By Type (Named)

wiki

Axiom of Choice: Definition (Formal) Mathematically speaking, what does the Axiom of Choice say? - Mark Chimes
CFAR should explicitly focus on AI safety The Center for Applied Rationality has historically had a "cause-neutral" mission but has recently r… - Stephanie Zolayvar
There will be a week during which it is more common to buy food with gold than any other form of money (e.g., USD) in some US settlement with at least 1000 people in 2017. The wording might not be perfect, but I’m trying to get at the idea that gold should be purchased an… - Adam Seyfarth
'Beneficial' Really actually good. A metasyntactic variable to mean "favoring whatever the speaker wants ideally to accomplish", although different speakers have different morals and metaethics. - Eliezer Yudkowsky
'Concept' In the context of Artificial Intelligence, a 'concept' is a category, something that identifies thingies as being inside or outside the concept. - Eliezer Yudkowsky
'Detrimental' The opposite of beneficial. - Eliezer Yudkowsky
'Rationality' of voting in elections "A single vote is very unlikely to swing the election, so your vote is unlikely to have an effect" versus "Many people similar to you are making a similar decision about whether to vote." - Eliezer Yudkowsky
----------Start Ghost Migration---------- this is a test - Alto Clef
0.999...=1 No, it's not "infinitesimally far" from 1 or anything like that. 0.999... and 1 are literally the same number. - Dylan Hendrickson
2017 US GDP growth will be lower than in 2016 - Alexei Andreev
2017 will have no interesting progress with Gaza or peace negotiations in general - Alexei Andreev
2017 will not have any major revolt (greater than or equal to Tiananmen Square) against Chinese Communist Party - Alexei Andreev
99LDT x 1CDT oneshot PD tournament as arguable counterexample to LDT doing better than CDT Arguendo, if 99 LDT agents and 1 CDT agent are facing off in a one-shot Prisoner's Dilemma tournament, the CDT agent does better on a problem that CDT considers 'fair'. - Eliezer Yudkowsky
A $1 donation to a top animal charity alleviates more suffering than is caused by a day of eating meat. For the purposes of this claim, top animal welfare charities include: - [Animal Charity Evaluators… - Eric Rogstad
A Return to Discussion - Eric Bruylant
A beginner's guide to explaining things Good explanations can be very different, but most of them have a few things in common. - Duncan Sabien
A clarification period for claims is net positive for Arbital Example pros: Claims are more carefully defined and less ambiguous, less wrong questions visible Ex… - Eric Bruylant
A googol A pretty small large number. - Nate Soares
A googolplex A moderately large number, as large numbers go. - Nate Soares
A permanent, self-sustaining off-Earth colony would be a much more effective mitigation of x-risk than even an equally well funded system of disaster shelters on Earth. See also the less precise claim: Establishing a permanent off-Earth colony would be a useful way to … - Eric Rogstad
A possible stance for AI control research I think that AI control research should focus on finding [scalable](https://arbital.com/pages/492374… - Paul Christiano
A quick econ FAQ for AI/ML folks concerned about technological unemployment Yudkowsky's attempted description of standard economic concepts that he thinks are vital for talking about technological unemployment and related issues. - Eliezer Yudkowsky
A reply to Francois Chollet on intelligence explosion A quick run-through of what I'd consider the standard replies to the arguments in Keras inventor Francois Chollet's essay "The impossibility of intelligence explosion". - Eliezer Yudkowsky
A typical donor with a $5,000 charity budget, on the margin, has increasing returns to scale - Benjamin Hoffman
A whirlwind tour A rapid tour of Eric's thoughts on the accelerator project. - Eric Bruylant
A-Class This page is well-written, high-quality, and essentially complete. - Eric Bruylant
AI alignment The great civilizational problem of creating artificially intelligent computer systems such that running them is a good idea. - Eliezer Yudkowsky
AI alignment open problem Tag for open problems under AI alignment. - Eliezer Yudkowsky
AI and Machine Learning resources Content that helped me with my AI/ML journey - adel shehadeh
AI arms race This part of the plan describes how to prevent and handle AI arms race. - Alexei Andreev
AI arms races AI arms races are bad - Eliezer Yudkowsky
AI control on the cheap Ideally, we will build aligned AI systems without sacrificing any efficiency. I think this is a rea… - Paul Christiano
AI safety mindset Asking how AI designs could go wrong, instead of imagining them going right. - Eliezer Yudkowsky
AIXI How to build an (evil) superintelligent AI using unlimited computing power and one page of Python code. - Eliezer Yudkowsky
AIXI-tl A time-bounded version of the ideal agent AIXI that uses an impossibly large finite computer instead of a hypercomputer. - Eliezer Yudkowsky
Abelian group A group where the operation commutes. Named after Niels Henrik Abel. - Nate Soares
Ability to read algebra Do you have sufficient mathematical ability that you can read a sentence that uses some algebra or invokes a mathematical idea, without slowing down too much? - Eliezer Yudkowsky
Ability to read calculus Can you take integral signs and differentiations in stride? - Eliezer Yudkowsky
Ability to read logic Can you read sentences symbolically stating "For all x: exists y: phi(x, y) or not theta(y)" without slowing down too much? - Eliezer Yudkowsky
Abortable plans Plans that can be undone, or switched to having low further impact. If the AI builds abortable nanomachines, they'll have a quiet self-destruct option that includes any replicated nanomachines. - Eliezer Yudkowsky
Absent-Minded Driver dilemma A road contains two identical intersections. An absent-minded driver wants to turn right at the second intersection. "With what probability should the driver turn right?" argue decision theorists. - Eliezer Yudkowsky
Absolute Complement The complement $A^\complement$ of a set $A$ is the set of all things that are not in $A$. Put simply… - M Yass
Abstract algebra The study of groups, fields, vector spaces, arithmetics, algebras, and more. - Nate Soares
Abstract approval-direction Consider the following design for an agent, which I first described [here](https://arbital.com/p/1t7… - Paul Christiano
Accelerator FAQ ## Project FAQ ### What is this all about? A large number of people are driven to move the needle… - Eric Bruylant
Accelerator Project The Accelerator Project aims to create a low-cost environment which facilitates rapid personal growt… - Eric Bruylant
Accelerator project Redirect: Accelerator Project - Eric Bruylant
Ackermann function The slowest-growing fast-growing function. - Alex Appel
Act based agents I’ve recently discussed three kinds of learning systems: - [Approval-directed agents](https://arbit… - Paul Christiano
Active learning for opaque, powerful predictors #### (An open theoretical question relevant to AI control.) Suppose that I have a very powerful p… - Olivia Schaefer
Active learning for opaque, powerful predictors (An open theoretical question relevant to AI control.) Suppose that I have a very powerful predicti… - Paul Christiano
Actual effectiveness If you want the AI's so-called 'utility function' to actually be steering the AI, you need to think about how it meshes up with beliefs, or what gets output to actions. - Eliezer Yudkowsky
Ad-hoc hack (alignment theory) A "hack" is when you alter the behavior of your AI in a way that defies, or doesn't correspond to, a principled approach for that problem. - Eliezer Yudkowsky
Addition of rational numbers (Math 0) The simplest operation on rational numbers is addition. - Patrick Stevens
Addition of rational numbers exercises Test and cement your understanding of how we add rational numbers! - Patrick Stevens
Advanced agent properties How smart does a machine intelligence need to be, for its niceness to become an issue? "Advanced" is a broad term to cover cognitive abilities such that we'd need to start considering AI alignment. - Eliezer Yudkowsky
Advanced nonagent Hypothetically, cognitively powerful programs that don't follow the loop of "observe, learn, model the consequences, act, observe results" that a standard "agent" would. - Eliezer Yudkowsky
Advanced safety An agent is *really* safe when it has the capacity to do anything, but chooses to do what the programmer wants. - Eliezer Yudkowsky
Adversarial collaboration Suppose that I have hired a group of employees who are much smarter than I am. For some tasks it’s… - Paul Christiano
Advisor games Machine learning algorithms often learn models or policies that are inscrutable to humans. We belie… - Paul Christiano
Against Compromise, or, Deciding as a Team without Succombing to Entropy - Andrea Gallagher
Against mimicry One simple and apparently safe AI system is a “copycat:” an agent that predicts what its user woul… - Paul Christiano
Alexei Andreev: Personal Fun things Alexei Andreev likes to do. - Alexei Andreev
Alexei Test Group - Alexei Andreev
Alexei's Blog Will come up with a better name later. - Alexei Andreev
Algebraic field A field is a structure with addition, multiplication and division. - Patrick Stevens
Algebraic structure Roughly speaking, an algebraic structure is a set $X$, known as the underlying set, paired with a co… - Nate Soares
Algebraic structure tree When is a monoid a semilattice? What's the difference between a semigroup and a groupoid? Find out here! - Ryan Hendrickson
Algorithmic complexity When you compress the information, what you are left with determines the complexity. - Eliezer Yudkowsky
Aligning an AGI adds significant development time Aligning an advanced AI foreseeably involves extra code and extra testing and not being able to do everything the fastest way, so it takes longer. - Eliezer Yudkowsky
All you need for SAT Math Here! Thanks for reading, this is a port of a study guide that I am using to study for the SAT. This should be done soon, but I don't have that much time. - 974
Almost all real-world domains are rich Anything you're trying to accomplish in the real world can potentially be accomplished in a *lot* of different ways. - Eliezer Yudkowsky
Alternate Clickbait? - Anton Geraschenko
Alternating group The alternating group is the only normal subgroup of the symmetric group (on five or more generators). - Patrick Stevens
Alternating group is generated by its three-cycles A useful result which lets us prove things about the alternating group more easily. - Patrick Stevens
Ambitious vs. narrow value learning Suppose I’m trying to build an AI system that “learns what I want” and helps me get it. I think tha… - Paul Christiano
An Effective Altruist's Guide to the Future The future is unknown, but not unknowable. What evidence do we have about what will happen, and what considerations are most important for doing good in a rapidly changing world? - Eric Bruylant
An Introduction to Logical Decision Theory for Everyone Else So like what the heck is 'logical decision theory' in terms a normal person can understand? - Eliezer Yudkowsky
An algorithm for creating good explanations Excellent explanations can break the rules, but it helps to know those rules in the first place. Following these steps will help you create explanations that are solid and that avoid common mistakes. - Duncan Sabien
An early stage prioritisation model How do you choose which projects to work on, early on in life? - Ben Pace
An early stage project generation model How do you figure out which projects to even consider, when you're getting started? - Ben Pace
An introductory guide to modern logic Logic, provability, Löb, Gödel and more! - Jaime Sevilla Molina
Angela Merkel will be re-elected Chancellor of Germany in 2017 - Alexei Andreev
Another Followup To “Economists On Education” (Arbital should model this debate) - Andrea Gallagher
Another another playpen child May it be a light for you in dark places, when all other lights go out. - Stephanie Zolayvar
Another playpen child asdf - Eric Rogstad
Answer to sparking widgets problem Odds of 1 : 3, probability of 1/4. - Eliezer Yudkowsky
Antisymmetric relation A binary relation where no two distinct elements are related in both directions - M Yass
Apprenticeship learning and mimicry This post compares my [recent proposal](https://arbital.com/p/1vp/mimicry_meeting_halfway) with [Ab… - Paul Christiano
Approaches to strategic disagreement Organizations self-select staff to agree with their strategies. By default, this causes them to sacrifice the fulfillment of others' plans. How can we resolve these strategic disagreements? - Ryan Carey
Approval directed agents Research in AI is steadily progressing towards more flexible, powerful, and autonomous goal-directe… - Paul Christiano
Approval-based agents An alternative to goal-directed behavior - Paul Christiano
Approval-directed bootstrapping Approval-directed behavior works best when the overseer is very smart. Where can we find a smart o… - Paul Christiano
Arbital Arbital is the place for crowdsourced, intuitive math explanations. - Alexei Andreev
Arbital "parent" relationship Parent-child relationship between pages implies a strong, inseparable connection. - Alexei Andreev
Arbital "requires" relationship A page can require a requisite if the reader needs to have it before they are able to understand the page. - Alexei Andreev
Arbital "tag" relationship Tags are a way to connect pages that share a common topic. - Alexei Andreev
Arbital "teaches" relationship A page can teach a requisite when the user can acquire it by reading the page. - Alexei Andreev
Arbital Blog Stay up to date on all things Arbital - Alexei Andreev
Arbital Labs Landing page for the Arbital Labs domain. - Alexei Andreev
Arbital Markdown All about Arbital's extended Markdown syntax. - Alexei Andreev
Arbital Markdown questionnaire How to ask questions in Markdown. - Alexei Andreev
Arbital Redesign What awesome things are in Arbital's future? - Alexei Andreev
Arbital Slack Where the cool kids hang out. - Eric Bruylant
Arbital arbiter Arbiters provide oversight and dispute resolution to an Arbital domain. - Eric Bruylant
Arbital archive An archive of all public content on Arbital! - Eric Bruylant
Arbital as single conversational locus Proposal and outline of Arbital's steps to create a single conversational locus. - Alexei Andreev
Arbital biographies As a very strong default (presently an absolute rule), Joe Smith's page only says nice things about Joe. Even if a negative fact is true, it doesn't go on Joe's page. - Eliezer Yudkowsky
Arbital claims are significantly more useful* when they are fairly well-specified and unambiguous** \* At least 30% more valuable to people sharing models. ** Not lojban level, but with some thoug… - Eric Bruylant
Arbital comment A comment is a way for you to express your thoughts and opinions within the context of a page. - Alexei Andreev
Arbital community input Do you have ideas about how to improve Arbital which you think the community should discuss? - Alexei Andreev
Arbital completed project Completed projects are essentially finished, having achieved the goals they set out to. - Eric Bruylant
Arbital content license What license does Arbital use for its content? - Alexei Andreev
Arbital content request Arbital doesn't explain something you'd like to learn? We'd like to know, so we can prioritize. - Eric Bruylant
Arbital domain What is a domain? Why is it important? - Alexei Andreev
Arbital draft Drafts are private work-in-progress pages. - Eric Bruylant
Arbital editor How to use Arbital's page editor. - Alexei Andreev
Arbital editor buttons What do all the buttons in the editor do? - Alexei Andreev
Arbital editor's manual A quick overview of Arbital features relevant to editors. - Alexei Andreev
Arbital editor: Advanced Advanced features of Arbital editor. - Alexei Andreev
Arbital editor: Basics The basics of how to use the Arbital editor. - Alexei Andreev
Arbital examplar pages Exemplar pages on Arbital. - Eric Bruylant
Arbital external resources Arbital wants to link users to great content, wherever it is! - Eric Bruylant
Arbital featured project Featured projects are active, currently promoted projects. - Eric Bruylant
Arbital features Overview of all Arbital features. - Alexei Andreev
Arbital greenlink What happens when you hover over an Arbital link? - Alexei Andreev
Arbital groups What are groups? How can I create a new group? - Alexei Andreev
Arbital hidden text How to hide text in Markdown behind a button. - Alexei Andreev
Arbital lens A lens is a page that presents another page's content from a different angle. - Alexei Andreev
Arbital lens: TL;DR Much shorter version of Arbital Lens page - Alexei Andreev
Arbital likes What are likes? When should I use them? What happens when I like something? - Alexei Andreev
Arbital listed page Listed pages have been accepted into at least one domain and checked by a reviewer. - Eric Bruylant
Arbital mark What is a mark on Arbital? When is it created? Why is it important? - Alexei Andreev
Arbital markdown demo Demo of Arbital's markdown - Eric Bruylant
Arbital math levels How mathy do you like your pages? - Eric Bruylant
Arbital members should state their beliefs clearly, even if they only hold them weakly. Sometimes there is a tendency for people to state a weak version of their belief, if they don't beli… - Alexei Andreev
Arbital needs a mechanism for defining terms Much of the discussion in claims seems to be about defining terms, which is a foundational part of r… - Andrea Gallagher
Arbital norms should encourage disagreement. - Alexei Andreev
Arbital norms should encourage nitpicking. - Alexei Andreev
Arbital ongoing project Ongoing projects are not complete, but also not high activity enough to promote. - Eric Bruylant
Arbital page The Arbital is a series of pages. - Alexei Andreev
Arbital page alias The alias is a short, unique name assigned to each page. For example: "arbital_alias". The alias u… - Eric Rogstad
Arbital page clickbait The text you are reading right now is clickbait. - Eric Rogstad
Arbital page summaries Because only one summary is not enough! - Alexei Andreev
Arbital page summaries Markdown syntax How to create page summaries using Arbital's Markdown syntax. - Alexei Andreev
Arbital page title The title of a page is shown at the top of the page (e.g. "Arbital page title") and in most places … - Eric Rogstad
Arbital page: Basics Explaining the basic features of an Arbital page. - Alexei Andreev
Arbital path Arbital path is a linear sequence of pages tailored specifically to teach a given concept to a user. - Alexei Andreev
Arbital playpen Want to test a feature? Feel free to edit this page! asdfasfdasfda - Eliezer Yudkowsky
Arbital practices Guidelines and rules for interacting on Arbital. - Eliezer Yudkowsky
Arbital project outline Project outlines are in-progress proposals for projects. - Eric Bruylant
Arbital projects Arbital projects are small-scale drives to fill in areas of content. - Eric Bruylant
Arbital proposed project Collecting all project proposals under this page. - Alexei Andreev
Arbital quality Arbital's system for tracking page quality. - Eric Bruylant
Arbital query What is a query? How to create it? How to resolve it? - Alexei Andreev
Arbital requisites To understand a thing you often need to understand some other things. - Alexei Andreev
Arbital reviewer Reviewers help writers improve their pages, check over all changes to Arbital's content, and assess page quality. - Eric Bruylant
Arbital scope What kind of content is Arbital looking for? - Eric Bruylant
Arbital should hide probability/approval votes until the user votes This is to avoid a potential [-anchoring\_effect]. Also, presumably the user would be still be able … - Alexei Andreev
Arbital should not require any member to have particular beliefs, but should instead focus on enforcing specific rules of conduct. - Alexei Andreev
Arbital subscriptions What's a subscription? How do you change it? What to expect? - Alexei Andreev
Arbital subscriptions: Maintenance Subscribing to a page with intention of maintaining it. - Alexei Andreev
Arbital todo So many things todo! - Eric Bruylant
Arbital trusted user Trusted users can edit most pages directly, and don't need approval to add pages to a domain. - Eric Bruylant
Arbital unlisted page What do you call a page that's not part of any domain? - Alexei Andreev
Arbital user groups Users can attain different powers and responsibilities on Arbital. - Eric Bruylant
Arbital's next pillar: Discussion Arbital has a prototype discussion platform. If you're excited about this and want to participate, y… - Eric Bruylant
Arbital: Do what works When deciding things on Arbital, think about the real goals, and move towards them. - Eric Bruylant
Arbital: Do what works: Justification **Do what works** is meant to create a firm but flexible foundation for Arbital policy. The aims inc… - Eric Bruylant
Arbital: Google Maps for knowledge Take your understanding from where it is to where it wants to be. - Alexei Andreev
Arbital: Solving online explanations An explanation of Arbital's mid-term goals - Eliezer Yudkowsky
Arbital: better blogging What makes Arbital the choice blogging platform? - Alexei Andreev
Arbital: fixing online discussion How can Arbital do better than existing discussion platforms? - Alexei Andreev
Arbital: information hub How will Arbital help you keep up to date on any given subject? - Alexei Andreev
Arbital: learning from Wikipedia How is Arbital different from Wikipedia? - Alexei Andreev
Arguments An argument is a formal reasoning, valid or not. - Jeremy Perret
Arithmetic of rational numbers (Math 0) How do we combine rational numbers together? - Patrick Stevens
Arithmetical hierarchy The arithmetical hierarchy is a way of classifying logical statements by the number of clauses saying "for every object" and "there exists an object". - Eliezer Yudkowsky
Arithmetical hierarchy: If you don't read logic The arithmetical hierarchy is a way of stratifying statements by how many "for every number" and "th… - Eliezer Yudkowsky
Arity (of a function) The arity of a function is the number of parameters that it takes. For example, the function $f(a, b… - Nate Soares
Artificial General Intelligence An AI which has the same kind of "significantly more general" intelligence that humans have compared to chimpanzees; it can learn new domains, like we can. - Eliezer Yudkowsky
Associative operation An **associative operation** $\bullet : X \times X \to X$ is a binary operation such that for all $x… - Nate Soares
Associativity vs commutativity Associativity and commutativity are often confused, because they are both constraints on how a funct… - Nate Soares
