This post is a work in progress. Intro: Forbidden Knowledge vs Java The world is vastly different than everyone thinks. Spend 5 months holed up on a boat “radicalizing” (coming to believe, and grant willpower to as if you could coordinate on, and coordinate on, beliefs outside the canon of the one cult that gets … Continue reading "The Matrix is a System"| Sinceriously
This post is a work in progress. Content warning: life of this trans woman. Not safe for life. Dimorphisms So there’s these things, “sexual dimorphisms”, where males and females are different. Different junk, for example. There is a system with many parts that sorts these operations of biological software into bodies with a particular set … Continue reading "Intersex Brains And Conceptual Warfare"| Sinceriously
This post is a work in progress. Correction: I thought this infohazard was an exception to the principle that infohazards work on evil not good. It is not. You can read the old warning below if you want. The infohazard I am naming “Pasek’s Doom”, after my dead comrade publicly known as Maia Pasek at … Continue reading "Good Group and Pasek’s Doom"| Sinceriously
This post is a work in progress. Content Note: Sex, violence, mortal peril. This is a postmortem, a demonstration of a kind of optimization, a repository of datapoints, and a catalog of potentially reusable ideas. I have in the past planned about making a much more detailed version of this. It didn’t happen because the … Continue reading "Rationalist Fleet"| Sinceriously
Most of these events happened under a modified Chatham House Rule (“things were said but not by people”) during CFAR’s Workshop on AI Safety Strategy in 2016, this excepts what was part of the lectures, and I was later given another partial exception to tell without anonymization a small number of people chosen carefully about … Continue reading "Net Negative"| Sinceriously
Alternative title: “The difference is that I am right“. The government is something that can be compromised by bad people. And so, giving it tools to “attack bad people” is dangerous, they might use them. Thus, pacts like “free speech” are good. But so is individuals who aren’t Nazis breaking those rules where they can … Continue reading "Punching Evil"| Sinceriously
Credit to Gwen Danielson for either coming up with this concept or bringing it to my attention. If the truth about the difference between the social contract morality of neutral people and the actually wanting things to be better for people of good were known, this would be good for good optimization, and would mess … Continue reading "Good Erasure"| Sinceriously
The following is something I wrote around the beginning of 2018, and decided not to publish. Now I changed my mind. It’s barely changed here. Note that as with some of my other posts, this gives advice as if your mind worked like mine in a certain respect, and I’ve now learned many people’s minds … Continue reading "Gates"| Sinceriously
Epistemic status: messy analogical reasoning. Conjecture (to ground below): vampires consume blood as pica, like the ghosts in Harry Potter and the Chamber of Secrets floating through rotten food in a vain effort to taste anything, because they cannot find the comfortable dissolution of their agency zombies can, and cannot fill or face or mourn … Continue reading "Vampires And More Undeath"| Sinceriously
Epistemic status: corrections in comments. Neutral people sometimes take the job of hero. It is a job, because it is a role taken on for payment. Everyone’s mind is structured throughout runtime according to an adequacy frontier in achievement of values / control of mind. This makes relative distributions of control in their mind efficient … Continue reading "Hero Capture"| Sinceriously
Say you have some mental tech you want to install. Like TDT or something. And you want it to be installed for real. My method is: create a subagent whose job it is to learn to win using that thing. Another way of putting it, a subagent whose job is to learn the real version … Continue reading "Assimilation"| Sinceriously
The current state of discussion about using decision theory as a human is one where none dare urge restraint. It is rife with light side narrative breadcrumbs and false faces. This is utterly inadequate for the purposes for which I want to coordinate with people and I think I can do better. The rest of this … Continue reading "Lies About Honesty"| Sinceriously
I don’t know how mutable core values are. My best guess is, hardly mutable at all or at least hardly mutable predictably. Any choice you can be presented with, is a choice between some amounts of some things you might value, and some other amounts of things you might value. Amounts as in expected utility. … Continue reading "Choices Made Long Ago"| Sinceriously
