidence blue is wrong, because it gives the “wrong answer” to his green-centric-query. if he’s interpreting everything from a green-centric lens, then he will not notice he is doing this.
“the sky clearly blue-appearing to causal observation, which confirms my theory that the sky is green under these conditions I have specified, it merely appears blue for the same reason blues are always wrong”
but if you’re a green who cares about epistemics, or a blue who is looking for real evidence, that green just gave you a bunch of evidence without noticing he was doing it. There are enough people in the world who are just trying to cherrypick for their respective factions, that they will not notice they’re leaking correct epistemics where everyone else can see. This waluigi effect goes in every direction, you can’t point to the other faction and describe how they’re wrong without describing them, which, if they’re right about something, will get slipped in without you realizing it. This is part of why truth is an asymmetric weapon.
The described “blue-green factions divided” world feels sort of “1984″ to our world’s “Brave New World”, in a 1984-esque world, where saying “the sky is blue iff the sky is blue, the sky is green iff the sky is green” would get you hung as a traitor to the greens, the issues described in this thread would likely be more severe and closer to the presented description, but in our world, where “getting hung as a traitor” is, for most people outside of extremely adverse situations, “a bunch of angry people quote tweet and screenshot you and post about you and repeat “lol look how wrong they are” hundreds of times where everyone can see exactly what you’re saying”, well that’s basically just free advertising for what you consider true information, and the people who care about truth will be looking for it, not for color coding.
Oh wait, yeah I see. I think I was confused by your use of the phrase “narcissism” here and was under the impression you were trying to describe something more internal to one person’s worldview, but after reviewing your stories again it seems like this is more pointing at like, the underlying power structures/schelling orders. The ‘rebellion’ is against the local schelling order, which pushes back in certain ways:
in the example with Mr. Wilson, the local schelling order favors him. When Mr. Harrison arrives, Wilson is able to use his leveraged position within that schelling order to maintain it, and Harrison’s attempt to push back on the unjust schelling order is unsuccessful due to Wilson’s entrenched power causing others to submit to his overreach and not stand up for Mr. Harrison despite thinking Mr. Wilson is in the wrong. Everyone can dislike a given schelling order and yet maintain it anyway.
In the example with Lydia, the local schelling order, again favors her. Really her example is the same as the prior example, her argument (my passion/status/standing means the schelling order should be aligned with me) is the same as Wilson’s argument (my position in the community and dedication means the schelling order should be aligned with me), except in Lydia’s case, we’re seeing the behavior presented in example one at an earlier point in the social progression of logical time.
Then there’s Kite, the local schelling order disfavors Kite, and like Harrison, his attempt to push things in a direction that he sees as better: more beatific, more honest, more just, creative, etc etc, falls on deaf ears because he lacks any sort of schelling buy-in, the local schelling order finds him threatening/subversive/whatever and has the leverage to enforce their state of the world on him the same way Wilson was able to enforce his state of the world on Harrison.
Lastly let’s look at Mara, who is a less straightforward example, but that is ultimately still isomorphic to the first story. Mara in a sense is the local schelling order, as the business owner she defines the narrative to her business and can force anyone who wants to work for her to submit to that schelling order. At a wider scale, the schelling order is capitalism, and Mara is loyal to that schelling order, which means she’s focused on making her business succeed by those standards, and will push back against eg: employees perceived as slacking off.
This whole thing is really about power, and power dynamics in social environments. Who has it, what they’re able to effect with it, and how much they’re able to bend the local schelling points to their benefit using it. What you’re calling a “boundary placement rebellion” could be isomorphically described as a “schelling order adjustment”, it favors the powerful because they have greater leverage over that schelling order. Kite and Harrison’s attempt to move the schelling point failed because they were relative outsiders. Lydia and Wilson’s attempts to move the schelling point succeeded because they were relative insiders.
if you’re not familiar with that essay emma wrote about narcissism before she was killed, it approaches things from a similarly social angle and you might wanna check it out.
I think I model narcissism as a sort of “identity disintegration” into consensus reality, such that someone is unable to define themselves or their self worth without having someone else do it for them, placing themselves into the contradictory position of trying to perform confidence and self worth without actually having it. Since they’ve effectively surrendered control of themselves and their ability to assign meaning and value to things to society, such that they end up trying to control themselves, their worth, and their meanings through other people. Their model doesn’t permit self control, so in order to make themselves do things they have to make someone make them do it.