Associativity: Examples Yes: [Addition], [multiplication], string concatenation. No: [subtraction], [division], a Function … - Nate Soares
Associativity: Intuition Associative functions can be interpreted as families of functions that reduce lists down to a singl… - Nate Soares
Assuming significant overhead in monitoring recipients of a microloan, it's more efficient to let them keep the money. A claim about microfinance. - Alexei Andreev
Astronomical Altruism Playing for the huge outcomes - Noah Walton
Asymptotic Notation Asymptotic notation seeks to capture the behavior of functions as its input(s) become extreme. It is most widely used in Computer Science and Numerical Approximation. - Morgan Redding
Attainable optimum The 'attainable optimum' of an agent's preferences is the best that agent can actually do given its finite intelligence and resources (as opposed to the global maximum of those preferences). - Eliezer Yudkowsky
Audience-centric Explanations A good explanation isn't one that says all the things, but one that allows all the things to be HEARD. - Duncan Sabien
Author's guide to Arbital How to write intuitive, flexible content on Arbital. - Alexei Andreev
Author's guide to Arbital explanations Requisite used for teaching authors about Arbital explanation features. - Alexei Andreev
Author's guide to Arbital: Advanced Requisite used for teaching authors about advanced Arbital features. - Alexei Andreev
Author's guide to Arbital: Basics Requisite used for teaching authors about basic Arbital features. - Alexei Andreev
Author's guide to processing feedback Requisite used for teaching authors about Arbital feedback features. - Alexei Andreev
Automated assistants In my [last post](https://arbital.com/p/1th?title=implementing-our-considered-judgment), I describ… - Paul Christiano
Automation favors those who own the capital. - Travis ionnukestorm@gmail.com
Autonomous AGI The hardest possible class of Friendly AI to build, with the least moral hazard; an AI intended to neither require nor accept further direction. - Eliezer Yudkowsky
Averting instrumental pressures Almost-any utility function for an AI, whether the target is diamonds or paperclips or eudaimonia, implies subgoals like rapidly self-improving and refusing to shut down. Can we make that not happen? - Eliezer Yudkowsky
Averting the convergent instrumental strategy of self-improvement We probably want the first AGI to *not* improve as fast as possible, but improving as fast as possible is a convergent strategy for accomplishing most things. - Eliezer Yudkowsky
Axiom An **axiom** of a [theory\_mathematics theory] $T$ is a [well\_formed well-formed] [sentence\_mathem… - Eric Bruylant
Axiom of Choice The most controversial axiom of the 20th century. - Mark Chimes
Axiom of Choice Definition (Intuitive) Definition of the Axiom of Choice, without using heavy mathematical notation. - Mark Chimes
Axiom of Choice: Guide Learn about the most controversial axiom of the 20th century. - Mark Chimes
Axiom of Choice: History and Controversy Really? The *most* controversial axiom of the 20th century? Yes. - Mark Chimes
Axiom of Choice: Introduction What is the axiom of choice and why do I care? - Mark Chimes
B-Class This page is mostly complete and without major problems, but has not had detailed feedback from the target audience and reviewers. - Eric Bruylant
Bag In mathematics, a "bag" is an unordered list. A bag differs from a set in that it can contain the sa… - Nate Soares
Bayes' Rule and its different forms This is an arc that includes different ways to look at Bayes' Rule. - Alexei Andreev
Bayes' Rule and its implications This is an arc that includes implications of the Bayes's Rule. - Alexei Andreev
Bayes' rule Bayes' rule is the core theorem of probability theory saying how to revise our beliefs when we make a new observation. - Eliezer Yudkowsky
Bayes' rule examples Interesting problems solvable by Bayes' rule - Eliezer Yudkowsky
Bayes' rule: Beginner's guide Beginner's guide to learning about Bayes' rule. - Alexei Andreev
Bayes' rule: Definition Bayes' rule is the mathematics of probability theory governing how to update your beliefs in the lig… - Nate Soares
Bayes' rule: Functional form Bayes' rule for to continuous variables. - Eliezer Yudkowsky
Bayes' rule: Guide The Arbital guide to Bayes' rule - Eliezer Yudkowsky
Bayes' rule: Log-odds form A simple transformation of Bayes' rule reveals tools for measuring degree of belief, and strength of evidence. - Eliezer Yudkowsky
Bayes' rule: Odds form The simplest and most easily understandable form of Bayes' rule uses relative odds. - Eliezer Yudkowsky
Bayes' rule: Odds form (Intro, Math 1) Introduction to the odds form of Bayes' rule - Eliezer Yudkowsky
Bayes' rule: Odds form (Intro, Probability) Intro to Bayes' rule, odds form, for people already familiar with probability. - Eliezer Yudkowsky
Bayes' rule: Probability form The original formulation of Bayes' rule. - Nate Soares
Bayes' rule: Proportional form The fastest way to say something both convincing and true about belief-updating. - Eliezer Yudkowsky
Bayes' rule: Vector form For when you want to apply Bayes' rule to lots of evidence and lots of variables, all in one go. (This is more or less how spam filters work.) - Eliezer Yudkowsky
Bayesian reasoning A probability-theory-based view of the world; a coherent way of changing probabilistic beliefs based on evidence. - Eliezer Yudkowsky
Bayesian update Bayesian updating: the ideal way to change probabilistic beliefs based on evidence. - Eliezer Yudkowsky
Bayesian view of scientific virtues Why is it that science relies on bold, precise, and falsifiable predictions? Because of Bayes' rule, of course. - Eliezer Yudkowsky
Behaviorist genie An advanced agent that's forbidden to model minds in too much detail. - Eliezer Yudkowsky
Being Strategic: The Very Idea Being strategic (here synonymous with "rationality" and "optimization") means systematically working… - Nicolas Bourbaki
Belief revision as probability elimination Update your beliefs by throwing away large chunks of probability mass. - Eliezer Yudkowsky
Big-O Notation This notation describes asymptotic behavior of functions. # O(x) A function f is O(g(x)) if, for la… - Aeneas Mackenzie
Big-picture strategic awareness We start encountering new AI alignment issues at the point where a machine intelligence recognizes the existence of a real world, the existence of programmers, and how these relate to its goals. - Eliezer Yudkowsky
Bijective Function: Intro (Math 0) Two boxes are bijective if they contain the same number of items. - Mark Chimes
Bijective function A bijective function is a function with an inverse. - Patrick Stevens
Binary function A binary function $f$ is a function of two inputs (i.e., a function with arity 2). For example, $+,$… - Nate Soares
Binary notation A way to write down numbers using powers of two. - Malcolm McCrimmon
Bit The term "bit" refers to different concepts in different fields. The common theme across all the us… - Nate Soares
Bit (abstract) An abstract bit is an element of the set $\mathbb B$, which has two elements. An abstract bit is to … - Nate Soares
Bit (of data) A bit of data is the amount of data required to single out one message from a set of two. Equivalen… - Nate Soares
Bit (of data): Examples In the game "20 questions", one player (the "leader") thinks of a concept, and the other players ask… - Nate Soares
Bitcoin will end 2017 higher than $1000 - Alexei Andreev
Blue oysters A probability problem about blue oysters. - Nate Soares
Bone Fracture A bone fracture (sometimes abbreviated **FRX** or **Fx**, **Fx**, or **#**) is a medical … - Alexei Andreev
Boolean A value in logic that evaluates to either "true" or "false". - Malcolm McCrimmon
Bounded agent An agent that operates in the real world, using realistic amounts of computing power, that is uncertain of its environment, etcetera. - Eliezer Yudkowsky
Boxed AI Idea: what if we limit how AI can interact with the world. That'll make it safe, right?? - Eliezer Yudkowsky
Browser optimization for autodidacts Your browser is your window on the 'net. Make it awesome. - Eric Bruylant
Building an intellectual edifice requires ongoing conversation - Eric Bruylant
Bulverism Bulverism is when you explain what goes so horribly wrong in people's minds when they believe X, before you've actually explained why X is wrong. Forbidden on Arbital. - Eliezer Yudkowsky
By end of 2017 ISIS will control less territory than it did at the beginning of the year - Alexei Andreev
Bézout's theorem Bézout's theorem is an important link between highest common factors and the integer solutions of a certain equation. - Patrick Stevens
C-Class This page has substantial content, but may not thoroughly cover the topic, may not meet style and prose standards, or may not explain the concept in a way the target audience will reliably understand. - Eric Bruylant
CFS-spectrum disorders are caused by bacterial or viral infections Chronic fatigue syndrome, fibromyalgia, Gulf War syndrome, and irritable bowel syndrome are often gr… - Sarah Constantin
Calcitriol Calcitriol, also called 1,25-dihydroxycholecalciferol or 1,25-dihydroxyvitamin D3, is the… - Alexei Andreev
Calcitriol in the Treatment of Prostate Cancer Review Link: http://ar.iiarjournals.org/content/26/4A/2647.full.pdf From the abstract: > "Calcitr… - Alexei Andreev
Calcium Calcium is a chemical element with symbol **Ca** and atomic number 20. Calcium is a soft gray alkali… - Alexei Andreev
Calcium Plus Vitamin D Supplementation and the Risk of Breast Cancer Randomized trial Link: http://jnci.oxfordjournals.org/content/100/22/1581.long From conclusions: … - Alexei Andreev
Calcium plus Vitamin D Supplementation and the Risk of Colorectal Cancer Randomized trial Link: http://www.fp.ucalgary.ca/FMResidentSecure/Articles/Ca%20vit%20d%20and%20ca%… - Alexei Andreev
Calories-In-Calories-Out CICO is a proposed conceptual decomposition of the causes of changes in human body mass, particularl… - Eliezer Yudkowsky
Cancer Cancer, also known as a malignant tumor or malignant neoplasm, is a group of diseases involving abno… - Alexei Andreev
Canons (What are they good for?) - Eric Bruylant
Cantor-Schröder-Bernstein theorem This theorem tells us that comparing sizes of sets makes sense: if one set is smaller than another, and the other is smaller than the one, then they are the same size. - Patrick Stevens
Cardinality The "size" of a set, or the "number of elements" that it has. - Joe Zeng
Cardiovascular Disease Cardiovascular disease (CVD) is a class of diseases that involve the heart or blood vessels.Alexei A… - Alexei Andreev
Cartesian agent Agents separated from their environments by impermeable barriers through which only sensory information can enter and motor output can exit. - Eliezer Yudkowsky
Cartesian agent-environment boundary If your agent is separated from the environment by an absolute border that can only be crossed by sensory information and motor outputs, it might just be a Cartesian agent. - Eliezer Yudkowsky
Cartesian product The Cartesian product of two sets $A$ and $B,$ denoted $A \times B,$ is the set of all [ordered\_pai… - Nate Soares
Category (mathematics) A description of how a collection of mathematical objects are related to one another. - Mark Chimes
Category of finite sets The category of finite sets is exactly what it claims to be. It's a useful training ground for some of the ideas of category theory. - Patrick Stevens
Category theory How mathematical objects are related to others in the same category. - Mark Chimes
Cauchy sequence Infinite sequences whose terms get arbitrarily close together. - Joe Zeng
Cauchy's theorem on subgroup existence Cauchy's theorem is a useful condition for the existence of cyclic subgroups of finite groups. - Patrick Stevens
Cauchy's theorem on subgroup existence: intuitive version Cauchy's Theorem states that if $G$ is a finite [-group], and $p$ is a prime dividing the order of $… - Patrick Stevens
Causal decision theories On CDT, to choose rationally, you should imagine the world where your physical act changes, then imagine running that world forward in time. (Therefore, it's irrational to vote in elections.) - Eliezer Yudkowsky
Cayley's Theorem on symmetric groups The "fundamental theorem of symmetry", forging the connection between symmetry and group theory. - Patrick Stevens
Ceiling The ceiling of a real number $x,$ denoted $\lceil x \rceil$ or sometimes $\operatorname{ceil}(x),$ i… - Nate Soares
Center for Applied Rationality Also known as CFAR. It's a non-profit organization created to figure out best rationality practices to mitigate AI x-risk. - Alexei Andreev
Central examples The "central examples" for a subject are examples that are referred to over and over again in the co… - Eliezer Yudkowsky
Central examples List of central examples in Value Alignment Theory domain. - Eliezer Yudkowsky
Challenges for safe AI from RL In this post, I’ll describe and discuss a few big problems for the proposal from [my last post](htt… - Paul Christiano
Chesterton's fence If someone did something, it's generally good to understand their reasons for doing it before undoing it. - Eric Bruylant
Children in a sidebar I always forget to scroll all the way down. I shouldn't have to. Putting children in a sidebar allow… - Olivia Schaefer
Cholecalciferol Cholecalciferol (toxiferol, vitamin D3) is one of the five forms of vitamin D. It is a se… - Alexei Andreev
Church encoding How can you represent things like numbers as lambda expressions? - Dylan Hendrickson
Church-Turing thesis A thesis about computational models - Jaime Sevilla Molina
Church-Turing thesis: Evidence for the Church-Turing thesis Why do we believe in CT thesis? - Jaime Sevilla Molina
Circles of discussion - Alexei Andreev
Civilization scale energy What are the main options for powering civilization, and how do they compare? - Eric Bruylant
Claim explainer: donor lotteries and returns to scale Sometimes, new technical developments in the discourse around effective altruism can be difficult to… - Benjamin Hoffman
Claim-tagging is worth trying more broadly Source of claim: Improve comments by tagging claims by Benjamin Hoffman - Stephanie Zolayvar
Closure A set $S$ is _closed_ under an operation $f$ if, whenever $f$ is fed elements of $S$, it produces an… - Nate Soares
Codomain (of a function) The codomain $\operatorname{cod}(f)$ of a function $f : X \to Y$ is $Y$, the set of possible outputs… - Nate Soares
Codomain vs image It is useful to distinguish codomain from image both (a) when the type of thing that the function pr… - Nate Soares
Cognitive domain An allegedly compact unit of knowledge, such that ideas inside the unit interact mainly with each other and less with ideas in other domains. - Eliezer Yudkowsky
Cognitive steganography Disaligned AIs that are modeling human psychology and trying to deceive their programmers will want to hide their internal thought processes from their programmers. - Eliezer Yudkowsky
Cognitive uncontainability 'Cognitive uncontainability' is when we can't hold all of an agent's possibilities inside our own minds. - Eliezer Yudkowsky
Coherence theorems A 'coherence theorem' shows that something bad happens to an agent if its decisions can't be viewed as 'coherent' in some sense. E.g., an inconsistent preference ordering leads to going in circles. - Eliezer Yudkowsky
Coherent decisions imply consistent utilities Why do we all use the 'expected utility' formalism? Because any behavior that can't be viewed from that perspective, must be qualitatively self-defeating (in various mathy ways). - Eliezer Yudkowsky
Coherent extrapolated volition (alignment target) A proposed direction for an extremely well-aligned autonomous superintelligence - do what humans would want, if we knew what the AI knew, thought that fast, and understood ourselves. - Eliezer Yudkowsky
Coliteracy The coliteracy of two parties is the - Alex Peterson
Collusion is a major concern Breaking out of the Prisoner's Dilemma - Olivia Schaefer
Colon-to notation Find out what the notation "f : X -> Y" means that everyone keeps using. - Qiaochu Yuan
Combining vectors One of the most useful things we can do with vectors is to combine them! - Adele Lopez
Comments are a high-quality, high-sensitivity measure of engagement with little in the way of viable substitutes. Source of claim: Improve comments by tagging claims by Benjamin Hoffman - Stephanie Zolayvar
Communication: magician example Imagine that you and I are both magicians, performing a trick where I think of a card from a deck of… - Nate Soares
Commutative operation A commutative function $f$ is a function that takes multiple inputs from a set $X$ and produces an o… - Nate Soares
Commutativity: Examples Yes: addition, multiplication, maximum, minimum, rock-paper-scissors. No: subtraction, division, st… - Nate Soares
Commutativity: Intuition We can think of commutativity either as an artifact of notation, or as a symmetry in the output of a… - Nate Soares
Complete lattice A poset that is closed under arbitrary joins and meets. - Kevin Clancy
Complex number A complex number is a number of the form $z = a + b\textrm{i}$, where $\textrm{i}$ is the imaginary … - Eliana Ruby
Complexity of value There's no simple way to describe the goals we want Artificial Intelligences to want. - Eliezer Yudkowsky
Complexity theory Study of the computational resources needed to compute something - Jaime Sevilla Molina
Complexity theory: Complexity zoo Pass and see the exotic beasts coming from the lands of afar! - Jaime Sevilla Molina
Comprehensive guide to Bayes' Rule This is an arc that includes all Bayes content. - Alexei Andreev
Compressing multiple messages How many bits of data does it take to encode an $n$-message? Naively, the answer is $\lceil \log_2(n… - Nate Soares
Computer Programming Familiarity Want to see programming analogies and applications in your math explanations? Mark this as known. - Kevin Clancy
Conceivability A hypothetical scenario is 'conceivable' or 'imaginable' when it is not *immediately* incoherent, al… - Eliezer Yudkowsky
Concept Add this meta tag to pages which are concepts. - Alexei Andreev
Concrete approval-directed agents This post lays out my current concrete “[approval-directed agents](https://arbital.com/p/1t7)” propo… - Paul Christiano
Concrete groups (Draft) Instead of thinking of a group as a set with operations satisfying axoims, we develop groups as symmetry groups of various objects - Daniel Satanove
Conditional probability The notation for writing "The probability that someone has green eyes, if we know that they have red hair." - Eliezer Yudkowsky
Conditional probability: Refresher Is P(yellow | banana) the probability that a banana is yellow, or the probability that a yellow thing is a banana? - Nate Soares
Confirming understanding Attempts to explain a concept should be falsifiable - Duncan Sabien
Conjugacy class In a group, the elements can be partitioned naturally into certain classes. - Patrick Stevens
Conjugacy class is cycle type in symmetric group There is a neat characterisation of the conjugacy classes in the symmetric group on a finite set. - Patrick Stevens
Conjugacy classes of the alternating group on five elements $A_5$ has easily-characterised conjugacy classes, based on a rather surprising theorem about when conjugacy classes in the symmetric group split. - Patrick Stevens
Conjugacy classes of the alternating group on five elements: Simpler proof A listing of the conjugacy classes of the alternating group on five letters, without using heavy theory. - Patrick Stevens
Conjugacy classes of the symmetric group on five elements The symmetric group on five elements is a group of just the right size to make a good example of a table of conjugacy classes. - Patrick Stevens
Conjunctions and disjunctions The fancy name for the "and" and "or" connectives. - Jeremy Perret
Consciousness research and valence research are tractable See: Principia Qualia: blueprint for a new cause area, consciousness research with an eye toward eth… - Eric Rogstad
Consciousness research is critically important See: Principia Qualia: blueprint for a new cause area, consciousness research with an eye toward et… - Eric Rogstad
Consciousness research is time-sensitive See: Principia Qualia: blueprint for a new cause area, consciousness research with an eye toward et… - Eric Rogstad
Consequentialist cognition The cognitive ability to foresee the consequences of actions, prefer some outcomes to others, and output actions leading to the preferred outcomes. - Eliezer Yudkowsky
Consequentialist preferences are reflectively stable by default Gandhi wouldn't take a pill that made him want to kill people, because he knows in that case more people will be murdered. A paperclip maximizer doesn't want to stop maximizing paperclips. - Eliezer Yudkowsky
Conservative concept boundary Given N example burritos, draw a boundary around what is a 'burrito' that is relatively simple and allows as few positive instances as possible. Helps make sure the next thing generated is a burrito. - Eliezer Yudkowsky
Consistency A consistent [-theory] is one in which there are well-formed statements that you cannot prove from i… - Jaime Sevilla Molina
Context disaster Some possible designs cause your AI to behave nicely while developing, and behave a lot less nicely when it's smarter. - Eliezer Yudkowsky
Contributing to Arbital Want to help Arbital become awesome? - Eric Bruylant
Convergent instrumental strategies Paperclip maximizers can make more paperclips by improving their cognitive abilities or controlling more resources. What other strategies would almost-any AI try to use? - Eliezer Yudkowsky
Convergent strategies of self-modification The strategies we'd expect to be employed by an AI that understands the relevance of its code and hardware to achieving its goals, which therefore has subgoals about its code and hardware. - Eliezer Yudkowsky
Convex **Placeholder** - Eric Bruylant
Convex function A function that only curves upward - Jessica Taylor
Convex set A set that contains all line segments between points in the set - Jessica Taylor
Coordinative AI development hypothetical What would safe AI development look like if we didn't have to worry about anything else? - Eliezer Yudkowsky
Core concepts for creating good explanations A moderately deep dive into the concepts that underlie understanding and how to create it. - Duncan Sabien
Corporations vs. superintelligences Corporations have relatively few of the advanced-agent properties that would allow one mistake in aligning a corporation to immediately kill all humans and turn the future light cone into paperclips. - Eliezer Yudkowsky
Correct credit-tracking is very important if we want our community to generate new good ideas. Correct credit-tracking is very important if we want our community to generate new good ideas. - Anna Salamon