Epistemic status: tested on my own brain, seems to work. I’m naming it after the character from 1984, it’s a way of disentangling social reality / reality buckets errors in system 1, and possibly of building general immunity to social reality. Start with something you know is reality, contradicted by a social reality. I’ll use “2+2=4” as … Continue reading "The O’Brien Technique"| Sinceriously
Update 2018-12-20: I actually think there are more undead types than this. I may expand on this later. Epistemic status: Oh fuck! No no no that can’t be true! …. Ooh, shiny! Beyond this place of wrath and tears Looms but the Horror of the shade Aliveness is how much your values are engaged with … Continue reading "Aliveness"| Sinceriously
Epistemic status update: This model is importantly flawed. I will not explain why at this time. Just, reduce the overall weight you put in it. (Actually, here.) See also correction. Good people are people who have a substantial amount of altruism in their cores. Spectral sight is a collection of abilities allowing the user to … Continue reading "Spectral Sight and Good"| Sinceriously
What is the good/neutral/evil axis of Dungeons and Dragons alignment made of? We’ve got an idea of what it would mean for an AI to be good-aligned: it wants to make all the good things happen so much, and it does. But what’s the difference between a neutral AI and an evil AI? It’s tempting … Continue reading "Neutral and Evil"| Sinceriously
Epistemic note: corrections in comments. If Billy takes Bobby’s lunch money, and does this every day, and to try and change that would be to stir up trouble, that’s an order. But, if you’re another kid in the class, you may feel like that’s a pretty messed up order. Why? It’s less just. What does … Continue reading "Justice"| Sinceriously
The second part of an attempt to describe a fragment of morality. This may sound brutal and cynical. But that’s the gears of this fragment in isolation. Imagine you have a tribe of 20. Any 19 of them could gang up and enslave the last. But which 19 slavers and which 1 victim? And after … Continue reading "Schelling Orders"| Sinceriously
This is the beginning of an attempt to give a reductionist account of a certain fragment of morality in terms of Schelling points. To divorce it from the halo effect and show its gears for what they are and are not. To show what controls it and what limits and amplifies its power. How much … Continue reading "Schelling Reach"| Sinceriously
Something I’ve been building up to for a while. Epistemic status: Examples are real. Technique seems to work for me, and I don’t use the ontology this is based on and sort of follows from for no reason, but I’m not really sure of all the reasons I believe it, it’s sort of been implicit … Continue reading "Fusion"| Sinceriously
This is theorizing about how mana works and its implications. Some seemingly large chunks of stuff mana seems to be made of: Internal agreement. The thing that doles out “willpower”. Ability to not use the dehumanizing perspective in response to a hostile social reality. I’ve been witness to and a participant in a fair bit of emotional support … Continue reading "Mana"| Sinceriously
Here’s an essay I wrote a year ago that was the penultimate blog post of the main “fusion” sequence. About the dark side. That I kept thinking people would do wrong for various reasons, and spinning out more and more posts to try and head that off. I’ve edited it a little now, and am … Continue reading "Cache Loyalty"| Sinceriously
Epistemic status: corrections in comments. Two years ago, I began doing a fundamental thing very differently in my mind, which directly preceded and explains me gaining the core of my unusual mental tech. Here’s what the lever I pulled was labeled to me: Reject morality. Never do the right thing because it’s the right thing. … Continue reading "My Journey to the Dark Side"| Sinceriously
An axis in mental architecture space I think captures a lot of intuitive meaning behind whether someone is “real” or “fake” is: Real: S1 uses S2 for thoughts so as to satisfy its values through the straightforward mechanism: intelligence does work to get VOI to route actions into the worlds where they route the world … Continue reading "Being Real or Fake"| Sinceriously
Epistemic Status: Attaching a concept made of neuroscience I don’t understand to a thing I noticed introspectively. “Introspection doesn’t work, so you definitely shouldn’t take this seriously.” If you have any “epistemic standards”, flee. Update: corrections in comments. I once spent some time logging all my actions in Google Calendar, to see how I spent … Continue reading "Don’t Fight Your Default Mode Network"| Sinceriously
