This page displays the concepts which are foci of LessWrong discussion.
The page has three sections:
Theory / Concepts
Models of the Mind
Basic Alignment Theory
General Science & Eng
Meta / Misc
Social & Economic
Biological & Psychological
The Practice of Modeling
Causes / Interventions
Working with Humans
Skills & Techniques
Rationality is the art of thinking in ways that result in accurate beliefs and good decisions. It is the primary topic of LessWrong.
Rationality is not only about avoiding the vices of self-deception and obfuscation, but also about the virtue of curiosity, seeing the world more clearly than before, and achieving things previously unreachable to you. The study of rationality on LessWrong includes a theoretical understanding of ideal cognitive algorithms, as well as building a practice that uses these idealized algorithms to inform heuristics, habits, and techniques, to successfully reason and make decisions in the real world.
Artificial Intelligence is the study of creating intelligence in algorithms. On LessWrong, the primary focus of AI discussion is to ensure that as humanity builds increasingly powerful AI systems, the outcome will be good. The central concern is that a powerful enough AI, if not designed and implemented with sufficient understanding, would optimize something unintended by its creators and pose an existential threat to the future of humanity. This is known as the AI alignment problem.
World Modeling is getting curious about how the world works. It’s diving into wikipedia, it’s running a survey to get data from your friends, it’s dropping balls from different heights and measuring how long they take to fall. Empiricism, scholarship, googling, introspection, data-gathering, science. Applying your epistemology and curiosity, finding out how the damn thing works, and writing it down for the rest of us.
World Optimization is the full use of our agency. It is extending the reach of human civilization. It is building cities and democracies and economic systems and computers and flight and science and space rockets and the internet. World optimization is about adding to that list.
But it’s not just about growth, it’s also about preservation. We are still in the dawn of civilization, with most of civilization in the billions of years ahead. We mustn’t let this light go out.
Practical posts give direct, actionable advice on how to achieve goals and generally succeed. The art of rationality would be useless if it did not connect to the real world; we must take our ideas and abstractions and collide them with reality. Many places on the internet will give you advice; here, we value survey data, literature reviews, self-blinded trials, quantitative estimates, and theoretical models that aim to explain the phenomena.
The LessWrong Community is the people who write on LessWrong and who contribute to its mission of refining the art of human rationality. This tag includes community events, analysis of the health, norms and direction of the community, and space to understand communities in general.
LessWrong also has many brothers and sisters like the Berkeley Rationality Community, SlateStarCodex, Effective Altruism, AI Alignment, and more, who participate here. To see upcoming LessWrong events, go to the community section.
Site Meta is the category for discussion about LessWrong website. It includes technical updates. It applies to team announcements such as updates, features, events, moderation activity and policy, downtime, requests for feedback, as well as site documentation, and the team’s writings about site philosophy/strategic thinking.
Open Threads are informal discussion areas, where users are welcome to post comments that didn't quite feel big enough to warrant a top-level post, nor fit in other posts.
Fiction isn't literal truth, but when done well it captures truths and intuitions that are difficult to explain directly. (It’s also damn fun to read.)
Book Reviews on LessWrong are different from normal book reviews; they summarize and respond to a book's core ideas first, and judge whether you should read it second. A good book review sometimes distills the book's ideas so well that you no longer need to read the book.
Decision theory is the study of principles and algorithms for making correct decisions—that is, decisions that allow an agent to achieve better outcomes with respect to its goals .
For general discussion about ethics and morality. Example posts: Fake Morality; What Would You Do Without Morality?; The Terrible, Horrible, No Good, Very Bad Truth About Morality and What To Do About It; Why Are Individual IQ Differences OK?; Morality is Awesome.
Anthropics is the study of how the fact that we succeed in making observations of a given kind at all gives us evidence about the world we are living, independently of the content of the observations. As an example, for living beings, making any observations at all is only possible in a universe with physical laws that support life.
The Machine Intelligence Research Institute, formerly known as the Singularity Institute for Artificial Intelligence (not to be confused with Singularity University).