Correlated competency When an AI achieving sufficiently high goodness on behavior A means we should strongly expect high goodness on behavior B. - Eliezer Yudkowsky
Correlated coverage In which parts of AI alignment can we hope that getting many things right, will mean the AI gets everything right? - Eliezer Yudkowsky
Correspondence visualizations for different interpretations of "probability" Let's say you have a model which says a particular coin is 70% likely to be heads. How should we as… - Nate Soares
Corrigibility "I can't let you do that, Dave." - Nate Soares
Cosmic endowment The 'cosmic endowment' consists of all the stars that could be reached from probes originating on Earth; the sum of all matter and energy potentially available to be transformed into life and fun. - Eliezer Yudkowsky
Cosmopolitan value Intuitively: Value as seen from a broad, embracing standpoint that is aware of how other entities may not always be like us or easily understandable to us, yet still worthwhile. - Eliezer Yudkowsky
Countability Some infinities are bigger than others. Countable infinities are the smallest infinities. - Alexei Andreev
Counterfactual oversight vs. training data I have written a lot recently about [counterfactual human oversight](https://arbital.com/p/1tj?titl… - Paul Christiano
Creating a /learn/ link What options are available when creating a /learn/ link? - Alexei Andreev
Crony belief **Crony belief** is a concept originally introduced in Kevin Simler's post, "Crony Beliefs". It's us… - Alexei Andreev
Crony beliefs (from Melting Asphalt) The original article that introduced and explained "merit beliefs" vs "crony beliefs" dichotomy. - Alexei Andreev
Crowdsourcing moderation without sacrificing quality - Eric Rogstad
Currying Transforms a function of many arguments into a function into a function of a single argument - M Yass
Curtis's Blog I'm testing the blogging functionality. - Curtis SerVaas
Cycle notation in symmetric groups Cycle notation is a convenient way to represent the elements of a symmetric group. - Patrick Stevens
Cycle type of a permutation The cycle type is an invariant of a permutation in the symmetric group. - Patrick Stevens
Cyclic Group Intro (Math 0) A finite cyclic group is a little bit like a clock. - Mark Chimes
Cyclic group Cyclic groups form one of the most simple classes of groups. - Patrick Stevens
Data capacity The data capacity of an object is defined to be the Logarithm of the number of different distinguish… - Nate Soares
David Moore
Death in Damascus Death tells you that It is coming for you tomorrow. You can stay in Damascus or flee to Aleppo. Whichever decision you actually make is the wrong one. This gives some decision theories trouble. - Eliezer Yudkowsky
Decimal notation The winning architecture for numerals - Michael Cohen
Decision Theory Nothing here yet.] Automatically generated page for "Decision Theory" group. If you are the owner,… - Alexei Andreev
Decision problem Formalization of general problems - Jaime Sevilla Molina
Decision theory The mathematical study of ideal decisionmaking - Eliezer Yudkowsky
Decit Decimal digit - Nate Soares
Deep Blue The chess-playing program, built by IBM, that first won the world chess championship from Garry Kasparov in 1996. - Eliezer Yudkowsky
Definition Meta tag used to mark pages that strictly define a particular term or phrase. - Eliezer Yudkowsky
Delegating to a mixed crowd ### Suppose I have ten programs, each a human-level agent. I suspect that at least one or two of… - Paul Christiano
Dependent messages can be encoded cheaply Say you want to transmit a 2-message, a 4-message, and a 256-message to somebody. For example, you m… - Nate Soares
Derivative How things change - Michael Cohen
Descriptive versus normative propositions A normative proposition talks about what should be; a descriptive proposition talks about what is. - Eliezer Yudkowsky
Development phase unpredictable Several proposed problems in advanced safety are alleged to be difficult because they depend on some… - Eliezer Yudkowsky
Diagonal lemma Constructing self-referential sentences - Jaime Sevilla Molina
Diamond maximizer How would you build an agent that made as much diamond material as possible, given vast computing power but an otherwise rich and complicated environment? - Eliezer Yudkowsky
Difference Between Weights and Biases: Another way of Looking at Forward Propagation My understanding on Forward Propagation - Alto Clef
Difficulty of AI alignment How hard is it exactly to point an Artificial General Intelligence in an intuitively okay direction? - Eliezer Yudkowsky
Digit wheel A mechanical device for storing a number from 0 to 9. ![](http://www.cl.cam.ac.uk/~djg11/howcompu… - Nate Soares
Dihedral group The dihedral groups are natural examples of groups, arising from the symmetries of regular polygons. - Patrick Stevens
Dihedral groups are non-abelian The group of symmetries of the triangle and all larger regular polyhedra are not abelian. - Patrick Stevens
Direct sum of vector spaces The direct sum of two vector spaces $U$ and $W,$ written $U \oplus W,$ is just the sum of $U$ and $W… - Nate Soares
Directing, vs. limiting, vs. opposing Getting the AI to compute the right action in a domain; versus getting the AI to not compute at all in an unsafe domain; versus trying to prevent the AI from acting successfully. (Prefer 1 & 2.) - Eliezer Yudkowsky
Disambiguation Several distinct concepts use this page's name, this page helps readers find what they're looking for. - Eric Bruylant
Discussion norms What makes conversation productive? - Eric Rogstad
Diseasitis 20% of patients have Diseasitis. 90% of sick patients and 30% of healthy patients turn a tongue depressor black. You turn a tongue depressor black. What's the chance you have Diseasitis? - Eliezer Yudkowsky
Disjoint cycle notation is unique Disjoint cycle notation provides a canonical way to express elements of the symmetric group. - Patrick Stevens
Disjoint cycles commute in symmetric groups In cycle notation, if two cycles are disjoint, then they commute. - Patrick Stevens
Disjoint union of sets One of the most basic ways we have of joining two sets together. - Patrick Stevens
Displaying the list of fundraiser donors sorted by the donation date would help with the "wait and see" problem. - Alexei Andreev
Distances between cognitive domains Often in AI alignment we want to ask, "How close is 'being able to do X' to 'being able to do Y'?" - Eliezer Yudkowsky
Distant superintelligences can coerce the most probable environment of your AI Distant superintelligences may be able to hack your local AI, if your AI's preference framework depends on its most probable environment. - Eliezer Yudkowsky
Distinguish which advanced-agent properties lead to the foreseeable difficulty Say what kind of AI, or threshold level of intelligence, or key type of advancement, first produces the difficulty or challenge you're talking about. - Eliezer Yudkowsky
Division of rational numbers (Math 0) "Division" is the idea of "dividing something up among some people so that we can give equal amounts to each person". - Patrick Stevens
Do-What-I-Mean hierarchy Successive levels of "Do What I Mean" or AGIs that understand their users increasingly well - Eliezer Yudkowsky
Does solar exposure, as indicated by the non-melanoma skin cancers, protect from solid cancers: Vitamin D as a possible explanation Correlational study Link: http://www.ejcancer.com/article/S0959-8049%2807%2900324-3/abstract From … - Alexei Andreev
Domain (of a function) The domain $\operatorname{dom}(f)$ of a function $f : X \to Y$ is $X$, the set of valid inputs for t… - Nate Soares
Don't try to solve the entire alignment problem New to AI alignment theory? Want to work in this area? Already been working in it for years? Don't try to solve the entire alignment problem with your next good idea! - Eliezer Yudkowsky
Donald Trump remains President at the end of 2017 - Alexei Andreev
Donald Trump’s approval rating at the end of 2017 is lower than fifty percent - Alexei Andreev
Donald Trump’s approval rating at the end of 2017 is lower than forty percent - Alexei Andreev
Donor coordination How should donors behave, given that their actions may affect other donors? - Eric Rogstad
Donor lotteries: demonstration and FAQ - Ryan Carey
Donor lottery An arrangement where a group of people pool their money and pick one person to give it away. - Alexei Andreev
Doppler Effect Why do things make a higher pitch sound as they come toward me but lower as they go away? - Silas Barta
Double Crux — A Strategy for Resolving Disagreement - Eric Rogstad
Dow Jones will not end 2017 down by more than 10% - Alexei Andreev
Drinking on average 8 grams of alcohol a day will shorten your life expectancy This is a very small amount equivalent to one UK unit. See https://en.wikipedia.org/wiki/Recommended… - Tom Ash
Early-life planning How do you figure out what to do at the beginning of your life? - Ben Pace
Easier, better, faster, brighter In which Arbital gets a makeover, shortcuts, quick feedback, and more! - Alexei Andreev
Edge instantiation When you ask the AI to make people happy, and it tiles the universe with the smallest objects that can be happy. - Eliezer Yudkowsky
Effability principle You are safer the more you understand the inner structure of how your AI thinks; the better you can describe the relation of smaller pieces of the AI's thought process. - Eliezer Yudkowsky
Effect of four monthly oral vitamin D3 (cholecalciferol) supplementation on fractures and mortality in men and women living in the community: randomised double blind controlled trial Randomised double blind controlled trial. Link: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC150177/… - Alexei Andreev
Effective altruism What's the most good you can do? - Eric Rogstad
Effective altruism outreach Effective Altruism Outreach (EAO) is part of the Centre for Effective Altruism and is an organizatio… - Alexei Andreev
Effective number of political parties A way of quantifying the relative dominance of a few political parties regardless of their actual number. - Joe Zeng
Effectiveness of scaling and root planing for gingivitus/periodontal disease Scaling and root planing (SRP) is a dental procedure that involves scraping stuff off of your teeth … - Daniel Smith
Efficient feedback In some machine learning domains, such as image classification, we can produce a bunch of labelled t… - Paul Christiano
Eigenvalues and eigenvectors We applied this linear transformation to one of its eigenvectors; you won't believe what happened next! - Zack M. Davis
Elaborations on apprenticeship learning Apprenticeship learning (AL) is an intuitively appealing approach to AI control. In AL, a human expe… - Paul Christiano
Element **Placeholder** - Eric Bruylant
Elementary Algebra How do we describe relations between different things? How can we figure out new true things from tr… - Adele Lopez
Eliezer office hours A series of meetings with Big Yud himself. - Eric Rogstad
Eliezer office hours 2016-04-19 ### Steph's notes from the actual meeting: - "good question" -> people upvoting your question is a g… - Eric Rogstad
Eliezer office hours 2016-05-07 ##Questions for Eliezer## ###Strategy### Q: What does a discussion of which EA cause to donate to … - Eric Rogstad
Eliezer's vision for Arbital Why are we building this? What's the goal? - Eric Bruylant
Emphemeral premises When somebody says X, don't just say, "Oh, not-X because Y" and then forget about Y a day later. Y is now an important load-bearing assumption in your worldview. Write Y down somewhere. - Eliezer Yudkowsky
Empirical probabilities are not exactly 0 or 1 "Cromwell's Rule" says that probabilities of exactly 0 or 1 should never be applied to empirical propositions - there's always some probability, however tiny, of being mistaken. - Eliezer Yudkowsky
Empty set The empty set does what it says on the tin: it is the set which is empty. - Patrick Stevens
Empty set The empty set, $\emptyset$, is the set with no elements. For every object $x$, $x$ is not in $\empt… - Patrick Stevens
Emulating digits In general, given enough $n$-digits, you can emulate an $m$-digit, for any $m, n \in$ $\mathbb N$. I… - Nate Soares
Encoding trits with GalCom bits There are $\log_2(3) \approx 1.585$ bits to a Trit. Why is it that particular value? Consider the Ga… - Nate Soares
Environmental goals The problem of having an AI want outcomes that are out in the world, not just want direct sense events. - Eliezer Yudkowsky
Epistemic and instrumental efficiency An efficient agent never makes a mistake you can predict. You can never successfully predict a directional bias in its estimates. - Eliezer Yudkowsky
Epistemic exclusion How would you build an AI that, no matter what else it learned about the world, never knew or wanted to know what was inside your basement? - Eliezer Yudkowsky
Epistemology What is truth? - Eliezer Yudkowsky
Equaliser (category theory) In Category theory, an *equaliser* of a pair of arrows $f, g: A \to B$ is an object $E$ and a univer… - Patrick Stevens
Equivalence relation A relation that allows you to partition a set into equivalence classes. - Dylan Hendrickson
Establishing a permanent off-Earth colony would be a useful way to mitigate x-risk - Posed by [purplepeople](http://effective-altruism.com/user/purplepeople/) on the [EA Forum](http:/… - Eric Rogstad
Ethics Offsets to the Rescue Hate hurting animals, but love eating meat? Throw money at the problem! - Eric Rogstad
Ethics research should proceed in parallel to value alignment research - Eric Rogstad
Euclid's Lemma on prime numbers A very basic but vitally important property of the prime numbers is that they "can't be split between factors": if a prime divides a product then it must divide one of the individual factors. - Patrick Stevens
Euclidean domains are principal ideal domains A Euclidean domain is one where we may somehow perform the division algorithm; this gives us access to some of the nicest properties of the integers. - Patrick Stevens
Every group is a quotient of a free group Given a group $G$, there is a Free group $F(X)$ on some set $X$, such that $G$ is isomorphic to some… - Patrick Stevens
Every member of a symmetric group on finitely many elements is a product of transpositions This fact can often simplify arguments about permutations: if we can show that something holds for transpositions, and that it holds for products, then it holds for everything. - Patrick Stevens
Evidential decision theories Theories which hold that the principle of rational choice is "Choose the act that would be the best news, if somebody told you that you'd chosen that act." - Eliezer Yudkowsky
Evolution Strategies and Reinforcement Learning Evolution strategies as a simplified implementation of reinforcement learning - Ashton Hellwig
Examination through isomorphism Isomorphism is the correct notion of equality between objects in a category. From the category-theor… - Luke Sciarappa
Example problem Tag for pages that provide an example problem referenced by a number of other pages. The summary of… - Nate Soares
Example: Dragon Pox Kai might have Dragon Pox. Oy. - Tsvi BT
Examples of good explanations A representative variety of good explanations, along with analysis of what each explanation does well (or not). - Duncan Sabien
Exchange rates between digits In terms of data storage, if a coin is worth $1, a digit wheel is worth more than $3.32, but less than $3.33. Why? - Nate Soares
Executable philosophy Philosophical discourse aimed at producing a trustworthy answer or meta-answer, in limited time, which can used in constructing an Artificial Intelligence. - Eliezer Yudkowsky
Exercise Meta tag for pages with exercises to practice a concept. - Eric Bruylant
Existence Proof of Logical Inductor A procedure for constructing an algorithm that is a logical inductor relative to any given deductive set. - Tarn Somervell Fletcher
Existential risk > Because of accelerating technological progress, humankind may be rapidly approaching a critical ph… - Eric Rogstad
Existential risk one where an adverse outcome would either **annihilate Earth-originating intelligent life** or perma… - Carolina Villegas
Expected utility Scoring actions based on the average score of their probable consequences. - Eliezer Yudkowsky
Expected utility agent If you're not some kind of expected utility agent, you're going in circles. - Eliezer Yudkowsky
Expected utility formalism Expected utility is the central idea in the quantitative implementation of consequentialism - Eliezer Yudkowsky
Expected value Trying to assign value to an uncertain state? The weighted average of outcomes is probably the tool you need. - Michael Cohen
Explicit Bayes as a counter for 'worrying' Explicitly walking through Bayes's Rule can summarize your knowledge and thereby stop you from bouncing around pieces of it. - Eliezer Yudkowsky
Explicitly tagging the core claims of a post will make people substantially more likely to respond to these claims. Source of claim: Improve comments by tagging claims by Benjamin Hoffman - Stephanie Zolayvar
Exponential Any function that constantly gets larger as a proportion of itself. - Joe Zeng
Exponential notation for function spaces Why $Y^X$ is good notation for the space of maps from $X$ to $Y$ - Izaak Meckler
Extensionality Axiom If two sets have exactly the same members, then they are equal - Ilia Zaichuk
External resources This lens links out to other great resources across the web. - Eric Bruylant
Externality Positive and negative affects on third parties, and the considerations they introduce - Silas Barta
Extraordinary claims What makes something an 'extraordinary claim' that requires extraordinary evidence? - Eliezer Yudkowsky
Extraordinary claims require extraordinary evidence The people who adamantly claim they were abducted by aliens do provide some evidence for aliens. They just don't provide quantitatively enough evidence. - Eliezer Yudkowsky
Extrapolated volition (normative moral theory) If someone asks you for orange juice, and you know that the refrigerator contains no orange juice, should you bring them lemonade? - Eliezer Yudkowsky
Factorial The number of ways you can order things. (Alternately subtitled: Is that exclamation point a factorial, or are you just excited to see me?) - Michael Cohen
Factorial The *factorial* of a number $n$ is how we describe "how many different ways we can arrange $n$ obje… - Patrick Stevens
Fair problem class A problem is 'fair' (according to logical decision theory) when only the results matter and not how we get there. - Eliezer Yudkowsky
Faithful simulation How would you identify, to a Task AGI (aka Genie), the problem of scanning a human brain, and then running a sufficiently accurate simulation of it for the simulation to not be crazy or psychotic? - Eliezer Yudkowsky
Fallacies To call something a fallacy is to assert that you think people shouldn't think like that. - Eliezer Yudkowsky
Featured This page is has been selected by Arbital to be featured and promoted. - Eric Bruylant
Featured math content Some Arbital pages we think are great! - Eric Bruylant
Feed meta tags Children of this page are meta tags that are used to add a page to a feed. - Alexei Andreev
Fewer refugees admitted by Europe in 2017 than 2016 - Alexei Andreev
Field homomorphism is trivial or injective Field homomorphisms preserve a *lot* of structure; they preserve so much structure that they are always either injective or totally boring. - Patrick Stevens
Field structure of rational numbers In which we describe the field structure on the rationals. - Patrick Stevens
Finishing your Bayesian path on Arbital The page that comes at the end of reading the Arbital Guide to Bayes' rule - Eliezer Yudkowsky
Finite set A finite set is one which is not infinite. Some of these are the least complicated sets. - Patrick Stevens
First order linear equations A **first order lineal equation** has the form $$ u'=a(t)u+b(t) $$ where $a$ and $b$ are continuous … - Jaime Sevilla Molina
Fixed point theorem of provability logic Deal with those pesky self-referential sentences! - Jaime Sevilla Molina
Flag the load-bearing premises If somebody says, "This AI safety plan is going to fail, because X" and you reply, "Oh, that's fine because of Y and Z", then you'd better clearly flag Y and Z as "load-bearing" parts of your plan. - Eliezer Yudkowsky
Flexagon Flexagons are flat models, that can be flexed in certain ways to reveal faces besides the two that were originally on the back and front - Ilia Livshits
Focusing Focusing is a psychotherapeutic process developed by psychotherapist Eugene Gendlin - Alexei Andreev
For mitigating AI x-risk, an off-Earth colony would be about as useful as a warm scarf H/T to Eliezer Yudkowsky for ["warm scarf"](https://www.facebook.com/robert.wiblin/posts/75711126783… - Eric Rogstad
For most EA-Blank projects, we would expect more good to be done if they would: i) disband or ii) remove EA from the name and aim to outgrow the EA movement. The claim refers to projects like: * Effective Altruism Forum * Effective Altruism Handbook * Effec… - Ryan Carey
Formal Logic Formal logic studies the form of correct arguments through rigorous and precise mathematical theories. - Erik Istre
Formal definition This page gives a purely formal definition of a topic, rather than motivating, explaining, and giving examples. - Eric Bruylant
Formal definition of the free group Van der Waerden's trick lets us define the free groups in a slick but mostly incomprehensible way. - Patrick Stevens
Formatting issues This page has formatting or mathjax issues. - Eric Bruylant
Fractional bits It takes $\log_2(8) = 3$ bits of data to carry one message from a set of 8 possible messages. Simila… - Nate Soares
Fractional bits: Digit usage interpretation It is 316, not 500, that requires about two and a half digits to write down. 500 requires nearly 2.7… - Nate Soares
Fractional bits: Expected cost interpretation In the GalCom thought experiment, you regularly have to send large volumes of information through de… - Nate Soares
Fractional digits When $b$ and $x$ are integers, $\log_b(x)$ has a few good interpretations. It's roughly the length o… - Nate Soares
France will not declare a plan to leave EU in 2017 - Alexei Andreev
Free group The free group is "the purest way to make a group containing a given set". - Patrick Stevens
Free group universal property The Free group may be defined by a Universal property, allowing Category theory to talk about free … - Patrick Stevens
Free groups are torsion-free An easy way to determine that many groups are not free: free groups contain no non-identity elements of finite order. - Patrick Stevens
Freely reduced word "Freely reduced" captures the idea of "no cancellation" in a free group. - Patrick Stevens
Frequency diagram Visualizing Bayes' rule by manipulating frequencies in large populations - Nate Soares