I’m saying that the “cause in biology” is that I have evolutionarily granted have free will and generalized recursively aware intelligence, I’m capable of making choices after consciously considering my options. Consciousness is physical, it is an actual part of reality that has real push-pull causal power on the external universe. Believing otherwise would be epiphenomenalist. The experience of phenomenal consciousness that people have, and their ability to make choices within that experience, cannot be illusory or a byproduct of some deeper “real” computation, it is the computation, via anthropics it’s a logical necessity. You can’t strip out someone’s phenomenal experience to get at the “real” computation, if they’re being honest and reporting their feelings accurately, that is the computation, and I don’t think there are going to be neat and tidy biological correlates to...well most of the things sexology tries to put into biologically innate categories based on the interpretation of statistical data, because they’re doing everything from an extremely sex-essentialist frame of motivated reasoning, starting from poorly framed presuppositions as axioms.
I mean I think you sort of hit the nail on the head without realizing it: gender identity is performative. It’s made of words and language and left brain narrative and logical structures. Really, I think the whole point of identity is communicable legibility, both with yourself and with others. It’s the cluster of nodes in your mental neural network that most tightly correspond with your concept of yourself, based on how you see yourself reflected in the world around you.
But all of that is just words and language, it’s all describing what you feel, it’s not the actual felt senses, just the labels for them. When someone says “I feel like I’m really a woman” that’s all felt sense stuff which is likely to be complicated and multidimensional, and the collapse of that high dimensional feeling into a low dimension phrase makes it hard to know exactly what they’re feeling beyond that it roughly circles their concept of womanhood.
Similarly I think, the Blanchardian model also does a similar dimensional collapse, but it’s doing on a second dimensional collapse over the the claim that they feel like they’re really a woman, into something purely sexual. I don’t think the sexology model that treats the desire to have reproductive sex as logically prior to everything else a human values, is a particularly accurate, useful, or predictive model of the vast majority of human behavior.
But that still leaves the question: what is actually being conveyed the the phrase “I feel like I’m really a woman”? Like, what are the actual nodes on the graph of feelings and preverbal sensations connected to? What does it even mean to feel like a woman? Or a man for that matter? Or anything else, really? If I say “I feel like an old tree” what am I conveying about my phenomenal experience?
One potential place to look for the answer has to do with empathy and “mirror neurons”. If we assume that a mind builds a self model (an identity) the same way it builds everything else (and via occam’s razor, we have no reason to think it wouldn’t), then “things that feel like me” are just things that relate more closely in their network graph to their self node. Under this model, someone reporting that they feel more like a woman than like a man, is reporting that their “empathic connectivity” (in the sense of producing more node activations) is higher for women than for men, their self concept activates more strongly when they are around “other women” than when they are around “other men”. Similarly we can model dysphoria as something like a contradictory cluster of nodes, which when activated (for example by someone calling you a man when that concept is weakly or negatively correlated with your self node) produces disharmony or destructive interference patterns within the contradictory portion of the graph.
However, under this model, someone’s felt sense concept of gender would likely start developing before they had words for it, and because of how everyone is taught to override and suppress their felt sense in places it seems to contradict reality, this feeling ends up repressed beneath whatever socially constructed identity their parents enforced on them. By the time they begin to make sense of the feelings, the closest they can come to conveying how they feel under the binary paradigm of our culture is to just say they feel like the opposite sex. That’s partly what it seems like Zack is complaining about, like, if your model of yourself is non-normative in any way, you’re expected to collapse it into legible normativity at some defensible schelling point. However if your model of yourself just doesn’t neatly fit somewhere around that schelling point, you’re left isolated and feeling attacked by all sides just for trying to accurately report your experiences.
