Skip Navigation
SneerClub @awful.systems
CinnasVerses @awful.systems

Selfishness and Altruism

An opposition between altruism and selfishness seems important to Yud. 23-year-old Yud said "I was pretty much entirely altruistic in terms of raw motivations" and his Pathfinder fic has a whole theology of selfishness. His protagonists have a deep longing to be world-historical figures and be admired by the world. Dreams of controlling and manipulating people to get what you want are woven into his community like mould spores in a condemned building.

Has anyone unpicked this? Is talking about selfishness and altrusm common in LessWrong like pretending to use Bayesian statistics?

9 comments

  • Jon Evans is the only person I know who has read Yud's early mailing-list posts, and he was already an AI cultist and went on to work for Metaculus and Meta Superintelligence. There is probably interesting material in there but clearly Yud already thought highly of himself, already believed he was the Chosen One, already got defensive and wordy when someone criticized his ideas, and already posted voluminous pseudo-intellectual screeds which are not as consistent and logical as he believed.

    Evans loves chatbot-summaries, but some science writers spent year at it and could not make the bot spit out useful abstracts. And he says he can skim a scientific paper in 5 minutes.

  • Why spend so much time worrying about this I wonder, does he think that if he stops the acausalrobotgod it doesnt count if he did it for ego reasons?

    Also this sentence is ver funny:

    No offense, Ben, but this is very simple stuff - in fact, it's right there in the Zen definition of altruism I quoted. This is a very straightforward trap by comparison with any of the political-emotion mindtwisters, much less the subtle emergent phenomena that show up in a pleasure-pain architecture.

    Emp mine, very simple stuff, creates a very weird sentence after that.

  • This paragraph caught my interest. It used some terms I wasn’t familiar with, so I dove in.

    Ego gratification as a de facto supergoal (if I may be permitted to describe the flaw in CFAImorphic terms)

    TL note: “CFAI” is this “book-length document” titled “Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures”, in case you forgot. It’s a little difficult to quickly distill what a supergoal is, despite it being defined in the appendix. It’s one of two things:

    1. A big picture type of goal that might require making “smaller” goals to achieve. In the literature this is also known as a “parent goal” (vs. a “child goal”)
    2. An “intrinsically desirable” world (end) state, which probably requires reaching other “world states” to bring about. (The other “world states” are known as “subgoals”, which are in turn “child goals”)

    Yes, these two things look pretty much the same. I’d say the second definition is different because it implies some kind of high-minded “desirability”. It’s hard to quickly figure out if Yud actually ever uses the second definition instead of the first because that would require me reading more of the paper.

    is a normal emotion, leaves a normal subjective trace, and is fairly easy to learn to identify throughout the mind if you can manage to deliberately "catch" yourself doing it even once.

    So Yud isn’t using “supergoal” on the scale of a world state here. Why bother with the cruft of this redundant terminology? Perhaps the rest of the paragraph will tell us.

    Anyway this first sentence is basically the whole email. “My brain was able to delete ego gratification as a supergoal”.

    Once you have the basic ability to notice the emotion,

    Ah, are we weaponising CBT? (cognitive behavioral therapy, not cock-and-ball torture)

    you confront the emotion directly whenever you notice it in action, and you go through your behavior routines to check if there are any cases where altruism is behaving as a de facto child goal of ego gratification; i.e., avoidance of altruistic behavior where it would conflict with ego gratification, or a bias towards a particular form of altruistic behavior that results in ego gratification.

    Yup we are weaponising CBT.

    All that being said, here’s what I think. We know that Yud believes that “aligning AI” is the most altruistic thing in the world. Earlier I said that “ego gratification” isn’t something on the “world state” scale, but for Yud, it is. See, his brain is big enough to change the world, so an impure motive like ego gratification is a “supergoal” in his brain. But at the same time, his certainty in AI-doomsaying is rooted in belief of his own super-intelligence. I’d say that the ethos of ego-gratification has far transcended what can be considered normal.

  • My hunch would be that he has matured at least somewhat since then, but who who knows.

    More broadly speaking, even if not analysing their own actions this way they tend to characterize—in a very manosphere way—the actions of others as being "status-seeking", as the primary motivator for most actions. I would definitely call that a self-report.

  • Eric Cartman earnestly believing he invented the fish stick joke

  • Eliezer, given the immense capacity of the human mind for self-delusion, it is entirely possible for someone to genuinely believe they're being 100% altruistic even when it's not the case. Since you know this, how then can you be so sure that you're being entirely altruistic?

    Because I didn't wake up one morning and decide "Gee, I'm entirely altruistic", or follow any of the other patterns that are the straightforward and knowable paths into delusive self-overestimation, nor do I currently exhibit any of the straightforward external signs which are the distinguishing marks of such a pattern. I know a lot about the way that the human mind tends to overestimate its own altruism.

    Fun to unpack this here. First is the argument that we should be dismissive of any professed act of altruism unless someone is perfectly knowable. There is an interesting point here completely missed: even if the person knows themselves well enough to make the claim, others cannot possibly know another well enough to make the claim of another. Instead what we get is "trust me bro" because being contrarian is evidence of being on the correct path 🙄. We went from "we can't possibly know another well enough to say they are altruist" to "I know when people are not altruist because they are predictable, but I am unpredictable therefore I am altruist". I think this touches on the manipulation present in the community: you are either being manipulated and therefore cannot be an altruist because your motives are not your own (are you even selfish at this point?), OR you are contrarian enough to show you are in control of your own motives (nevermind we still can't say whether your motives are altruistic). This is a very surface level read, I can't bring myself to read all that slop. Parts are so redundant it feels like it was written by AI.

    • So basically, trying to figure out whether someone is actually being altruistic is just the poisoned chalice bit from The Princess Bride, forever

    • Good thing there are very prominent in-group approved channels to rid you of your money ethically and effectively.

9 comments