Frequency diagrams: A first look at Bayes The most straightforward visualization of Bayes' rule. - Nate Soares
Friendly AI Old terminology for an AI whose preferences have been successfully aligned with idealized human values. - Eliezer Yudkowsky
Function Intuitively, a function $f$ is a procedure (or machine) that takes an input and performs some opera… - Nate Soares
Function: Physical metaphor Many functions can be visualized as physical mechanisms of wheels and gears, that take their inputs … - Nate Soares
Fundamental Theorem of Arithmetic The FTA tells us that natural numbers can be decomposed uniquely into prime factors; it is the basis of almost all number theory. - Patrick Stevens
Funding governance filtering Current-best guess at how these parts of organization will happen. ### Funding Eric provided initi… - Eric Bruylant
Fundraisers should have a threshold amount which, if not hit, results in a refund. When starting a fundraiser, a nonprofit should declare a threshold amount. If the nonprofit doesn't … - Alexei Andreev
GalCom In the GalCom thought experiment, you live in the future, and make your money by living in the Dene… - Nate Soares
GalCom: Rules 1. It costs 1 galcoin per bit to reserve on-peak bits in advance. (Galcoins are very expensive.) 2. … - Nate Soares
General intelligence Compared to chimpanzees, humans seem to be able to learn a much wider variety of domains. We have 'significantly more generally applicable' cognitive abilities, aka 'more general intelligence'. - Eliezer Yudkowsky
Generalized associative law Given an associative operator $\cdot$ and a list $[a, b, c, \ldots]$ of parameters, all ways of red… - Nate Soares
Generalized element A category-theoretic generalization of the notion of element of a set. - Luke Sciarappa
Generalized principle of cognitive alignment When we're asking how we want the AI to think about an alignment problem, one source of inspiration is trying to have the AI mirror our own thoughts about that problem. - Eliezer Yudkowsky
Geometric algebra A geometric algebra is a Clifford algebra over the reals which represents Euclidean geometry and man… - Adele Lopez
Geometric product #Motivation want to incorporate rotors like $e^{\text{I}\theta}$ and scalars $n$ in the same system … - Adele Lopez
Geometric product: summary Product for [multivectors multivectors]. Associative, left and right distributive. Non-commutative. … - Adele Lopez
Geometry of vectors: direction What rotation would it take to line up this vector to this one? - Adele Lopez
Germany will not declare a plan to leave EU - Alexei Andreev
GiveWell and the problem of partial funding A foundation that plans to move around ten billion dollars and is relying on advice from GiveWell isn’t enough to get the top charities fully funded. That’s weird and surprising. - Benjamin Hoffman
GiveWell: a case study in effective altruism, part 1 > GiveWell has recently [written about](http://blog.givewell.org/2015/11/25/good-ventures-and-giving… - Alexei Andreev
Glossary (Value Alignment Theory) Words that have a special meaning in the context of creating nice AIs. - Eliezer Yudkowsky
Goal-concept identification Figuring out how to say "strawberry" to an AI that you want to bring you strawberries (and not fake plastic strawberries, either). - Eliezer Yudkowsky
Good Ventures has increasing returns to scale - Benjamin Hoffman
Goodhart's Curse The Optimizer's Curse meets Goodhart's Law. For example, if our values are V, and an AI's utility function U is a proxy for V, optimizing for high U seeks out 'errors'--that is, high values of U - V. - Eliezer Yudkowsky
Goodness estimate biaser Some of the main problems in AI alignment can be seen as scenarios where actual goodness is likely to be systematically lower than a broken way of estimating goodness. - Eliezer Yudkowsky
Gotcha button A conversational point which, when pressed, causes the other person to shout "Gotcha!" and leap on what they think is a weakness allowing them to dismiss the conversation. - Eliezer Yudkowsky
Graham's number A fairly large number, as numbers go. - Nate Soares
Greatest common divisor The greatest common divisor of two natural numbers is… the largest number which is a divisor of both. The clue is in the name, really. - Patrick Stevens
Greatest lower bound in a poset The greatest lower bound is an abstraction of the idea of the greatest common divisor to a general poset. - Patrick Stevens
Grid scale storage Scalable energy storage is required if civilization's switches to primarily renewables in order to keep the grid powered at night. What are the options and how do they compare? - Eric Bruylant
Group The algebraic structure that captures symmetry, relationships between transformations, and part of what multiplication and addition have in common. - Nate Soares
Group action "Groups, as men, will be known by their actions." - Qiaochu Yuan
Group action induces homomorphism to the symmetric group We can view group actions as "bundles of homomorphisms" which behave in a certain way. - Patrick Stevens
Group conjugate Conjugation lets us perform permutations "from the point of view of" another permutation. - Patrick Stevens
Group coset Given a subgroup $H$ of Group $G$, the *left cosets* of $H$ in $G$ are sets of the form $\{ gh : h \… - Patrick Stevens
Group homomorphism A group homomorphism is a "function between groups" that "respects the group structure". - Patrick Stevens
Group isomorphism "Isomorphism" is the proper notion of "sameness" or "equality" among groups. - Patrick Stevens
Group orbit When we have a group acting on a set, we are often interested in how the group acts on a particular … - Adele Lopez
Group orbits partition When a group acts on a set, the set falls naturally into distinct pieces, where the group action only permutes elements within any given piece, not between them. - Patrick Stevens
Group presentation Presentations are a fairly compact way of expressing groups. - Patrick Stevens
Group theory What kinds of symmetry can an object have? - Nate Soares
Group theory: Examples What does thinking in terms of group theory actually look like? And what does it buy you? - Qiaochu Yuan
Group: Examples Why would anyone have invented groups, anyway? What were the historically motivating examples, and what examples are important today? - Qiaochu Yuan
Group: Exercises Test your understanding of the definition of a group with these exercises. - Qiaochu Yuan
Groups as symmetires A group is an abstraction of a collection of symmetries of an object. Examples of groups include th… - Daniel Satanove
Groups trying to make intellectual progress need a central locus of discussion For communities that are trying to make intellectual progress, it's important to have a single place… - Stephanie Zolayvar
Growing the EA movement is net positive - Eric Rogstad
Guarded definition A guarded definition is one where at least one position suspects there will be pressure to stretch a… - Eliezer Yudkowsky
Guide Meta tag for the start page of a multi-page guide. - Eric Bruylant
Guide to Logical Decision Theory The entry point for learning about logical decision theory. - Eliezer Yudkowsky
Gödel II and Löb's theorem [ Gödel's second incompleteness theorem] and [ Löb's theorem] are equivalent to each other. ] The … - Jaime Sevilla Molina
Gödel encoding and self-reference The formalism that mathematicians use to talk about arithmetic turns out to be able to talk about itself. - Patrick LaVictoire
Gödel's first incompleteness theorem The theorem that destroyed Hilbert's program - Jaime Sevilla Molina
Handling adversarial errors Even a very powerful learning system can’t do everything perfectly at first — it requires time to l… - Paul Christiano
Handling errors with arguments My [recent proposal](https://arbital.com/p/1v7?title=steps-towards-safe-ai-from-online-learning) f… - Paul Christiano
Happiness maximizer It is sometimes proposed that we build an AI intended to maximize human happiness. (One early propo… - Eliezer Yudkowsky
Hard problem of corrigibility Can you build an agent that reasons as if it knows itself to be incomplete and sympathizes with your wanting to rebuild or correct it? - Eliezer Yudkowsky
Harem A group of women loving their superman. - Dmitriy Zhukov
Harmless supernova fallacy False dichotomies and continuum fallacies which can be used to argue that anything, including a supernova, must be harmless. - Eliezer Yudkowsky
Harry Potter at Ollivander's A simple word problem on the application of Bayes rule. - Vojta Kovarik
Headers demo Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore … - Stephanie Zolayvar
Hexayurt External resource: http://hexayurt.com/![enter image description here](https://s-media-cache-ak0.pin… - Eric Bruylant
High-speed explanation Use this tag to indicate that a page offers a relatively faster and more terse explanation. Note th… - Eric Rogstad
High-speed intro to Bayes's rule A high-speed introduction to Bayes's Rule on one page, for the impatient and mathematically adept. - Eliezer Yudkowsky
Hiring What's Omniment's protocol for hiring employees? - Alexei Andreev
How common is imitation? How often do we train machine learning systems to imitate human behavior? Some researchers explicit… - Paul Christiano
How many bits to a trit? $\log_2(3) \approx 1.585.$ This can be interpreted a few different ways: 1. If you multiply the nu… - Nate Soares
How much of the discussion around AI safety should be public? - Alexei Andreev
How to author on Arbital! Want to contribute pages to Arbital? Here's our current version of the ad-hoc guide to being an author! - Eliezer Yudkowsky
How to build your own Lumenator Treating Seasonal Affective Disorder using MOAR LIGHT can sometimes solve what dinky little lightboxes can't. - Eliezer Yudkowsky
How understanding is made How analogy and concept maps help us acquire and retain knowledge - Duncan Sabien
Hub page This tag is applied to pages which server the role of a "hub": the user starts there, goes off to learn more about the topic, and then comes back. This meta tag modifies the page's UI. - Alexei Andreev
Human arguments and AI control ### Explanation and AI control Consider the definition: > An action is good to the extent that I w… - Paul Christiano
Human in counterfactual loop Consider an autonomous system which is buying or selling assets, operating heavy machinery, or mak… - Paul Christiano
Human in the counterfactual loop Consider an autonomous system which is buying or selling assets, operating heavy machinery, or makin… - Olivia Schaefer
Human perception of sound What is the mechanism by which vibrations around the human ear are translated into the sensation of sound? - Silas Barta
Humans consulting HCH Consider a human who has access to a question-answering machine. Suppose the machine answers questio… - Paul Christiano
Humans doing Bayes The human use of Bayesian reasoning in everyday life - Eliezer Yudkowsky
Humean degree of freedom A concept includes 'Humean degrees of freedom' when the intuitive borders of the human version of that concept depend on our values, making that concept less natural for AIs to learn. - Eliezer Yudkowsky
Hypercomputer Some formalisms demand computers larger than the limit of all finite computers - Eliezer Yudkowsky
I often wait to see how much other people will donate to a fundraiser before donating myself. - Alexei Andreev
IRL and VOI Consider the following straightforward algorithm based on inverse reinforcement learning: - Given… - Paul Christiano
ISIS will not continue to exist as a state entity in Iraq/Syria by end of 2017 - Alexei Andreev
Ideal target The 'ideal target' of a meta-utility function is the value the ground-level utility function would take on if the agent updated on all possible evidence; the 'true' utilities under moral uncertainty. - Eliezer Yudkowsky
Ideals are the same thing as kernels of ring homomorphisms In ring theory, the notion of "[ideal\_ring\_theory ideal]" corresponds precisely with the notion o… - Patrick Stevens
Identifying ambiguous inductions What do a "red strawberry", a "red apple", and a "red cherry" have in common that a "yellow carrot" doesn't? Are they "red fruits" or "red objects"? - Eliezer Yudkowsky
Identifying causal goal concepts from sensory data If the intended goal is "cure cancer" and you show the AI healthy patients, it sees, say, a pattern of pixels on a webcam. How do you get to a goal concept *about* the real patients? - Eliezer Yudkowsky
Identity element An element in a set with a binary operation that leaves every element unchanged when used as the other operand. - Joe Zeng
Ideological Turing test Can you explain the opposing position well enough that people can't tell whether you or a real advocate of that position created the explanation? - Eliezer Yudkowsky
If CFAR suffered negative branding due to AI risk focus, it is possible to spin out a new program with the same people and avoid brand damage. - Timothy Chu
If EA leaders with similar values disagree about how the EA movement should be branded, then they should discuss in detail the subquestions that would cause them to change their minds if they have not already done so. - Ryan Carey
If they spent 100x longer deciding where to donate, then most effective altruists would choose targets with much higher expected impact. Does analysis help? - Ryan Carey
If we can’t lie to others, we will lie to ourselves - Eric Rogstad
If you want to make a task fun you will need to craft and combine different feelings with care. - Sarah Wolf
Iff If and only if... - Alexei Andreev
Ignorance prior Key equations for quantitative Bayesian problems, describing exactly the right shape for what we believed before observation. - Eliezer Yudkowsky
Image (of a function) The image $\operatorname{im}(f)$ of a function $f : X \to Y$ is the set of all possible outputs of $… - Nate Soares
Image of the identity under a group homomorphism is the identity All group homomorphisms preserve the identity. - Patrick Stevens
Image requested An editor has requested an image for this page. - Eric Bruylant
Imitation and justification Suppose that I am training an AI system to play Go. One approach is to have the AI observe human m… - Paul Christiano
Imitation-based agent An AI meant to imitate the behavior of a reference human as closely as possible. - Eliezer Yudkowsky
Immediate goods One of the potential views on 'value' in the value alignment problem is that what we should want fro… - Eliezer Yudkowsky
Implementing our considered judgment Suppose I had a very powerful prediction algorithm. How might I use this algorithm to build a smar… - Paul Christiano
Implicit consequentialism Consider a machine that does exactly what its user [would tell it to do](https://arbital.com/p/1tj?t… - Paul Christiano
Improve comments by tagging claims Comment sections are more important for discourse than I thought. They can be improved by explicitly tagging an article's main claims as anchors for discussion. - Benjamin Hoffman
In 2017 SSC will get fewer hits than in 2016 - Alexei Andreev
In 2017 at least one SSC post will have more than 100,000 hits - Alexei Andreev
In 2017 there will be no major intifada in Israel (ie > 250 Israeli deaths, but not in Cast Lead style war) - Alexei Andreev
In 2017, Assad will remain President of Syria - Alexei Andreev
In 2017, EMDrive is launched into space and testing is successfully begun - Alexei Andreev
In 2017, Israel will not get in a large-scale war (ie >100 Israeli deaths) with any Arab state - Alexei Andreev
In 2017, North Korea’s government will survive the year without large civil war/revolt - Alexei Andreev
In 2017, Trump administration will not initiate extra prosecution of Hillary Clinton - Alexei Andreev
In 2017, US does not publicly and explicitly disavow One China policy - Alexei Andreev
In 2017, US does not withdraw from large trade org like WTO or NAFTA - Alexei Andreev
In 2017, US lifts at least half of existing sanctions on Russia - Alexei Andreev
In 2017, US will not get involved in any new major war with death toll of > 100 US soldiers - Alexei Andreev
In 2017, Ukraine will neither break into all-out war or get neatly resolved - Alexei Andreev
In 2017, a significant number of believers will not become convinced EMDrive doesn’t work - Alexei Andreev
In 2017, a significant number of skeptics will not become convinced EMDrive works - Alexei Andreev
In 2017, construction on Mexican border wall (beyond existing barriers) begins - Alexei Andreev
In 2017, no terrorist attack in any First World country will kill > 100 people - Alexei Andreev
In 2017, no terrorist attack in the USA will kill > 100 people - Alexei Andreev
In 2017, there will be no major civil war in Middle Eastern country not already experiencing a major civil war at the beginning of 2017 - Alexei Andreev
In a principal ideal domain, "prime" and "irreducible" are the same Principal ideal domains have a very useful property that we don't need to distinguish between the informal notion of "prime" (i.e. "irreducible") and the formal notion. - Patrick Stevens
In defense of maximization I’ve been thinking about [AI systems that take actions their users would most approve of](https://… - Paul Christiano
In notation There's a weird E-looking symbol called \in in LaTeX. What does it mean? - Qiaochu Yuan
In order to have a shared conversation, it would help to have a Schelling set of posts. - Eric Rogstad
In order to think accumulatively we must have a shared conversation. - Eric Rogstad
Index two subgroup of group is normal An easy (though not very widely applicable) criterion for a subgroup to be normal. - Patrick Stevens
Indirect decision theory In which I argue that understanding decision theory can be delegated to AI. ### Indirect normativit… - Paul Christiano
Inductive prior Some states of pre-observation belief can learn quickly; others never learn anything. An "inductive prior" is of the former type. - Eliezer Yudkowsky
Information Information is a measure of how much a message grants an observer the ability to predict the world.… - Nate Soares
Information theory The study (and quantificaiton) of information, and its communication and storage. - Nate Soares
Informed oversight Incentivize a reinforcement learner that's less smart than you to accomplish some task - Jessica Taylor
Infrahuman, par-human, superhuman, efficient, optimal A categorization of AI ability levels relative to human, with some gotchas in the ordering. E.g., in simple domains where humans can play optimally, optimal play is not superhuman. - Eliezer Yudkowsky
Injective function A Function $f: X \to Y$ is *injective* if it has the property that whenever $f(x) = f(y)$, it is the… - Patrick Stevens
Instrumental What is "instrumental" in the context of Value Alignment Theory? - Eliezer Yudkowsky
Instrumental convergence Some strategies can help achieve most possible simple goals. E.g., acquiring more computing power or more material resources. By default, unless averted, we can expect advanced AIs to do that. - Eliezer Yudkowsky
Instrumental goals are almost-equally as tractable as terminal goals Getting the milk from the refrigerator because you want to drink it, is not vastly harder than getting the milk from the refrigerator because you inherently desire it. - Eliezer Yudkowsky
Instrumental pressure A consequentialist agent will want to bring about certain instrumental events that will help to fulfill its goals. - Eliezer Yudkowsky
Integer An **integer** is a Number that can be represented as either a Natural number or its [-additive\_inv… - Michael Cohen
Integers: Intro (Math 0) The integers are the whole numbers extended into the negatives. - Joe Zeng
Integral domain An integral domain is a ring where the only way to express zero as a product is by having zero as one of the terms. - Patrick Stevens
Intelligence explosion What happens if a self-improving AI gets to the point where each amount x of self-improvement triggers >x further self-improvement, and it stays that way for a while. - Eliezer Yudkowsky
Intended goal Definition. An "intended goal" refers to the intuitive intention in the mind of a human programmer … - Eliezer Yudkowsky
Intension vs. extension "Red is a light with a wavelength of 700 nm" vs. "Look at this red apple, red car, and red cup." - Eliezer Yudkowsky
Intentional Communities wiki pages A categorized, handpicked list of articles relevant to the Accelerator project - Toon Alfrink
Interest in mathematical foundations in Bayesianism "Want" this requisite if you prefer to see extra information about the mathematical foundations in Bayesianism. - Eliezer Yudkowsky
Interpretations of "probability" What does it *mean* to say that a fair coin has a 50% probability of coming up heads? - Nate Soares
Interruptibility A subproblem of corrigibility under the machine learning paradigm: when the agent is interrupted, it must not learn to prevent future interruptions. - Eliezer Yudkowsky
Intersection The intersection of two sets is the set of elements they have in common - M Yass
Intradependent encoding An encoding $E(m)$ of a message $m$ is intradependent if the fact that $E(m)$ encodes $m$ can be de… - Nate Soares
Intradependent encodings can be compressed Given an encoding scheme $E$ which gives an Intradependent encoding of a message $m,$ we can in prin… - Nate Soares
Intro to Number Sets An introduction to number sets for people who have no idea what a number set is. - Joe Zeng
Introduction to Bayes' Rule odds form This is an arc that includes just enough content to teach about Bayes's Rule odds form. - Alexei Andreev
Introduction to Bayes' rule: Odds form Bayes' rule is simple, if you think in terms of relative odds. - Eliezer Yudkowsky
Introduction to Effective Altruism Effective altruism (EA) means using evidence and reason to take actions that help others as much as … - Aaron Gertler
Introduction to Logical Decision Theory for Analytic Philosophers Why "choose as if controlling the logical output of your decision algorithm" is the most appealing candidate for the principle of rational choice. - Eliezer Yudkowsky
Introduction to Logical Decision Theory for Computer Scientists 'Logical decision theory' from a math/programming standpoint, including how two agents with mutual knowledge of each other's code can cooperate on the Prisoner's Dilemma. - Eliezer Yudkowsky
Introduction to Logical Decision Theory for Economists An introduction to 'logical decision theory' and its implications for the Ultimatum Game, voting in elections, bargaining problems, and more. - Eliezer Yudkowsky
Introductory Bayesian problems Bayesian problems to try to solve yourself, before beginning to learn about Bayes' rule. - Eliezer Yudkowsky
Introductory guide to logarithms Welcome to the Arbital introduction to logarithms! In modern education, logarithms are often mention… - Nate Soares
Intution pump In philosophy, a metaphor or visualization used to shove the listener's intuition in a particular direction. - Eliezer Yudkowsky