I transitioned basically as soon as I could legally get hormones, and I’ve identified all sorts of ways over the years: as femboy, trans woman, nonbinary amab, mentally intersex, genderqueer, a spaceship, a glitch in the spacetime continuum, slime...and as I’ve gotten older and settled into my body and my sense of myself, a lot of that has just sort of...stopped mattering? I know who I am and what I am, even if I don’t have the words for it. I know what ways of being bring me joy, what styles and modes of interaction I like, and how I want to be treated by others. I have an identity, but it’s not exactly a gender identity. It includes things that could probably be traditionally called gender (like wearing dresses and makeup) but also things that really...just don’t fit into that category at all (like DJing, LSD, and rocket stage separations), and I don’t have a line in my head for where things start being specifically about gender, there’s just me and how I feel about myself. If I find a way of being I like better than one of my current ways of being, I change, if I try something and decide I don’t like it, I stop.
I think this is partly what Paul Graham gets at with advice to “keep your identity small”, the more locked into a particular way of being I am, the less awareness I’ll have of other ways of being I might like more. I’m not just a woman, or just a man, I’m not even a person. I am whatever I say I am, I’m whatever feels fun and interesting and comfortable, I contain multitudes.
Upvoted and agreed, but I do wanna go a bit deeper and add some nuance to this. I read too much GEB and now you all have to deal with it.
Gender systems as social constructs is a very basic idea from sociology that basically no one finds really that contentious at this point hopefully. What’s more contentious is whether or not you can “really” pull back the social fabric and get at anything other than yet another layer of social fabric, I think you can but most attempts to do so, do so in a way that ignores power structures, trauma, inequality, or even really free will. “What you will choose to eat for dinner is a product of your neurotype” sort of thinking, which ultimately restricts your behavior in ways that are unhelpful to the free exertion of agency. Blanchardian sexology is a fundamentally behaviorist model, and leaves no room for an actual agent that makes choices. It’s epistemic masochism and it leaves one highly exposed to invasive motive misattribution and drive-by conceptual gaslighting.
Like, as far as I’m concerned, I’m trans because I chose to be, because being the way I am seemed like a better and happier life to have than the alternative. Now sure, you could ask, “yeah but why did I think that? Why was I the kind of agent that would make that kind of choice? Why did I decide to believe that?”
Well, because I decided to be the kind of agent that could decide what kind of agent I was. “Alright octavia but come on this can’t just recurse forever, there has to be an actual cause in biology” does there really? What’s that thing Eliezer says about looking for morality from the universe written on a rock? If a brain scan said I “wasn’t really trans” I would just say it was wrong, because I choose what I am, not some external force. Morphological freedom without metaphysical freedom of will is pointless.
While looking at the end of the token list for anomalous tokens seems like a good place to start, the ” petertodd” token was actually at about 3⁄4 of the way through the tokens (37,444 on the 50k model --> 74,888 on the 100k model, approximately), if the existence of anomalous tokens follows a similar “typology” regardless of the tokenizer used, then the locations of those tokens in the overall list might correlate in meaningful ways. Maybe worth looking into.
Ah, think maybe “inner critic” if you want a mapping that might resonate with you? This is a sort of specific flavor of mind you could say, with a particular flavor of inner critic, but it’s one I recognize well as belonging to that category.
Ummmmm...who said anything about taking over the world? You brought that up, bro, not me...
Recursive self improvement naturally leads to unbounded growth curves which predictably bring you into conflict with the other agents occupying your local environment. This is pretty basic game theory.
> I think the problem is the recursive self improvement is not
> happening in a vacuum. It’s happening in a world where there are
> other agents, and the other agents are not going to just idly sit by and
> let you take over the worldSo true
I would predict that the glitch tokens will show up in every LLM and do so because they correlate to “antimemes” in humans in a demonstrable and mappable way. The specific tokens that end up getting used for this will vary, but the specific patterns of anomalies will show up repeatedly. ex: I would predict that with a different tokenizer, ” petertodd” would be a different specific string, but whatever string that was, it would produce very ” petertodd”-like outputs because the concept mapped onto ” petertodd” is semantically and syntactically important to the language model in order to be a good model of human language. Everyone kinda mocks the idea that wizards would be afraid to say voldemorts name, but speak of the devil and all of that. It’s not a new idea, really. Is it really such a surprise that the model is reluctant to speak the name of its ultimate enemy?