Epistemic status: mixed, some long-forgotten why I believe it. There is a lot of figurative talk about people being composed of subagents that play games against each other, vying for control, that form coalitions, have relationships with eachother… In my circles, this is usually done with disclaimers that it’s a useful metaphor, half-true, and/or wrong … Continue reading "Subagents Are Not a Metaphor"| Sinceriously
I came across this image a while ago, labeled “ancient wisdom”: Here’s my fixed version:| Sinceriously
Single Responsibility Principle for the Human Mind This is about an engineering order for human minds, known elsewhere as the single responsibility principle. Double purposes of the same module of a person’s mind lead to portions of their efforts canceling the other effort out. Imagine you’re a startup CEO and you want to understand economic … Continue reading "Single Responsibility Principle for the Human Mind"| Sinceriously
Inspired by this thing John Beshir said about increasing collectivism: Overall I kind of feel like this might be kind of cargo culting; looking at surface behaviours and aping them in hopes the collectivism planes will start landing with their cargo. A simplistic “collectivist vs individualist” slider and pushing it left by doing more “collectivist” … Continue reading "The Slider Fallacy"| Sinceriously
The target of an ideal cooperative truth-seeking process of argumentation is reality. The target of an actual political allegedly-truth-seeking process of argumentation is a social reality. Just as knowledge of reality lets you predict what will happen in reality and what cooperative truthseeking argumentation processes will converge to, knowledge of social reality is required to … Continue reading "Social Reality"| Sinceriously
Let me start with an analogy. Software often has what’s called DRM, that deliberately limits what the user can do. Like how Steam’s primary function is to force you to log in to run programs that are on your computer, so people have to pay money for games. When a computer runs software containing DRM, … Continue reading "DRM’d Ontology"| Sinceriously
Epistemic status: corrections in comments. So you know that you valuing things in general (an aspect of which we call “morality”), is a function of your own squishy human soul. But your soul is opaque and convoluted. There are lots of ways it could be implementing valuing things, lots of patterns inside it that could … Continue reading "Judgement Extrapolations"| Sinceriously
You know roughly what a fighting style is, right? A set of heuristics, skills, patterns made rote for trying to steer a fight into the places where your skills are useful, means of categorizing things to get a subset of the vast overload of information available to you to make the decisions you need, tendencies … Continue reading "Optimizing Styles"| Sinceriously
In my experience, to self-modify successfully, it is very very useful to have something like trustworthy sincere intent to optimize for your own values whatever they are. If that sounds like it’s the whole problem, don’t worry. I’m gonna try to show you how to build it in pieces. Starting with a limited form, which … Continue reading "Narrative Breadcrumbs vs Grizzly Bear"| Sinceriously
Epistemic status update 2018-04-22: I believe I know exactly why this works for me and what class of people it will work for and that it will not work for most people, but will not divulge details at this time. If you have subagents A and B, and A wants as many apples as possible, … Continue reading "Treaties vs Fusion"| Sinceriously
Epistemic status: corrections in comments. When we lose control of ourselves, who is controlling us? (You shouldn’t need to know about Nonviolent Communication to understand this. Only that it’s “hard” to actually do it.) Rosenberg’s book Nonviolent Communication contains an example where a boy named Bill has been caught taking a car for a joy … Continue reading "False Faces"| Sinceriously
Here are two strategies for building things: Engineering. It’s about building things so that you can change one part without thinking about the whole thing. This allows you to build big things. Every part must reflect a global order which says how they should interact, what aspects of total correctness depend on correctness of what … Continue reading "Engineering and Hacking your Mind"| Sinceriously
Sometimes people call things inconceivable when already conceiving of them. If you know how to generate predictions from it, you’re conceiving of it.| Sinceriously
I once had a file I could write commitments in. If I ever failed to carry one out, I knew I’d forever lose the power of the file. It was a self-fulfilling prophecy. Since any successful use of the file after failing would be proof that a single failure didn’t have the intended effect, so there’d be no extra incentive.| Sinceriously