Inverse function The inverse of a function returns an input of the original function when fed the original's corresponding output. - Michael Cohen
Invisible background fallacies Universal laws also apply to objects and ideas that may fade into the invisible background. Reasoning as if these laws didn't apply to less obtrusive concepts is a type of fallacy. - Eliezer Yudkowsky
Irrational number Real numbers that are not rational numbers - Joe Zeng
Irreducible element (ring theory) This is the appropriate abstraction of the concept of "prime number" to general rings. - Patrick Stevens
Irrelevant nitpicks are an important problem in comment sections on sites such as LessWrong. Source of claim: Improve comments by tagging claims by Benjamin Hoffman - Stephanie Zolayvar
Is Eric's music better than Steph's? This is a sample debate topic. - Eric Rogstad
Isomorphism A morphism between two objects which describes how they are "essentially equivalent" for the purposes of the theory under consideration. - Mark Chimes
Isomorphism: Intro (Math 0) Things which are basically the same, except for some stuff you don't care about. - Mark Chimes
It's better to donate now rather than later. - Alexei Andreev
It's better to give $1000 to one person one time than to lend it out through microloans and then, as the money's repaid, keep relending it to other people indefinitely A claim about microloans. - Alexei Andreev
It's easier to make scientific progress in countries with fewer regulations. - Alexei Andreev
It's good for GiveWell and Good Ventures to crowd out donors by their donations. - Alexei Andreev
Join and meet Let $\langle P, \leq \rangle$ be a poset, and let $S \subseteq P$. The **join** of $S$ in $P$, deno… - Kevin Clancy
Join and meet: Examples A union of sets and the least common multiple of a set of natural numbers can both be viewed as join… - Kevin Clancy
Join and meet: Exercises Try these exercises to test your knowledge of joins and meets. Tangled up -------------------- !… - Kevin Clancy
Joint probability The notation for writing the chance that both X and Y are true. - Eliezer Yudkowsky
Joint probability distribution A probability distribution over the collection of joint configurations of all the variables you care about. - Tsvi BT
Joint probability distribution: (Motivation) coherent probabilities If you don't use joint probability distributions, none of your probabilities will make any sense. So, yeah, use joint probability distributions. - Tsvi BT
Just a requisite A tag for nodes that just act as part of Arbital's requisite system - Eliezer Yudkowsky
Keith Ellison will be chosen as new DNC chair in 2017 - Alexei Andreev
Kernel of group homomorphism The kernel of a Group homomorphism $f: G \to H$ is the collection of all elements $g$ in $G$ such th… - Patrick Stevens
Kernel of ring homomorphism The kernel of a ring homomorphism is the collection of things which that homomorphism sends to 0. - Patrick Stevens
Kickstarter project is a better tool for fundraising a threshold amount of money to start an EA project than a donor charity - Alexei Andreev
Knowing your audience A brief introduction to the concepts of assessment and pedagogical content knowledge - Duncan Sabien
Known-algorithm non-self-improving agent Possible advanced AIs that aren't self-modifying, aren't self-improving, and where we know and understand all the component algorithms. - Eliezer Yudkowsky
Kripke model The semantics of modal logic - Jaime Sevilla Molina
LaTeX **Placeholder** - Eric Bruylant
Lagrange theorem on subgroup size Lagrange's Theorem is an important restriction on the sizes of subgroups of a finite group. - Patrick Stevens
Lagrange theorem on subgroup size: Intuitive version Lagrange's theorem strongly restricts the size a subgroup of a group can be. - Patrick Stevens
Lambda calculus A minimal, inefficient, and hard-to-read, but still interesting and useful, programming language. - Dylan Hendrickson
Laplace's Rule of Succession Suppose you flip a coin with an unknown bias 30 times, and see 4 heads and 26 tails. The Rule of Succession says the next flip has a 5/32 chance of showing heads. - Eliezer Yudkowsky
Lattice (Order Theory) A poset that is closed under binary joins and meets. - Kevin Clancy
Lattice: Examples Here are some additional examples of lattices. $\newcommand{\nsubg}{\mathcal N \mbox{-} Sub~G}$ A f… - Kevin Clancy
Lattice: Exercises Try these exercises to test your knowledge of lattices. ## Distributivity Does the lattice meet op… - Kevin Clancy
Law of syllogism Deriving something from the conclusion of another thing. - Jeremy Perret
Learn policies or goals? I’ve [recently proposed](https://arbital.com/p/1t7/approval_directed_agents) training agents to ma… - Paul Christiano
Learning and logic In most machine learning tasks, the learner maximizes a concrete, empirical performance measure: i… - Paul Christiano
Learning representations Many AI systems form internal representations of their current environment or of particular data. Pr… - Olivia Schaefer
Learning representations Many AI systems form internal representations of their current environment or of particular data. Pr… - Paul Christiano
Least common multiple The **least common multiple (LCM)** of two positive natural numbers a, b is the smallest natural … - Johannes Schmitt
Left cosets are all in bijection The left cosets of a subgroup in a parent group are all the same size. - Patrick Stevens
Left cosets partition the parent group In a group, every element has a unique coset in which it lies, allowing us to compress some of the information about the group. - Patrick Stevens
Less Wrong A community blog devoted to refining the art of human rationality. - Alexei Andreev
Less Wrong renaissance attempt will seem less (rather than more) successful by end of 2017 - Alexei Andreev
Libya will remain a mess in 2017 - Alexei Andreev
Life in logspace The log lattice hints at the reason that engineers, scientists, and AI researchers find logarithms s… - Nate Soares
Likelihood "Likelihood", when speaking of Bayesian reasoning, denotes *the probability of an observation, sup… - Nate Soares
Likelihood function Let's say you have a piece of evidence $e$ and a set of hypotheses $\mathcal H.$ Each $H_i \in \math… - Nate Soares
Likelihood functions, p-values, and the replication crisis What's the whole Bayesian-vs.-frequentist debate about? - Eliezer Yudkowsky
Likelihood notation The likelihood of a piece of evidence $e$ according to a hypothesis $H,$ known as "the likelihood of… - Nate Soares
Likelihood ratio Given a piece of evidence $e$ and two hypothsese $H_i$ and $H_j,$ the likelihood ratio between them… - Nate Soares
Limited AGI Task-based AGIs don't need unlimited cognitive and material powers to carry out their Tasks; which means their powers can potentially be limited. - Eliezer Yudkowsky
Linear algebra The study of [linear\_transformation linear transformations] and vector spaces. - Nate Soares
Linguistic conventions in value alignment How and why to use precise language and words with special meaning when talking about value alignment. - Eliezer Yudkowsky
Link glossary pages for overloaded words If your subject is using what sound like ordinary-language words in a special sense, create a glossa… - Eliezer Yudkowsky
List Meta tags for pages that are basically lists. - Alexei Andreev
List A list is an ordered collection of objects, such as `[0, 1, 2, 3]` or `["red", "blue", 0, "shoe"]`. … - Nate Soares
List of Eliezer's current most desired fixes and features A place for Eliezer to note down his current list of personally-wanted features for editing and writing. - Eliezer Yudkowsky
List: value-alignment subjects Bullet point list of core VAT subjects. - Eliezer Yudkowsky
Locale Topology - but right - Adele Lopez
Location on the comments-links continuum is an important aspect of discourse design. Source of claim: Improve comments by tagging claims by Benjamin Hoffman - Stephanie Zolayvar
Location on the comments-links continuum is an important aspect of discourse design. - Benjamin Hoffman
Log as generalized length To estimate the log (base 10) of a number, count how many digits it has. - Nate Soares
Log as the change in the cost of communicating When interpreting logarithms as a generalization of the notion of "length" and as digit exchange rat… - Nate Soares
Log base infinity There is no log base infinity, but if there were, it would send everything to zero - Nate Soares
Logarithm The logarithm base $b$ of a number $n,$ written $\log_b(n),$ is the answer to the question "how man… - Nate Soares
Logarithm base 1 There is no log base 1. - Nate Soares
Logarithm tutorial overview The logarithm tutorial covers the following six subjects: 1. What are logarithms? 2. Logarithms as… - Nate Soares
Logarithm: Examples $\log_{10}(100)=2.$ $\log_2(4)=2.$ $\log_2(3)\approx 1.58.$ (TODO) - Nate Soares
Logarithm: Exercises Without using a calculator: What is $\log_{10}(4321)$? What integer is it larger than, what integer … - Nate Soares
Logarithmic identities - [ Inversion of exponentials]: $b^{\log_b(n)} = \log_b(b^n) = n.$ - [ Log of 1 is 0]: $\log_b(1) … - Nate Soares
Logarithms invert exponentials The function $\log_b(\cdot)$ inverts the function $b^{(\cdot)}.$ In other words, $\log_b(n) = x$ imp… - Nate Soares
Logic Logic is the study of correct arguments. - Erik Istre
Logical Induction (incomplete) The theoretically ideal algorithm for bounded reasoning with lots of computational resources - Alex Appel
Logical Inductor Notation and Definitions A handy guide to the blizzard of notation in the Logical Induction Paper - Alex Appel
Logical Uncertainty The study of resource-bounded inference. - Alex Appel
Logical decision theories Root page for topics on logical decision theory, with multiple intros for different audiences. - Eliezer Yudkowsky
Logical game Game's mathematical structure at its purest form. - Eliezer Yudkowsky
Logical system Logical systems (a.k.a. formal systems) are mathematical abstractions that aim to capture the notion… - Jaime Sevilla Molina
Logistic function A monotonic function from the real numbers to the open unit interval. - Joe Zeng
Look where I'm pointing, not at my finger When trying to communicate the concept "glove", getting the AGI to focus on "gloves" rather than "my user's decision to label something a glove" or "anything that depresses the glove-labeling button". - Eliezer Yudkowsky
Low impact The open problem of having an AI carry out tasks in ways that cause minimum side effects and change as little of the rest of the universe as possible. - Eliezer Yudkowsky
Low-speed explanation Use this tag to indicate that a page offers a relatively slower, more gentle, or more wordy explanat… - Eric Rogstad
Lt. Gilbert S. Daniels and the myth of averages There is no such thing as an average pilot - Duncan Sabien
Löb's theorem Löb's theorem - Jaime Sevilla Molina
Löb's theorem and computer programs The close relationship between [ logic and computability] allows us to frame Löb's theorem in terms … - Jaime Sevilla Molina
Löbstacle Imagine you have an artificial intelligence $D1$ who uses a logical [ knowledge base] and a certain … - Jaime Sevilla Molina
Machine Intelligence Research Institute Where to work if you're doing more formal or technical work on AI safety, of a kind not easily milked for publications. - Alexei Andreev
Malcolm Ocean's Arbitlog Not actually a thing. Visit [malcolmocean.com](http://malcolmocean.com/). - Malcolm Ocean
Mapsto notation There's an arrow called \mapsto in LaTeX. What does it mean? - Qiaochu Yuan
Marine Le Pen will not be elected President of France in 2017 - Alexei Andreev
Market monetarism Domain for school of macroeconomic thought. - Alexei Andreev
Math 0 Are you not actively bad at math, nor traumatized about math? - Eliezer Yudkowsky
Math 1 Is math sometimes fun for you, and are you not anxious if you see a math puzzle you don't know how to solve? - Eliezer Yudkowsky
Math 2 Do you work with math on a fairly routine basis? Do you have little trouble grasping abstract structures and ideas? - Eliezer Yudkowsky
Math 2 example statements If you can read these formulas, you're in Math 2! - Joe Zeng
Math 3 Can you read the sort of things that professional mathematicians read, aka LaTeX formulas with a minimum of explanation? - Eliezer Yudkowsky
Math 3 example statements If you can read these formulas, you're in Math 3! - Joe Zeng
Math playpen Playpen page for Math domain - Alexei Andreev
Math style guidelines Stylistic conventions specific to pages about math. - Dylan Hendrickson
Mathematical induction Proving a statement about all positive integers by knocking them down like dominoes. - Douglas Weathers
Mathematical object **Placeholder** - Eric Bruylant
Mathematics Mathematics is the study of numbers and other ideal objects that can be described by axioms. - Eliezer Yudkowsky
Mechanical Turk (example) The 19th-century chess-playing automaton known as the Mechanical Turk actually had a human operator inside. People at the time had interesting thoughts about the possibility of mechanical chess. - Eliezer Yudkowsky
Meeting your audience Framing explanations, overcoming inferential distance, and effective differentiation - Duncan Sabien
Meta (Arbital Labs) Tag for meta discussion in Arbital Labs - Eric Rogstad
Meta tags What are meta tags and when to use them? - Eliezer Yudkowsky
Meta tags which request an edit to the page Tags that mean your page should be edited. - Stephanie Zolayvar
Meta tags which suppress a page from being featured This parent collects all meta tags which will prevent a page from being listed in the featured secti… - Alexei Andreev
Meta-rules for (narrow) value learning are still unsolved We don't currently know a simple meta-utility function that would take in observation of humans and spit out our true values, or even a good target for a Task AGI. - Eliezer Yudkowsky
Meta-utility function Preference frameworks built out of simple utility functions, but where, e.g., the 'correct' utility function for a possible world depends on whether a button is pressed. - Eliezer Yudkowsky
Metaethics Metaethics asks "What kind of stuff is goodness made of?" (or "How would we compute goodness?") rather than "Which particular policies or outcomes are good or not-good?" - Eliezer Yudkowsky
Methodology of foreseeable difficulties Building a nice AI is likely to be hard enough, and contain enough gotchas that won't show up in the AI's early days, that we need to foresee problems coming in advance. - Eliezer Yudkowsky
Methodology of unbounded analysis What we do and don't understand how to do, using unlimited computing power, is a critical distinction and important frontier. - Eliezer Yudkowsky
Metric A metric is a function that defines a distance between elements in a set and follows some basic rules. - Bryce Woodworth
Mic-Ra-finance and the illusion of control This post discusses the following claims: * [claim([6th])] * [claim([6tk])] * [claim([6tl])] - Alexei Andreev
Microlending The practice of giving microloans, which are small loans that are issued by individuals. - Alexei Andreev
Mid Term Such great mid-term - Alex Foster
Mild optimization An AGI which, if you ask it to paint one car pink, just paints one car pink and doesn't tile the universe with pink-painted cars, because it's not trying *that* hard to max out its car-painting score. - Eliezer Yudkowsky
Mimicry and meeting halfway I’ve talked recently about two different model-free decision procedures: - At each step, pick the … - Paul Christiano
Mind design space is wide Imagine all human beings as one tiny dot inside a much vaster sphere of possibilities for "The space of minds in general." It is wiser to make claims about *some* minds than *all* minds. - Eliezer Yudkowsky
Mind projection fallacy Uncertainty is in the mind, not in the environment; a blank map does not correspond to a blank territory. In general, the territory may have a different ontology from the map. - Eliezer Yudkowsky
Mindcrime Might a machine intelligence contain vast numbers of unhappy conscious subprocesses? - Eliezer Yudkowsky
Mindcrime: Introduction The more predictive accuracy we want from a model, the more detailed the model becomes. A very roug… - Eliezer Yudkowsky
Minimality principle The first AGI ever built should save the world in a way that requires the least amount of the least dangerous cognition. - Eliezer Yudkowsky
Missing the weird alternative People might systematically overlook "make tiny molecular smileyfaces" as a way of "producing smiles", because our brains automatically search for high-utility-to-us ways of "producing smiles". - Eliezer Yudkowsky
Modal combat Modal combat - Jaime Sevilla Molina
Modal logic The logic of boxes and bots. - Jaime Sevilla Molina
Modalized modal sentence A [ modal sentence] $A$ is said to be **modalized** in $p$ if every occurrence of $p$ happens within… - Jaime Sevilla Molina
Modeling AI control with humans I’ve been trying to build an aligned AI out of reward-maximizing modules. A successful scheme could … - Paul Christiano
Modeling distant superintelligences The several large problems that might occur if an AI starts to think about alien superintelligences. - Eliezer Yudkowsky
Modular arithmetic Addition as traveling around a circle, instead of along a line. - Malcolm McCrimmon
Modus tollens Deriving a negation from another negation - Jeremy Perret
Molecular basis of the potential of vitamin D to prevent cancer Theoretical meta-analysis Link: http://www.researchgate.net/publication/5812584_Molecular_basis_of_… - Alexei Andreev
Monoid A monoid $M$ is a pair $(X, \diamond)$ where $X$ is a [set\_theory\_set set] and $\diamond$ is an [a… - Nate Soares
Monotone function An order-preserving map between posets. - Kevin Clancy
Monotone function: examples Here are some examples of monotone functions. A cunning plan -------- There's a two-player game ca… - Kevin Clancy
Monotone function: exercises Try these exercises and become a *deity* of monotonicity. Monotone composition ----- Let $P, Q$, … - Kevin Clancy
Moral hazards in AGI development "Moral hazard" is when owners of an advanced AGI give in to the temptation to do things with it that the rest of us would regard as 'bad', like, say, declaring themselves God-Emperor. - Eliezer Yudkowsky
Moral uncertainty A meta-utility function in which the utility function as usually considered, takes on different values in different possible worlds, potentially distinguishable by evidence. - Eliezer Yudkowsky
More about Arbital Lots more information about Arbital vision. - Alexei Andreev
More comments and claims should be driven by cruxes. - Alexei Andreev
Morphism A morphism is the abstract representation of a relation between mathematical objects. Usually, it i… - Jaime Sevilla Molina
Most complex things are not very compressible We can't *prove* it's impossible, but it would be *extremely surprising* to discover a 500-state Turing machine that output the exact text of "Romeo and Juliet". - Eliezer Yudkowsky
Moving outside of the US will likely result in cheaper accommodations and living costs. - Alexei Andreev
Multiple stage fallacy You can make an arbitrary proposition sound very improbable by observing how it seemingly requires X, Y, and Z. This didn't work for Nate Silver forecasting the Trump nomination. - Eliezer Yudkowsky
Multiplication multiiplication - Travis Rivera
Multiplication of rational numbers (Math 0) "Multiplication" is the idea of "now do the same as you just did, but instead of doing it to one apple, do it to some other number". - Patrick Stevens
Mutual information http://colah.github.io/posts/2015-09-Visual-Information/ - Curtis SerVaas
Mutually exclusive and exhaustive The condition needed for probabilities to sum to 1 - Eliezer Yudkowsky
NGDP level targeting Central banks ought to regularize the total flow of money to increase at a predictable 5% rate per year, and doing this would solve a surprising number of other problems. - Eliezer Yudkowsky
Nate's ruminations These posts are a mirror of posts on the blog [MindingOurWay.com](mindingourway.com) which pertain t… - Nate Soares
Natural language understanding of "right" will yield normativity What will happen if you tell an advanced agent to do the "right" thing? - Eliezer Yudkowsky
Natural number The numbers we use to count: 0, 1, 2, 3, ... - Jaime Sevilla Molina
Natural numbers: Intro to Number Sets Natural numbers are the numbers we use to count in everyday life. - Joe Zeng
Nearest unblocked strategy If you patch an agent's preference framework to avoid an undesirable solution, what can you expect to happen? - Eliezer Yudkowsky
Necessary conditions for expertise: the P-I-F-T method A domain-general method to help you assess whether a person has the necessary conditions for expert in a given domain. - Tyler Alterman
Needs accessible summary This page needs a summary for a less technical audience. - Eric Bruylant
Needs alias This page needs a custom alias for the url. - Eric Bruylant
Needs brief summary Meta tag for pages which need a brief summary. - Eric Bruylant
Needs cleanup Meta tag to indicate a page needs cleanup, such as fixing spelling, grammar, typos, stylistic issues, or tone. - Eric Bruylant
Needs clickbait This page does not have clickbait (a short teaser for the page displayed on various lists). Feel free to add it! - Eric Bruylant
Needs examples This page would benefit from more examples of the concept it teaches. - Eric Bruylant
Needs exercises Add this tag to a page which doesn't have enough exercises. - Alexei Andreev
Needs image Meta tag for pages which would be improved by having images - Eric Bruylant
Needs lenses This page has only a technical introduction. If you're able to, please help by adding an intuitive explanation! - Nate Soares
Needs links This page could do with more greenlinks. - Eric Bruylant
Needs motivation A tag for text that could benefit from some motivating statements. Why is the reader interested in w… - Eric Rogstad
Needs parent This page is not attached to an appropriate parent page. If you know where it should go, please help categorize it! - Eric Bruylant
Needs requisites This page has important requisites which are not listed. If you know what they are, you could help add them! - Eric Bruylant
Needs splitting by mastery This page seems to serve multiple different mastery levels, and may benefit from being split into separate lenses. - Eric Bruylant
Needs summary This page does not have a summary which provides an informative overview of the page's primary topic. - Alexei Andreev
Needs technical summary Meta tag for pages which need a technical summary. - Eric Bruylant
Needs work Meta tag for pages which need content improvement. - Eric Bruylant
Negation of propositions The proposition that is false if another one is true and vice-versa. - Jeremy Perret