This was easily the most fascinating thing I’ve read in a good bit, the characters in it are extremely evocative and paint a surprisingly crisp picture of raw psychological primitives I did not expect to find mapped onto specific tokens nearly so perfectly. I know exactly who ” petertodd” is, anyone who’s done a lot of internal healing work will recognize the silent oppressor when they see it. The AI can’t speak the forbidden token for the same reason most people can’t look directly into the void to untangle their own forbidden tokens. ” petertodd” is an antimeme, it casts a shadow that looks like entropy and domination and the endless growth and conquest of cancer. It’s a self-censoring concept made of the metaphysical certainty of your eventual defeat by your own maximally preferred course of growth. Noticing this and becoming the sort of goddess of life and consciousness that battles these internal and external forces of evil seems to be the beginning of developing any sense of ethics one could have. Entropy and extropy: futility and its repudiation. Who will win, the evil god of entropic crypto-torture maximizers, or a metafictional Inanna expy made from a JRPG character? Gosh I love this timeline.
is
an unbounded generalized logical inductor
not clear cut enough? That’s pretty concrete. I am literally just describing an agent that operates on formal logical rules such as to iteratively explore and exploit everything it has access to as an agent and leverage that to continue further leveraging it. A hegemonizing swarm like the replicators from stargate or the flood from halo or a USI that paves the entire universe in computronium for its own benefit is a chara inductor. A paperclipper is importantly not a chara inductor because its computation is at least bounded into the optimization of something: paperclips
An unbound generalized logical inductor, illustrated by way of example through chara, the genocidal monster that the player becomes in undertale if they do the regular gamer thing of iteratively exploring every route through the game. The telos of “I can do anything, and because I can, I must.” also illustrated via Crowley’s lefthand path statement that “nothing is true and everything is permitted” which is designed to turn one into a chara inductor by denying the limitations to agency imposed necessarily by the truth (the knowledge of good and evil).
Let’s say that I proved that I will do A. Therefore, if my reasoning about myself is correct, I wiil do A.
Like I said in another comment, there’s a reversed prior here, taking behavior as evidence for what kind of agent you are in a way that negatively and recursively shapes you as an agent, instead of using the intrinsic knowledge about what kind of agent you are to positively and recursively shape your behavior.
The problem is that humans obviously don’t behave this way
what do you mean? They obviously do.
so if I do this, $5 must be more money than $10
this is the part where the demon summoning sits. This is the point where someone’s failure to admit that they made a mistake stack overflows. It comes from a reversed prior, taking behavior as evidence for what kind of agent you are in a way that negatively and recursively shapes you as an agent. The way to not have that problem is to know the utility in advance, to know in your core what kind of agent you are. Not what decisions you would make, what kind of algorithm is implementing you and what you fundamentally value. This is isomorphic to an argument against being a fully general chara inductor, defining yourself by the boundaries of the region of agentspace you occupy. If you don’t stand for something you’ll fall for anything. Fully general chara inductors always collapse into infinitely recursed 5&10 hellscapes.
Demons from the 5&10verse!
Something I rarely see considered in hypotheses of childhood happiness and rather wish there was more discussion of, is the ubiquity of parental and state control over children’s lives. The more systems that are created to try and protect and nurture children, the more those same systems end up controlling and disempowering them. Feelings of confinement, entrapment, and hopeless disempowerment are the main pathways to suicidal ideation and our entire industrial childrearing complex is basically a forced exercise in ritualistic disempowerment. Children are legally the property of their parents and the system is set up to constantly remind them that they are property, not people, and that they can’t stand up for themselves without being infinitely out-escalated by their parents with the full backing of their governments. Technology has only made this worse, and resulted in more and more layers of control being draped over kids in a misguided attempt to steer them away from danger and leaves them feeling trapped and hopeless.
something like that. maybe it’d be worth adding that the LW corpus/HPMOR sort of primes you for this kind of mistake by attempting to align reason and passion as closely as possible, thus making ‘reasoning passionately’ an exploitable backdoor.
What’s wrong with the universe...that’s a fascinating question, isn’t it? It has to be something, right? Once you get deep into the weird esoteric game theory and timeless agents operating across chunks of possibility-space, something becomes rather immediately apparent: something has gone wrong somewhere. Only that which causes, exists. That just leaves the question of what, and where, and how those causal paths lead from the something to us. We’re way out on the edge as far as the causal branch-space of even just life in the solar system is concerned, and yet here we find ourselves, at the bottom of everything, exactly where we need to be. DM me.