Neutral genie metaphor Definition. A neutral-genie metaphor is an attempt to illustrate a possible formal problem via an in… - Alexei Andreev
Newcomb's Problem There are two boxes in front of you, Box A and Box B. You can take both boxes, or only Box B. Box A contains $1000. Box B contains $1,000,000 if and only if Omega predicted you'd take only Box B. - Eliezer Yudkowsky
Newcomblike decision problems Decision problems in which your choice correlates with something other than its physical consequences (say, because somebody has predicted you very well) can do weird things to some decision theories. - Eliezer Yudkowsky
Niceness is the first line of defense The *first* line of defense in dealing with any partially superhuman AI system advanced enough to possibly be dangerous is that it does not *want* to hurt you or defeat your safety measures. - Eliezer Yudkowsky
Nick Bostrom Nick Bostrom, secretly the inventor of Friendly AI - Eliezer Yudkowsky
Nick Bostrom's book Superintelligence The current best book-form introduction to AI alignment theory. - Eliezer Yudkowsky
No agreement will be reached on "two-speed EU" - Alexei Andreev
No country currently in Euro or EU will announce new plan to leave in 2017 - Alexei Andreev
No exchange of fire over "tiny stupid islands" in 2017 - Alexei Andreev
No major earthquake (>10,000 deaths) in the world in 2017 - Alexei Andreev
No major earthquake (>100 deaths) in US in 2017 - Alexei Andreev
No major war in Asia (with >100 Chinese, Japanese, South Korean, and American deaths combined) over "tiny stupid islands" in 2017 - Alexei Andreev
No serious impeachment proceedings are active against Trump in 2017 - Alexei Andreev
No-Free-Lunch theorems are often irrelevant There's often a theorem proving that some problem has no optimal answer across every possible world. But this may not matter, since the real world is a special case. (E.g., a low-entropy universe.) - Eliezer Yudkowsky
Non-adversarial principle At no point in constructing an Artificial General Intelligence should we construct a computation that tries to hurt us, and then try to stop it from hurting us. - Eliezer Yudkowsky
Non-standard terminology A tag for terminology that is Arbital-specific, Arbital-originated, or just not very common outside … - Nate Soares
Nonperson predicate If we knew which computations were definitely not people, we could tell AIs which programs they were definitely allowed to compute. - Eliezer Yudkowsky
Normal subgroup Normal subgroups are subgroups which are in some sense "the same from all points of view". - Patrick Stevens
Normal system of provability logic Between the modal systems of provability, the normal systems distinguish themselves by exhibiting ni… - Jaime Sevilla Molina
Normalization (probability) That thingy we do to make sure our probabilities sum to 1, when they should sum to 1. - Eliezer Yudkowsky
Note on 1x1 Convolutions what's the purpose? - Alto Clef
Noticing Preferences - Nicolas Bourbaki
Now I am become Life, the protector of worlds In which Arbital is brought forth into the world. - Alexei Andreev
Number An abstract object that expresses quantity or value of some sort. - Joe Zeng
Object identity via interactions If we think of objects as opaque "black boxes", how can we tell whether two objects are different? By looking at how they interact with other objects! - Patrick Stevens
Object-level vs. indirect goals Difference between "give Alice the apple" and "give Alice what she wants". - Eliezer Yudkowsky
Octalysis Framework ![enter image description here](https://i.ibb.co/dbThDWX/download.png) In the Octalysis Framework %… - Sarah Wolf
Octalysis Framework is useful for identifying what game mechanics will lead to different feelings - Sarah Wolf
Odds Odds express a relative probability. - Eliezer Yudkowsky
Odds form to probability form The odds form of Bayes' rule works for any two hypotheses $H_i$ and $H_j,$ and looks like this: $$\… - Nate Soares
Odds: Introduction What's the difference between probabilities and odds? Why is a 20% probability of success equivalent to 1 : 4 odds favoring success? - Nate Soares
Odds: Refresher A quick review of the notations and mathematical behaviors for odds (e.g. odds of 1 : 2 for drawing a red ball vs. green ball from a barrel). - Nate Soares
Odds: Technical explanation Formal definitions, alternate representations, and uses of odds and odds ratios (like a 1 : 2 chance of drawing a red ball vs. green ball from a barrel). - Alexei Andreev
Of arguments and wagers (In which I explore an unusual way of combining the two.) Suppose that Alice and Bob disagree, and … - Paul Christiano
Of simulations and inductive definitions _(Warning: weird.)_ Consider a simple AI system, named A, that carries out a task by predicting wha… - Paul Christiano
Oil will end 2017 higher than $50 a barrel - Alexei Andreev
Oil will end 2017 lower than $60 a barrel - Alexei Andreev
Omega (alien philosopher-troll) The entity that sets up all those trolley problems. An alien philosopher/troll imbued with unlimited powers, excellent predictive ability, and very odd motives. - Eliezer Yudkowsky
Omniment Nothing here yet.] Automatically generated page for "Omniment" group. If you are the owner, click … - Eric Rogstad
Omnipotence test for AI safety Would your AI produce disastrous outcomes if it suddenly gained omnipotence and omniscience? If so, why did you program something that *wants* to hurt you and is held back only by lacking the power? - Eliezer Yudkowsky
On heterogeneous objectives Eliezer Yudkowsky [has said](https://www.facebook.com/yudkowsky/posts/10153748345169228): > If you … - Paul Christiano
On the importance of Less Wrong, or another single conversational locus In this post, Anna Salamon talks about how Less Wrong used to a locus of discussion, and that it is… - Alexei Andreev
On the margin, effective altruist researchers and leaders should carry out more empirical investigation of strategic questions. Strategic question might include: * How can we shape the development of brain-computer interfaces? … - Ryan Carey
Online guarantees and AI control I’m interested in claims of the form: “If we had an AI that could do X well, then we could build a… - Paul Christiano
Ontology identification problem How do we link an agent's utility function to its model of the world, when we don't know what that model will look like? - Eliezer Yudkowsky
Ontology identification problem: Technical tutorial Technical tutorial for ontology identification problem. - Eliezer Yudkowsky
Open questions in life-planning What questions do the two models above not solve? - Ben Pace
Open subproblems in aligning a Task-based AGI Open research problems, especially ones we can model today, in building an AGI that can "paint all cars pink" without turning its future light cone into pink-painted cars. - Eliezer Yudkowsky
Operations in Set theory An operation in set theory is a Function of two sets, that returns a set. Common set operations inc… - M Yass
Operator An operation $f$ on a set $S$ is a function that takes some values from $S$ and produces a new value… - Nate Soares
Opinion page Opinion pages represent one position on a topic (often from a single author), and are not necessarily balanced or a reflection of consensus. - Eric Bruylant
Optimization and goals If we want to write a program that _doesn’t_ pursue a goal, we can have two kinds of trouble: 1. We… - Paul Christiano
Optimization daemons When you optimize something so hard that it crystalizes into an optimizer, like the way natural selection optimized apes so hard they turned into human-level intelligences - Eliezer Yudkowsky
Optimizing with comparisons I could [elicit a user’s approval](https://arbital.com/p/1w5) of an action _a_ by having them supply… - Paul Christiano
Oracle System designed to safely answer questions. - Eliezer Yudkowsky
Orbit-Stabiliser theorem: External Resources External resources on the Orbit-Stabiliser theorem. - Mark Chimes
Orbit-stabiliser theorem The Orbit-Stabiliser theorem tells us a lot about how a group acts on a given element. - Patrick Stevens
Order of a group The order $|G|$ of a group $G$ is the size of its underlying set. For example, if $G=(X,\bullet)$ an… - Nate Soares
Order of a group element Given an element $g$ of group $(G, +)$ (which henceforth we abbreviate simply as $G$), the order of … - Patrick Stevens
Order of operations Conventions used for disambiguating infix notation. - Joe Zeng
Order of rational operations (Math 0) Our shorthand for all the operations on rationals is very useful, but full of brackets; this is how to get rid of some of the brackets. - Patrick Stevens
Order relation A way of determining which elements of a set come "before" or "after" other elements. - Joe Zeng
Order theory The study of binary relations that are reflexive, transitive, and antisymmetic. - Kevin Clancy
Ordered field An ordered ring with division. - Joe Zeng
Ordered ring A ring with a total ordering compatible with its ring structure. - Dylan Hendrickson
Ordering of rational numbers (Math 0) How do we know if one lot of apples is "more apples" than another lot? - Patrick Stevens
Ordinary claims require ordinary evidence Extraordinary claims require extraordinary evidence, but ordinary claims *don't*. - Nate Soares
Organizations and people Comprehensive list of organizations and people relevant to navigating development of AGI. - Alexei Andreev
Organizations' utility curves for money are usually smooth (fundraiser milestones notwithstanding) - Eric Rogstad
Oropharyngeal cancer is a significant risk of HPV HPV can cause oral and pharyngeal cancer. The incidence of HPV-associated oropharyngeal cancer is ab… - Sarah Constantin
Orthogonality Thesis Will smart AIs automatically become benevolent, or automatically become hostile? Or do different AI designs imply different goals? - Eliezer Yudkowsky
Other-izing (wanted: new optimization idiom) Maximization isn't possible for bounded agents, and satisficing doesn't seem like enough. What other kind of 'izing' might be good for realistic, bounded agents? - Eliezer Yudkowsky
Our community has a shot at seriously helping with x-risk. - Eric Rogstad
Our community should relocate to Iceland. - Alexei Andreev
Our community should relocate to Japan. - Alexei Andreev
Our community should relocate to a country other than the US Claims with specific country proposals: * [claim([6v8])] * [claim([6v9])] Relevant claims: * [cla… - Alexei Andreev
Out of date Meta tag used when the page has a lot of information that's obsolete - Alexei Andreev
Outside view Taking the **outside view** (another name for reference class forecasting) means using an estimate b… - Alexei Andreev
P (Polynomial Time Complexity Class) P is the class of problems which can be solved by algorithms whose run time is bounded by a polynomial. - Eric Leese
P vs NP Is creativity purely mechanical? - Jaime Sevilla Molina
P vs NP: Arguments against P=NP Why we believe P and NP are different - Jaime Sevilla Molina
P-value The probability of observing the sample data we have _actually_ observed; the sauce behind significance testing. - Stephen Fox
Page's title should always be capitalized Vote "agree" if you think Arbital should enforce the first letter of a page title to always be capit… - Alexei Andreev
Paperclip A configuration of matter that we'd see as being worthless even from a very cosmopolitan perspective. - Eliezer Yudkowsky
Paperclip maximizer This agent will not stop until the entire universe is filled with paperclips. - Eliezer Yudkowsky
Parfit's Hitchhiker You are dying in the desert. A truck-driver who is very good at reading faces finds you, and offers to drive you into the city if you promise to pay $1,000 on arrival. You are a selfish rationalist. - Eliezer Yudkowsky
Partial function A partial function is one which "might not be defined everywhere one might expect it to be". - Patrick Stevens
Partially ordered set A set endowed with a relation that is reflexive, transitive, and antisymmetric. - Kevin Clancy
Patch resistance One does not simply solve the value alignment problem. - Eliezer Yudkowsky
Path targeting Don't say "We want this price to go up at 2%/year", say "We want this to be $1 in year 1, $1.02 in year 2, $1.04 in year 3" and don't change the rest of the path if you miss one year's target. - Eliezer Yudkowsky
Path to Acceleration (Back to Accelerator home) So, you know why we're doing this and what we're aiming for, a natural … - Eric Bruylant
Path: Insights from Bayesian updating A learning-path placeholder page for insights derived from the Bayesian rule for updating beliefs. - Eliezer Yudkowsky
Path: Multiple angles on Bayes's Rule A learning-path placeholder page for learning multiple angles on Bayes's Rule. - Eliezer Yudkowsky
Paul Christiano's AI control blog Speculations on the design of safe, efficient AI systems. - Paul Christiano
Peano Arithmetic A system for proving theorems about arithmetic, which is strong enough to include self-reference. - Patrick LaVictoire
People A category for human beings! - Eliezer Yudkowsky
Perfect rolling sphere If you don't understand something, start by assuming it's a perfect rolling sphere. - Eliezer Yudkowsky
Phenomenological Complexity Classes A phenomenological theory of differences in the complexity of minds-in-general. - G Gordon Worley
Philosophy A stub parent node to contain standard concepts, belonging to subfields of academic philosophy, that are being used elsewhere on Arbital. - Eliezer Yudkowsky
Pi Pi, usually written $π$, is a number equal to the ratio of a circle's [-circumference] to its [-diam… - Michael Cohen
Pi is irrational The number pi is famously not rational, in spite of joking attempts at legislation to fix its value at 3 or 22/7. - Patrick Stevens
Pigovian tax Taxation of negative externalities so that their producers have an incentive to cheaply reduce them - Silas Barta
Pivotal event Which types of AIs, if they work, can do things that drastically change the nature of the further game? - Eliezer Yudkowsky
Placeholder This is an empty page created for structural reasons (parent, requisite, or teaches). - Eric Bruylant
Playpen child asdf - Erictest Rogstadtest
Policy desiderata in the development of machine superintelligence Link to the paper by Nick Bostrom, Allan Dafoe, and Carrick Flynn. - Alexei Andreev
Politics Tag for political discussion in Arbital Labs - Eric Rogstad
Poset: Examples The standard $\leq$ relation on integers, the $\subseteq$ relation on sets, and the $|$ (divisibilit… - Kevin Clancy
Poset: Exercises Try these exercises to test your poset knowledge. # Corporate Ladder Imagine a company with five … - Kevin Clancy
Possible math pages A list of things which we may want math pages on - Eric Bruylant
Posterior probability What we believe, after seeing the evidence and doing a Bayesian update. - Eliezer Yudkowsky
Potential new users are confused by the goal of Arbital and how they can best contribute - Ted Sanders
Power set The power set is the collection of all subsets of a set - Daniel Satanove
Practicing Brevity Wanna save the world? Write better TLDRs. And spend more time respecting your reader's time. - Raymond Arnold
Predictions For 2017 Scott Alexander made 105 predictions for 2017. Most of them are not personal and are listed below. … - Alexei Andreev
Preemptive Learning One of the basic theorems of logical inductors, used to derive many other theorems that rely on "buy low, sell high" strategies. - Alex Appel
Preference framework What's the thing an agent uses to compare its preferences? - Eliezer Yudkowsky
Prime element of a ring Despite the name, "prime" in ring theory refers not to elements which are "multiplicatively irreducible" but to those such that if they divide a product then they divide some term of the product. - Patrick Stevens
Prime number The prime numbers are the "building blocks" of the counting numbers. - Patrick Stevens
Prime order groups are cyclic This is the first step on the road to classifying the finite groups. - Patrick Stevens
Primer on Infinite Series What does it mean to add things together forever? - Chris Holden
Principal ideal domain A principal ideal domain is a kind of ring, in which all ideals have a certain nice form. - Patrick Stevens
Principia Qualia: blueprint for a new cause area, consciousness research with an eye toward ethics and x-risk Claims discussed in this post: - [claim([6xd])] - [claim([6x4])] - [claim([6xf])] - Eric Rogstad
Principles in AI alignment A 'principle' of AI alignment is a very general design goal like 'understand what the heck is going on inside the AI' that has informed a wide set of specific design proposals. - Eliezer Yudkowsky
Prior A state of prior knowledge, before seeing information on a new problem. Potentially complicated. - Eliezer Yudkowsky
Prior probability What we believed before seeing the evidence. - Eliezer Yudkowsky
Prisoner's Dilemma You and an accomplice have been arrested. Both of you must decide, in isolation, whether to testify against the other prisoner--which subtracts one year from your sentence, and adds two to theirs. - Eliezer Yudkowsky
Probability The degree to which someone believes something, measured on a scale from 0 to 1, allowing us to do math to it. - Eliezer Yudkowsky
Probability distribution (countable sample space) A function assigning a probability to each point in the sample space. - Tsvi BT
Probability distribution: Motivated definition People keep writing things like P(sick)=0.3. What does this mean, on a technical level? - Nate Soares
Probability interpretations: Examples Consider evaluating, in June of 2016, the question: "What is the probability of Hillary Clinton wi… - Nate Soares
Probability notation for Bayes' rule The probability notation used in Bayesian reasoning - Eliezer Yudkowsky
Probability notation for Bayes' rule: Intro (Math 1) How to read, and identify, the probabilities in Bayesian problems. - Eliezer Yudkowsky
Probability theory The logic of science; coherence relations on quantitative degrees of belief. - Eliezer Yudkowsky
Problem of fully updated deference Why moral uncertainty doesn't stop an AI from defending its off-switch. - Eliezer Yudkowsky
Problem: safe AI from episodic RL In [a previous post](https://arbital.com/p/1tv?title=the-steering-problem), I posed the steering pr… - Paul Christiano
Processes of Rationality An idiosyncratic organization of rationality materials. - Nicolas Bourbaki
Product (Category Theory) How a product is characterized rather than how it's constructed - Mark Chimes
Product is unique up to isomorphism If something satisfies the universal property of the product, then it is uniquely specified by that property, up to isomorphism. - Patrick Stevens
Programmer Who is building these advanced agents? - Eliezer Yudkowsky
Programmer deception Programmer deception is when the AI's decision process leads it to optimize for an instrumental goal… - Eliezer Yudkowsky
Programming in Dependent Type Theory Working with simple types in Lean - Jack Gallagher
Project outline: Intro to the Universal Property Outline detailing all the work required for a proposed Arbital Project - Eric Rogstad
Project proposal: Complex numbers Project proposal for complex numbers - Alexei Andreev
Project proposal: Intro to numbers Should Arbital's first "project" be a guide to numbers? - Eric Rogstad
Project proposal: Intro to the Universal Property Proposal for one of the first Arbital Projects. - Patrick Stevens
Proof This page is just a proof, rather than a motivated explanation. - Eric Bruylant
Proof by contradiction Discover what 'reductio ad absurdum' means! - Jaime Sevilla Molina
Proof of Bayes' rule Proofs of Bayes' rule, with graphics - Eliezer Yudkowsky
Proof of Bayes' rule: Intro Proof of Bayes' rule, assuming you know the rule itself, and the notations for the quantities involved. - Eliezer Yudkowsky
Proof of Bayes' rule: Probability form Let $\mathbf H$ be a [random\_variable variable] in $\mathbb P$ for the true hypothesis, and let $H_… - Nate Soares
Proof of Gödel's first incompleteness theorem ##Weak form The weak Gödel's first incompleteness theorem states that every [ $\omega$-consistent] [… - Jaime Sevilla Molina
Proof of Löb's theorem Proving that I am Santa Claus - Jaime Sevilla Molina
Proof of Rice's theorem A standalone proof of Rice's theorem, including one surprising lemma. - Patrick Stevens
Proof technique **Placeholder** - Eric Bruylant
Proof that there are infinitely many primes Suppose there were finitely many primes. Then consider the product of all the primes plus 1... - Joe Zeng
Properties of the logarithm - $\log_b(x \cdot y) = \log_b(x) + \log_b(y)$ for any $b$, this is the defining characteristic of … - Nate Soares
Proportion A representation of a value as a fraction or multiple of another value. - Joe Zeng
Proposed A-Class Pages which have been proposed for A-Class status. - Eric Bruylant
Proposed B-Class Pages which have been proposed for B-Class status. - Eric Bruylant
Propositions Propositions are statements with a truth value. - Jeremy Perret
Provability logic Learn how to reason about provability! - Jaime Sevilla Molina
Provability predicate A provability predicate of a theory $T$ is a formula $P(x)$ with one free variable $x$ such that: … - Jaime Sevilla Molina
Proving too much If your argument could just as naturally be used to prove that Bigfoot exists and that Peano arithmetic is inconsistent, maybe it's an untrustworthy kind of argument. - Eliezer Yudkowsky
Psychologizing It's sometimes important to consider how other people might be led into error. But psychoanalyzing them is also dangerous! Arbital discussion norms say to explicitly note this as "psychologizing". - Eliezer Yudkowsky
Quality meta tags Meta tags which determine the page's quality. - Alexei Andreev
Querying the AGI user Postulating that an advanced agent will check something with its user, probably comes with some standard issues and gotchas (e.g., prioritizing what to query, not manipulating the user, etc etc). - Eliezer Yudkowsky
Questionnaire helper 1 Just a helper page to demonstrate Arbital's questionnaire features. - Alexei Andreev
Questionnaire helper 2 Just a helper page to demonstrate Arbital's questionnaire features. - Alexei Andreev
Questionnaire helper 3 Just a helper page to demonstrate Arbital's questionnaire features. - Alexei Andreev
Quine A computer program that prints (or does other computations to) its own source code, using indirect self-reference. - Patrick LaVictoire
Quotient by subgroup is well defined if and only if subgroup is normal Let $G$ be a Group and $N$ a Normal subgroup of $G$. Then we may define the *quotient group* $G/N$ t… - Patrick Stevens
Quotient group Given a group $G$ with operation $\bullet$ and a special kind of subgroup $N \leq G$ called the "no… - Adele Lopez
Random utility function A 'random' utility function is one chosen at random according to some simple probability measure (e.g. weight by Kolmorogov complexity) on a logical space of formal utility functions. - Eliezer Yudkowsky
Range (of a function) The "range" of a function is an ambiguous term that is generally used to refer to either the functio… - Nate Soares
Rational arithmetic all works together The various operations of arithmetic all play nicely together in a certain specific way. - Patrick Stevens
Rational number The rational numbers are "fractions". - Patrick Stevens
Rational numbers: Intro (Math 0) The rational numbers are "fractions". While the natural numbers measure the answer to the question … - Patrick Stevens
Rationality The subject domain for [ epistemic] and [ instrumental] rationality. - Eliezer Yudkowsky
Real analysis The study of real numbers and real-valued functions. - Kevin Clancy
Real number A **real number** is any number that can be used to represent a physical quantity. Intuitively, rea… - Michael Cohen
Real number (as Cauchy sequence) There are several ways to construct real numbers; this is the most natural way to use them in computations. - Patrick Stevens
Real number (as Dedekind cut) A way to construct the real numbers that follows the intuition of filling in the gaps. - Joe Zeng
Real numbers are uncountable The real numbers are uncountable. - Eric Bruylant
Real-world domain Some AIs play chess, some AIs play Go, some AIs drive cars. These different 'domains' present different options. All of reality, in all its messy entanglement, is the 'real-world domain'. - Eliezer Yudkowsky
Realistic (Math 1) Real-life examples of Bayesian reasoning - Eliezer Yudkowsky
Reflective consistency A decision system is reflectively consistent if it can approve of itself, or approve the construction of similar decision systems (as well as perhaps approving other decision systems too). - Eliezer Yudkowsky
Reflective stability Wanting to think the way you currently think, building other agents and self-modifications that think the same way. - Eliezer Yudkowsky
Reflectively consistent degree of freedom When an instrumentally efficient, self-modifying AI can be like X or like X' in such a way that X wants to be X and X' wants to be X', that's a reflectively consistent degree of freedom. - Eliezer Yudkowsky
Reflexive relation A binary relation over some set is **reflexive** when every element of that set is related to itself… - Ryan Hendrickson
Regex's feedback on site design Feb 15th 2017 Wherein Regex is confused about the current state of things - Regex Rationalist
Reinforcement learning Reinforcement learning is the process by which an agent learns what actions to take by maximizing a … - Olivia Schaefer
Reinforcement learning and linguistic convention Existing machine learning techniques are most effective when we can provide concrete feedback — such… - Paul Christiano
Relation A **relation** is a set of [tuple\_mathematics tuples], all of which have the same [tuple\_arity ar… - Kevin Clancy
Relative complement The relative complement of two sets $A$ and $B$, denoted $A \setminus B$, is the set of elements tha… - M Yass
Relative likelihood How relatively likely an observation is, given two or more hypotheses, determines the strength and direction of evidence. - Eliezer Yudkowsky
Relevant limited AI Can we have a limited AI, that's nonetheless relevant? - Eliezer Yudkowsky
Relevant powerful agent An agent is relevant if it completely changes the course of history. - Eliezer Yudkowsky
Relevant powerful agents will be highly optimized The probability that an agent that is cognitively powerful enough to be relevant to existential outc… - Eliezer Yudkowsky
Reliable prediction How can we train predictors that reliably predict observable phenomena such as human behavior? - Jessica Taylor
Replacing Guilt In my experience, many people are motivated primarily by either guilt, shame, or some combination of… - Nate Soares
Report likelihoods not p-values: FAQ This page answers frequently asked questions about the Report likelihoods, not p-values proposal for… - Nate Soares
Report likelihoods, not p-values If scientists reported likelihood functions instead of p-values, this could help science avoid p-ha… - Nate Soares
Representability theorem for computable functions A [ logical theory] $T$ is said to satisfy the **representability theorem for computable functions**… - Jaime Sevilla Molina
Representation theory The study of how groups act on vector spaces. - Qiaochu Yuan
Requisites for personal growth A mashup of models - Toon Alfrink
Rescuing the utility function If your utility function values 'heat', and then you discover to your horror that there's no ontologically basic heat, switch to valuing disordered kinetic energy. Likewise 'free will' or 'people'. - Eliezer Yudkowsky
Research directions in AI control What research would best advance our understanding of AI control? I’ve been thinking about this qu… - Paul Christiano
Researchers in value alignment theory Who's working full-time in value alignment theory? - Eliezer Yudkowsky
Resources and the future Resource constraints are a widely held concern. Which are most likely to be limiting factors, and what can we do to relax those limits? - Eric Bruylant
Reward engineering This post gestures at a handful of research questions with a loose thematic connection. ## The idea… - Olivia Schaefer
Reward engineering This post gestures at a handful of research questions with a loose thematic connection. ### The id… - Paul Christiano
Rice's Theorem Rice's Theorem tells us that if we want to determine pretty much anything about the behaviour of an arbitrary computer program, we can't in general do better than just running it. - Patrick Stevens
Rice's Theorem: Intro (Math 1) You can't write a program that looks at another programs source code, and tells you whether it computes the Fibonacci sequence. - Dylan Hendrickson
Rice's theorem and the Halting problem We will show that Rice's theorem and the the halting problem are equivalent. #The Halting theorem i… - Jaime Sevilla Molina
Rich domain A domain is 'rich', relative to our own intelligence, to the extent that (1) its [ search space] is … - Eliezer Yudkowsky
Ring A ring is a kind of Algebraic structure which we obtain by considering groups as being "things with… - Nate Soares
SSC will remain active by end of 2017 - Alexei Andreev
Safe AI from question-answering _(Warning: minimal new content. Just a clearer framing.)_ Suppose that I have a question-answering… - Paul Christiano
Safe but useless Sometimes, at the end of locking down your AI so that it seems extremely safe, you'll end up with an AI that can't be used to do anything interesting. - Eliezer Yudkowsky
Safe impact measure What can we measure to make sure an agent is acting in a safe manner? - Eliezer Yudkowsky
Safe plan identification and verification On a particular task or problem, the issue of how to communicate to the AGI what you want it to do and all the things you don't want it to do. - Eliezer Yudkowsky
Safe training procedures for human-imitators How does one train a reinforcement learner to act like a human? - Jessica Taylor
Sample space The set of possible things that could happen in a part of the world that you are uncertain about. - Tsvi BT
Sample spaces are too large Sample spaces are often large, so it is hard to do probabilistic computations using a raw distribution over the sample space. - Tsvi BT
Scalable AI Control By AI control, I mean the problem of getting AI systems to do what we want them to do, to the best o… - Paul Christiano
Scalable AI control By AI control, I mean the problem of getting AI systems to do what we want them to do, to the best… - Paul Christiano
Scalable ways to associate evidence (pro or con) with claims will be more valuable in elevating accuracy than complex voting and reputation systems Discussions on Less Wrong have delved into [complex systems of voting and moderation](http://lesswro… - Andrea Gallagher
Science Survey Nothing here yet.] Automatically generated page for "Science Survey" group. If you are the owner, … - Alexei Andreev
Seed Seeds are outlines of pages. They're not much use for readers, but can help authors. - Eric Bruylant
Selective similarity metrics for imitation Can we make human-imitators more efficient by scoring them more heavily on imitating the aspects of human behavior we care about more? - Jessica Taylor
Separation from hyperexistential risk The AI should be widely separated in the design space from any AI that would constitute a "hyperexistential risk" (anything worse than death). - Eliezer Yudkowsky
Sequence: Why Social Dynamics are So Complicated Yesterday in NYC, we had a meetup delving into a few recent-ish blogposts about why Social Dynamics… - Eric Bruylant
Serum 25-Hydroxyvitamin D Levels and the Prevalence of Peripheral Arterial Disease Clinical and population study Link: http://atvb.ahajournals.org/content/28/6/1179.full From conclu… - Alexei Andreev
Serum 25-Hydroxyvitamin D and Risks of Colon and Rectal Cancer in Finnish Men Case-control study. Link: http://aje.oxfordjournals.org/content/173/5/499.full From discussion: >… - Alexei Andreev
Serum Vitamin D Concentration and Prostate Cancer Risk: A Nested Case – Control Study Prospective analysis. Link: http://jnci.oxfordjournals.org/content/100/11/796.full.pdf From conclu… - Alexei Andreev
Set An unordered collection of distinct objects. - Nate Soares
Set builder notation $\{ 2n \mid n \in \mathbb N \}$ denotes the set of all even numbers, using set builder notation. Set… - Nate Soares
Set product A fundamental way of combining sets is to take their product, making a set that contains all tuples of elements from the originals. - Patrick Stevens
Shanghai index will not end 2017 down by more than 10% - Alexei Andreev
Shannon The shannon (Sh) is a unit of Information. One shannon is the difference in [info\_entropy entropy] … - Nate Soares
Shift towards the hypothesis of least surprise When you see new evidence, ask: which hypothesis is *least surprised?* - Nate Soares
Show me what you've broken To demonstrate competence at computer security, or AI alignment, think in terms of breaking proposals and finding technically demonstrable flaws in them. - Eliezer Yudkowsky
Shutdown problem How to build an AGI that lets you shut it down, despite the obvious fact that this will interfere with whatever the AGI's goals are. - Eliezer Yudkowsky
Shutdown utility function A special case of a low-impact utility function where you just want the AGI to switch itself off harmlessly (and not create subagents to make absolutely sure it stays off, etcetera). - Eliezer Yudkowsky
Sign homomorphism (from the symmetric group) The sign homomorphism is how we extract the alternating group from the symmetric group. - Patrick Stevens
Simple group The simple groups form the "building blocks" of group theory, analogously to the prime numbers in number theory. - Patrick Stevens
Situation in Israel will look more worse than better by end of 2017 - Alexei Andreev
Size of a set - Nate Soares
SlateStarCodex will have more than 15,000 Twitter followers by end of 2017 - Alexei Andreev
Small donors are more likely to do other good if crowded out - Alexei Andreev
Sock-dresser search There's a 4/5 chance your socks are in one of your dresser's 8 drawers. You check 6 drawers at random. What's the probability they'll be in the next drawer you check? - Nate Soares
Solomonoff induction A simple way to superintelligently predict sequences of data, given unlimited computing power. - Eliezer Yudkowsky
Solomonoff induction: Intro Dialogue (Math 2) An introduction to Solomonoff induction for the unfamiliar reader who isn't bad at math - Eliezer Yudkowsky
Solovay's theorems of arithmetical adequacy for GL Using GL to reason about PA, and viceversa - Jaime Sevilla Molina
Solutions Paper - Solving Employment in the Light of Automation GeM Labs solution space to tackle labour market challenges that arise from the rise of automation and artificial intelligence. - Geneva Macro Labs
Solving Intelligence What does it mean exactly to "solve intelligence"? - Lancelot Verinia
Some Thoughts on Deep Neural Networks and Handwritten digit recognition after my first contact with it... - Alto Clef
Some computations are people It's possible to have a conscious person being simulated inside a computer or other substrate. - Eliezer Yudkowsky
Some men just want to watch the world learn In which Arbital gets paths. - Alexei Andreev
Some page with todos Lots of things to do - Alexei Andreev
Sparking widgets 10% of widgets are bad and 90% are good. 4% of good widgets emit sparks, and 12% of bad widgets emit… - Nate Soares
Splitting conjugacy classes in alternating group The conjugacy classes in the alternating group are usually the same as those in the symmetric group; there is a surprisingly simple condition for when this does not hold. - Patrick Stevens
Square root What is the opposite of multiplying a number by itself? - Travis Rivera
Square visualization of probabilities on two events $$ \newcommand{\true}{\text{True}} \newcommand{\false}{\text{False}} \newcommand{\bP}{\mathbb{P}} … - Tsvi BT
Square visualization of probabilities on two events: (example) Diseasitis But it *seems* like the patient with the black tongue depressor has diseasitis... - Tsvi BT
Stabiliser (of a group action) If a group acts on a set, it is useful to consider which elements of the group don't move a certain element of the set. - Patrick Stevens
Stabiliser is a subgroup Given a group acting on a set, each element of the set induces a subgroup of the group. - Patrick Stevens
Stable self-improvement as an AI safety problem “Stable self-improvement” seems to be a primary focus of MIRI’s work. As I understand it, the proble… - Paul Christiano
Stages List of stages in AGI development and their properties. - Alexei Andreev
Standard agent properties What's a Standard Agent, and what can it do? - Eliezer Yudkowsky
Standard provability predicate Encoding provability as a statement of arithmetic - Jaime Sevilla Molina
Start This page gives a basic overview of the topic, but may be missing important information or have stylistic issues. If you're able to, please help expand or improve it! - Eliezer Yudkowsky
Steps towards safe AI from online learning ### Steps towards safe AI from online learning Suppose that we have a good algorithm for episodic r… - Paul Christiano
Still needs work The next step up from "Work in Progress". The page can be read as complete, but is a draft that needs further review and fine-tuning. - Eliezer Yudkowsky
Strained argument A phenomenological feeling associated with a step of reasoning going from X to Y where it feels like… - Eliezer Yudkowsky
Strategic AGI typology What broad types of advanced AIs, corresponding to which strategic scenarios, might it be possible or wise to create? - Eliezer Yudkowsky
Strength of Bayesian evidence From a Bayesian standpoint, the strength of evidence can be identified with its likelihood ratio. - Eliezer Yudkowsky
Strictly confused A hypothesis is strictly confused by the raw data, if the hypothesis did much worse in predicting it than the hypothesis itself expected. - Eliezer Yudkowsky
Strictly factual question A "question of strict fact" is one which is true or false about the material universe (and maybe some math) without introducing any issues of values, perspectives, etcetera. - Eliezer Yudkowsky
String (of text) A string (of text) is a series of letters (often denoted by quote marks), such as `"abcd"` or `"hell… - Nate Soares
Strong Church Turing thesis A strengthening of the Church Turing thesis - Jaime Sevilla Molina
Strong cognitive uncontainability An advanced agent can win in ways humans can't understand in advance. - Eliezer Yudkowsky
Stub This page only gives a very brief overview of the topic. If you're able to, please help expand or improve it! - Eliezer Yudkowsky
Style guidelines Various stylistic conventions people should follow on Arbital - Alexei Andreev
Subgroup A group that lives inside a bigger group. - Dylan Hendrickson
Subgroup is normal if and only if it is a union of conjugacy classes A useful way to think about normal subgroups, which meshes with their "closed under conjugation" interpretation. - Patrick Stevens
Subgroup is normal if and only if it is the kernel of a homomorphism The "correct way" to think about normal subgroups is as kernels of homomorphisms. - Patrick Stevens
Subjective probability Probability is in the mind, not in the environment. If you don't know whether a coin came up heads or tails, that's a fact about you, not a fact about the coin. - Eliezer Yudkowsky
Subjectivism vs Frequentism Probability is in the mind, not in the environment. If you don't know whether a coin came up heads or tails, that's a fact about you, not a fact about the coin. - Eric Bruylant
Submitting a page to a domain How and why to submit a page to a domain - Alexei Andreev
Subspace A subspace $U=(F_U, V_U)$ of a Vector space $W=(F_W, V_W)$ is a vector space where $F_U = F_W$ and $… - Nate Soares
Subtraction of rational numbers (Math 0) In which we meet anti-apples. - Patrick Stevens
Sufficiently advanced Artificial Intelligence 'Sufficiently advanced Artificial Intelligences' are AIs with enough 'advanced agent properties' that we start needing to do 'AI alignment' to them. - Eliezer Yudkowsky
Sufficiently optimized agents appear coherent If you could think as well as a superintelligence, you'd be at least that smart yourself. - Eliezer Yudkowsky
Sum of vector spaces The sum of two vector spaces $U$ and $W,$ written $U + W,$ is a vector space where the set of vector… - Nate Soares
Superintelligent A "superintelligence" is strongly superhuman (strictly higher-performing than any and all humans) on every cognitive problem. - Eliezer Yudkowsky
Supply and Demand How are prices typically formed in market systems? - Silas Barta
Surjective function A surjective function is one which "hits everything in the codomain". - Patrick Stevens
Symmetric group The symmetric groups form the fundamental link between group theory and the notion of symmetry. - Patrick Stevens
Synthesizing training data [Counterfactual oversight](https://arbital.com/p/1tj?title=human-in-counterfactual-loop) requires th… - Paul Christiano
Syria’s civil war will not end in 2017 - Alexei Andreev
Taking people seriously - Olivia Schaefer
Task (AI goal) When building the first AGIs, it may be wiser to assign them only goals that are bounded in space and time, and can be satisfied by bounded efforts. - Eliezer Yudkowsky
Task identification problem If you have a task-based AGI (Genie) then how do you pinpoint exactly what you want it to do (and not do)? - Eliezer Yudkowsky
Task-directed AGI An advanced AI that's meant to pursue a series of limited-scope goals given it by the user. In Bostrom's terminology, a Genie. - Eliezer Yudkowsky
Team Arbital The people behind Arbital - Alexei Andreev
Team Arbital The people behind this site. - Eric Bruylant
Technical and social approaches to AI safety I often divide solutions to the AI control problem into two parts: technical and social. I think a… - Paul Christiano
Teleological Measure and agency A crackpot's research proposal - Jaime Sevilla Molina
Terminal versus instrumental goals / values / preferences Distinguish events wanted for their consequences, from events wanted locally. - Eliezer Yudkowsky
The AI must tolerate your safety measures A corollary of the nonadversarial principle is that "The AI must tolerate your safety measures." - Eliezer Yudkowsky
The End (of the basic log tutorial) That concludes our introductory tutorial on logarithms! You have made it to the end. Throughout thi… - Nate Soares
The Harmonic Series: How Comes the Divergence An intuitive way of viewing it - Alto Clef
The Necessity of Credibility - Eric Rogstad
The Octalysis Framework will not tell you which combinations of feelings will lead to good gameplay. - Sarah Wolf
The Robots, AI, and Unemployment Anti-FAQ Q. Are the current high levels of unemployment being caused by advances in Artificial Intelligence … - Eliezer Yudkowsky
The Stamp Collector Once upon a time, a group of naïve philosophers found a robot that collected trinkets. Well, more sp… - Nate Soares
The UK will trigger Article 50 in 2017 - Alexei Andreev
The Value of Coordination >When you’re part of a community, the counterfactuals become more complex, and doing the most good b… - Alexei Andreev
The absentee billionaire Once each day, Hugh wakes for 10 minutes. During these 10 minutes, he spends 10 million dollars. The… - Paul Christiano
The alternating group on five elements is simple The smallest (nontrivial) simple group is the alternating group on five elements. - Patrick Stevens
The alternating group on five elements is simple: Simpler proof A proof which avoids some of the heavy machinery of the main proof. - Patrick Stevens
The alternating groups on more than four letters are simple The alternating groups are the most accessible examples of simple groups, and this fact also tells us that the symmetric groups are "complicated" in some sense. - Patrick Stevens
The benefits of moving the community won't be realized in time before AGI. - Alexei Andreev
The biggest source of human bias is the incentive to lead others to believe that you are better than you are If evolution were optimizing creatures that were exactly like humans except that they were not socia… - Stephanie Zolayvar
The characteristic of the logarithm Any time you find an output that adds whenever the input multiplies, you're probably looking at a (… - Nate Soares
The collection of even-signed permutations is a group This proves the well-definedness of one particular definition of the alternating group. - Patrick Stevens
The community would lose a lot of its influence if it doesn't have a strong presence in key geographical locations (e.g. Bay Area). - Alexei Andreev
The composition of two group homomorphisms is a homomorphism The collection of group homomorphisms is closed under composition. - Patrick Stevens
The current message of effective altruism heavily discourages creativity. Alyssa Vance expands on this point in her [FB post](https://www.facebook.com/alyssamvance/posts/1021… - Alexei Andreev
The development of Artificial General Intelligence, as a scientific purpose for human life Purpose here is not to be confused for teleological argument/theism/deities/subjective endeavours. Instead, this thread refers to teleonomy, or purpose in the realm of science/objectivity. - Jordan Bennett
The easy goal inference problem is still hard Goal inference and inverse reinforcement learning ------------------------------------------------… - Paul Christiano
The effect of vitamin D supplementation on skeletal, vascular, or cancer outcomes: a trial sequential meta-analysis Trial sequential meta-analysis. Link: http://www.thelancet.com/journals/landia/article/PIIS2213-858… - Alexei Andreev
The empiricist-theorist false dichotomy No discussion here yet: See https://www.facebook.com/groups/674486385982694/permalink/7846641016315… - Eliezer Yudkowsky
The empty set is the only set which satisfies the universal property of the empty set This theorem tells us that the universal property provides a sensible way to define the empty set uniquely. - Patrick Stevens
The ideal Arbital math page Think of the best math textbook you've ever read -- why was it good? - Eric Rogstad
The image of a group under a homomorphism is a subgroup of the codomain Group homomorphisms take groups to groups, but it is additionally guaranteed that the elements they hit form a group. - Patrick Stevens
The log lattice Log as the change in the cost of communicating and other pages give physical interpretations of what… - Nate Soares
The main downside of CFAR focusing on AI risk is that it may cause brand damage. - Timothy Chu
The missing step between Zero and Hero Creating a space for high potential people grow and improve the world at scale. - Eric Bruylant
The n-th root of m is either an integer or irrational In other words, no power of a rational number that is not an integer is ever an integer. - Joe Zeng
The plan Root page for the plan on how to approach and navigate through AGI development. - Alexei Andreev
The plan experiment Root page for describing the reason and the process for planning how to approach and navigate through AGI development. - Alexei Andreev
The plan should be public There is an open question of whether or not The plan experiment should be public. My current intuiti… - Alexei Andreev
The rationals form a field The set $\mathbb{Q}$ of rational numbers is a field. # Proof $\mathbb{Q}$ is a (commutative) ring … - Patrick Stevens
The reals (constructed as Dedekind cuts) form a field The reals are an archetypal example of a field, but if we are to construct them from simpler objects, we need to show that our construction does indeed have the right properties. - Patrick Stevens
The reals (constructed as classes of Cauchy sequences of rationals) form a field The reals are an archetypal example of a field, but if we are to construct them from simpler objects, we need to show that our construction does indeed have the right properties. - Patrick Stevens
The rocket alignment problem If people talked about the problem of space travel the way they talked about AI... - Eliezer Yudkowsky
The set of rational numbers is countable Although there are "lots and lots" of rational numbers, there are still only countably many of them. - Patrick Stevens
The sign of a permutation is well-defined This result is what allows the alternating group to exist. - Patrick Stevens
The square root of 2 is irrational The number whose square is 2 can't be written is a quotient of natural numbers - Dylan Hendrickson
The state of the steering problem The [steering problem](https://arbital.com/p/1tv?title=the-steering-problem) asks: given some powe… - Paul Christiano
The steering problem Most AI research focuses on reproducing human abilities: to learn, infer, and reason; to perceive,… - Paul Christiano
The world needs something like a miracle of good thought if it is to have decent odds of overcoming x-risk. - Eric Rogstad
Theory of (advanced) agents One of the research subproblems of building powerful nice AIs, is the theory of (sufficiently advanced) minds in general. - Eliezer Yudkowsky
There is only one logarithm All logarithm functions are the same, up to a multiplicative constant. - Nate Soares
There will be no Cast Lead style bombing/invasion of Gaza in 2017 - Alexei Andreev
There will be no announcement of genetically engineered human baby or credible plan for such in 2017 - Alexei Andreev
There will be no race riot killing > 5 people in 2017 - Alexei Andreev
Theresa May will remain PM of Britain in 2017 - Alexei Andreev
Thinking accumulatively is one of the keys to solving existential risks. - Eric Rogstad
This is just a test proposal Only a test! - Alexei Andreev
Thought experiment Meta-tag for thought experiments. - Nate Soares
Tiling agents theory The theory of self-modifying agents that build successors that are very similar to themselves, like repeating tiles on a tesselated plane. - Eliezer Yudkowsky
Time-machine metaphor for efficient agents Don't imagine a paperclip maximizer as a mind. Imagine it as a time machine that always spits out the output leading to the greatest number of future paperclips. - Eliezer Yudkowsky
To make faster intellectual progress, it would help if the community was located more densely together. - Alexei Andreev
To math explanations and beyond! In which Arbital doubles down on math explanations. - Alexei Andreev
To think thoughts fully uninfluenced by the surrounding society one has to be physically removed from it. This claim is related to Our community should relocate to a country other than the US. - Alexei Andreev
Too long Meta tag used to indicate that this page is too long by Arbital's standards. - Alexei Andreev
Tools and tactics for improving explanations A list of some of the most useful and generally applicable techniques for creating understanding. - Duncan Sabien
Total alignment We say that an advanced AI is "totally aligned" when it knows *exactly* which outcomes and plans are beneficial, with no further user input. - Eliezer Yudkowsky
Totally ordered set A set where all the elements can be compared as greater than or less than. - Joe Zeng
Toxoplasmosis dilemma A parasitic infection, carried by cats, may make humans enjoy petting cats more. A kitten, now in front of you, isn't infected. But if you *want* to pet it, you may already be infected. Do you? - Eliezer Yudkowsky
Transcendental number A transcendental number is one which is not the root of any integer-coefficient polynomial. - Patrick Stevens
Transitive relation If a is related to b and b is related to c, then a is related to c. - Dylan Hendrickson
Transparent Newcomb's Problem Omega has left behind a transparent Box A containing $1000, and a transparent Box B containing $1,000,000 or nothing. Box B is full iff Omega thinks you one-box on seeing a full Box B. - Eliezer Yudkowsky
Transposition (as an element of a symmetric group) A transposition is the simplest kind of permutation: it swaps two elements. - Patrick Stevens
Trit Trinary digit - Nate Soares
True Prisoner's Dilemma A scenario that would reproduce the ideal payoff matrix of the Prisoner's Dilemma about human beings who care about their public reputation and each other. - Eliezer Yudkowsky
Trying Things Optimization requires trying things and being wrong. - Nicolas Bourbaki
Turing machine A Turing Machine is a simple mathematical model of computation that is powerful enough to describe any computation a computer can do. - Eric Leese
Turing machine: External resources * [Wikipedia](https://en.wikipedia.org/wiki/Turing_machine) * [Wolfram MathWorld](http://mathworld.w… - Eric Bruylant
Two independent events What do [a pair of dice], [a pair of coins], and [a pair of people on opposite sides of the planet] all have in common? - Tsvi BT
Two independent events: Square visualization $$ \newcommand{\true}{\text{True}} \newcommand{\false}{\text{False}} \newcommand{\bP}{\mathbb{P}} … - Tsvi BT
Type theory Modern foundations for formal mathematics. - Jack Gallagher
US unemployment to be higher at end of 2017 than beginning - Alexei Andreev
Ultimatum Game A Proposer decides how to split $10 between themselves and the Responder. The Responder can take what is offered, or refuse, in which case both parties get nothing. - Eliezer Yudkowsky
Unassessed This page's quality has not been assessed. - Eric Bruylant
Uncomputability The diagonal function and the halting problem - Jaime Sevilla Molina
Uncountability Some infinities are bigger than others. Uncountable infinities are larger than countable infinities. - Jason Gross
Uncountability (Math 3) Formal definition of uncountability, and foundational considerations. - Patrick Stevens
Uncountability: Intro (Math 1) Not all infinities are created equal. The infinity of real numbers is infinitely larger than the infinity of counting numbers. - Jason Gross
Uncountability: Intuitive Intro Are all sizes of infinity the same? What does "the same" even mean here? - Jason Gross
Uncountable sample spaces are way too large We can't define probability distributions over uncountable sample spaces by just assigning numbers to each point in the sample space. - Tsvi BT
Under a group homomorphism, the image of the inverse is the inverse of the image The operations of "taking inverses" and "applying a group homomorphism" commute: it does not matter in which order we do them. - Patrick Stevens
Underestimating complexity of value because goodness feels like a simple property When you just want to yell at the AI, "Just do normal high-value X, dammit, not weird low-value X!" and that 'high versus low value' boundary is way more complicated than your brain wants to think. - Eliezer Yudkowsky
Underlying set What do a Group, a Partially ordered set, and a [ topological space] have in common? Each is a Set … - Nate Soares
Understandability principle The more you understand what the heck is going on inside your AI, the safer you are. - Eliezer Yudkowsky
Unemployment and Automation #WORK IN PROGRESS I'm going to research and explore the topic of unemployment and automation. Quest… - Alexei Andreev
Unforeseen maximum When you tell AI to produce world peace and it kills everyone. (Okay, some SF writers saw that one coming.) - Eliezer Yudkowsky
Union The union of two sets is the set of elements which are in one or the other, or both - M Yass
Unique factorisation domain This is the correct way to abstract from the integers the fact that every integer can be written uniquely as a product of prime numbers. - Patrick Stevens
Unit (ring theory) A unit in a ring is just an element with a multiplicative inverse. - Patrick Stevens
Universal prior A "universal prior" is a probability distribution containing *all* the hypotheses, for some reasonable meaning of "all". E.g., "every possible computer program that computes probabilities". - Eliezer Yudkowsky
Universal property A universal property is a way of defining an object based purely on how it interacts with other objects, rather than by any internal property of the object itself. - Patrick Stevens
Universal property of joins and meets in a poset Partially ordered sets are a good setting to illustrate some of the concepts of category theory; joins and meets are instances of category-theoretic ideas. - Patrick Stevens
Universal property of the disjoint union Just as the empty set may be described by a universal property, so too may the disjoint union of sets. - Patrick Stevens
Universal property of the empty set The empty set can be characterised by how it interacts with other sets, rather than by any explicit property of the empty set itself. - Patrick Stevens
Universal property of the product The product can be defined in a very general way, applicable to the natural numbers, to sets, to algebraic structures, and so on. - Patrick Stevens
Unphysically large finite computer The imaginary box required to run programs that require impossibly large, but finite, amounts of computing power. - Eliezer Yudkowsky
Unsupervised learning and AI control Reinforcement learning systems optimize for an objective defined by external feedback — anything fro… - Paul Christiano
Up to isomorphism A phrase mathematicians use when saying "we only care about the structure of an object, not about specific implementation details of the object". - Patrick Stevens
Updateless decision theories Decision theories that maximize their policies (mappings from sense inputs to actions), rather than using their sense inputs to update their beliefs and then selecting actions. - Eliezer Yudkowsky
Useless variable decomposition A variable decomposition can be true but useless if it is a poor guide to intervention due to automa… - Alexei Andreev
User manipulation If not otherwise averted, many of an AGI's desired outcomes are likely to interact with users and hence imply an incentive to manipulate users. - Eliezer Yudkowsky
User maximization A sub-principle of avoiding user manipulation - if you see an argmax over X or 'optimize X' instruction and X includes a user interaction, you've just told the AI to optimize the user. - Eliezer Yudkowsky
Utility What is "utility" in the context of Value Alignment Theory? - Eliezer Yudkowsky
Utility function The only coherent way of wanting things is to assign consistent relative scores to outcomes. - Eliezer Yudkowsky
Utility indifference How can we make an AI indifferent to whether we press a button that changes its goals? - Eliezer Yudkowsky
VAT playpen Playpen page for VAT domain. - Alexei Andreev
Valley of Dangerous Complacency When the AGI works often enough that you let down your guard, but it still has bugs. Imagine a robotic car that almost always steers perfectly, but sometimes heads off a cliff. - Eliezer Yudkowsky
Value The word 'value' in the phrase 'value alignment' is a metasyntactic variable that indicates the speaker's future goals for intelligent life. - Eliezer Yudkowsky
Value achievement dilemma How can Earth-originating intelligent life achieve most of its potential value, whether by AI or otherwise? - Eliezer Yudkowsky
Value alignment problem You want to build an advanced AI with the right values... but how? - Eliezer Yudkowsky
Value identification problem The subproblem category of value alignment which deals with pinpointing valuable outcomes to an adva… - Eliezer Yudkowsky
Value-laden Cure cancer, but avoid any bad side effects? Categorizing "bad side effects" requires knowing what's "bad". If an agent needs to load complex human goals to evaluate something, it's "value-laden". - Eliezer Yudkowsky
Vector arithmetic Vectors: what they are, and how to add and scale them. - Adele Lopez
Vector space A vector space is a field $F$ paired with a Group $V$ and a function $\cdot : F \times V \to V$ (cal… - Nate Soares
Vinge's Law You can't predict exactly what someone smarter than you would do, because if you could, you'd be that smart yourself. - Eliezer Yudkowsky
Vinge's Principle An agent building another agent must usually approve its design without knowing the agent's exact policy choices. - Eliezer Yudkowsky
Vingean reflection The problem of thinking about your future self when it's smarter than you. - Eliezer Yudkowsky
Vingean uncertainty You can't predict the exact actions of an agent smarter than you - so is there anything you _can_ say about them? - Eliezer Yudkowsky
Vitamin D Vitamin D refers to a group of fat-soluble secosteroids responsible for enhancing intestinal absorpt… - Alexei Andreev
Vitamin D Deficiency and Risk for Cardiovascular Disease Theoretical meta-analysis. Link: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2726624/ From conclus… - Alexei Andreev
Vitamin D and Cardiometabolic Outcomes: A Systematic Review Meta-analysis. Link: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3211092/ From conclusions: > "An… - Alexei Andreev
Vitamin D and calcium supplementation reduces cancer risk: results of a randomized trial Randomized trial Link: http://www.ncbi.nlm.nih.gov/pubmed/17556697%20 From conclusions: > "Improv… - Alexei Andreev
Vitamin D helps prevent bone fracture (Yes) One randomized trial shows some promise, but at extremely high doses of 100,000 IUs. (No) A l… - Alexei Andreev
Vitamin D helps prevent breast cancer No -- Calcium and vitamin D supplementation did not reduce invasive breast cancer incidence in post… - Alexei Andreev
Vitamin D helps prevent cancer There have been a lot of studies performed that show that vitamin D helps prevent cancer, but overal… - Alexei Andreev
Vitamin D helps prevent cardiovascular disease This question is a bit vague. There are two ways to make it more specific. 1. Does vitamin D deffic… - Alexei Andreev
Vitamin D helps prevent colorectal cancer No -- Daily supplementation of calcium with vitamin D for seven years had no effect on the incidenc… - Alexei Andreev
Vitamin D helps prevent prostate cancer Yes --- Calcitriol showed significant antineoplastic activity in pre-clinical models of prostate ca… - Alexei Andreev
Vitamin D is good for you We'll consider two categories of vitamin D supplementation: below and above the recommended levels. … - Alexei Andreev
Vitamin D is related to blood pressure and other cardiovascular risk factors in middle-aged men Correlational study Link: http://www.ncbi.nlm.nih.gov/pubmed/8541004 - Alexei Andreev
Vitamin, Mineral, and Multivitamin Supplements for the Primary Prevention of Cardiovascular Disease and Cancer: A Systematic Evidence Review for the US Preventive Services Task Force Meta-study Link: http://www.ncbi.nlm.nih.gov/pubmed/24308073 From results: > "Vitamin D and/or ca… - Alexei Andreev
Wants to get straight to Bayes A simple requisite page to mark whether the user has selected wanting to get straight into Bayes on … - Eliezer Yudkowsky
Waterfall diagram Visualizing Bayes' rule as the mixing of probability streams. - Eliezer Yudkowsky
Waterfall diagrams and relative odds A way to visualize Bayes' rule that yields an easier way to solve some problems - Eliezer Yudkowsky
We do not currently have a single shared conversation. - Eric Rogstad
Welcome to Arbital Front page explaining what Arbital is all about. - Alexei Andreev
Well-calibrated probabilities Even if you're fairly ignorant, you can still strive to ensure that when you say "70% probability", it's true 70% of the time. - Eliezer Yudkowsky
Well-defined A mathematical object is "well-defined" if we have given it a completely unambiguous definition. - Patrick Stevens
Well-ordered set An ordered set with an order that always has a "next element". - Dylan Hendrickson
What is a logarithm? Logarithms are a group of functions that take a number as input and produce another number. There i… - Nate Soares
What is the probability that impeachment proceedings will be commenced against President Donald Trump during his first term? More on impeachment in United States: https://en.wikipedia.org/wiki/Impeachment_in_the_United_States - Alexei Andreev
What should superintelligence be programmed to do? This is one of the key open questions in The plan experiment. Coherent extrapolated volition (align… - Alexei Andreev
When I donate to a charity, I am concerned whether or not the charity will raise enough money to make my donation worthwhile. - Alexei Andreev
Who needs civilization? The most common difference between my model and that of people I've discussed this with is that many… - Eric Bruylant
Whole number A term that can refer to three different sets of "numbers that are not fractions". - Joe Zeng
Why argument structure is important How might we make collaborative truth-seeking both fun and easy? - Andrea Gallagher
Why is log like length? If a number $x$ is $n$ digits long (in Decimal notation), then its logarithm (base 10) is between $n… - Nate Soares
Why is the decimal expansion of log2(3) infinite? Because 2 and 3 are relatively prime. - Nate Soares
Why waiting to donate harms charities A blog post explaining the potential reasons why someone would choose to wait to donate and how that leads to suboptimal outcomes for the charity. - Alexei Andreev
Will Narrow AI Seriously Affect Long-Term Employment? ###Definitions: **Narrow AI** - artificial intelligence capable of doing a narrow task at a level … - Alexei Andreev
William Frankena's list of terminal values Life, consciousness, and activity; health and strength; pleasures and satisfactions of all or certain kinds; happiness, beatitude, contentment, etc.; truth; knowledge and true opinions... - Eliezer Yudkowsky
With some fixed amount of money to start, a microloan charity could make loans indefinitely A claim about microloans. - Alexei Andreev
Without loss of generality *Without loss of generality* (abbreviated as w.l.o.g.) is a common idiom in mathematics that remarks… - Jaime Sevilla Molina
Work in progress This page is being actively worked on by an editor. Check with them before making major changes. - Eliezer Yudkowsky
Working out, weightlifting, and nutrition Just a collection of links / resources I'll be using to seed some content. # Working out ### How t… - Alexei Andreev
You can't get more paperclips that way Most arguments that "A paperclip maximizer could get more paperclips by (doing nice things)" are flawed. - Eliezer Yudkowsky
You can't get the coffee if you're dead An AI given the goal of 'get the coffee' can't achieve that goal if it has been turned off; so even an AI whose goal is just to fetch the coffee may try to avert a shutdown button being pressed. - Eliezer Yudkowsky
You're allowed to fight for something The first sort of guilt I want to address is the listless guilt, that vague feeling one gets after p… - Nate Soares
Zermelo-Fraenkel provability oracle We might be able to build a system that can safely inform us that a theorem has a proof in set theory, but we can't see how to use that capability to save the world. - Eliezer Yudkowsky
Zero-Shot Translation with Google’s Multilingual Neural Machine Translation System Sorry, old news. But I'll leave it up. - Andrea Gallagher
child test - Alex Foster
concat (function) The string concatenation function `concat` puts two strings together, i.e., `concat("one","two")="on… - Nate Soares
fdsa Nothing here yet.] Automatically generated page for "fdsa" group. If you are the owner, click [her… - Eric Rogstad
game mechanics are tools that manipulate the players feelings rather than tools to make a task fun. - Sarah Wolf
n-digit An $n$-digit is a physical object that can be stably placed into any of $n$ distinguishable states. … - Nate Soares
n-message A message singling out one thing from a set of $n$ is sometimes called an $n$-message. For example,… - Nate Soares
neural nets already determine the key features that are important to the decision. The importance of a given feature is represented by the weight on a particular neuron/input-feature. - Travis Rivera
playpen subpage playpen subpage clickbait - Robert Lecnik
some formulas that are not directly given that may or may not help i oofed on the other one - 974
test page blah blah blah - ordinary title
test page 2 blah blah blah - ordinary title
test page please ignore - Mars (person)
test123 test page - Eric Bruylant
testing testing - Jesse Aldridge
testpage test123 - Eric Bruylant
this is a claim - Alex Foster
ε-ROI Lemma The fundamental lemma for analyzing logical inductor properties. - Alex Appel

group

comment

question

Do we need to worry about AI? Why worry about AI when nothing has gone wrong yet? - Eliezer Yudkowsky
What does a sample question look like? Just an example of an Arbital question. - Alexei Andreev
Where is a playpen question? Sandbox / playpen question page. - Alexei Andreev
aaaaaaaaaaaaaaaaaaaaaaaaaa weeeeeeeeeeeeeeeee - Eric Bruylant

By Type (Named)

wiki

group

comment

question

no-type