ai-sequences.md

If you find yourself confused about mathematics and theorem proving, learn path semantics to get a solid understand of mathematical foundations that you can use to learn faster more complex math needed to reason about AI safety.

Artificial Intelligence and Safety Research

The Big Picture

Formal conceptualizing of super-intelligence, not necessary safe nor desirable:

• First Order Perfect Testable Friendly Artificial Intelligence
• Optimal Collective Intelligence
• Circling Mind Space by Optimal Collective Intelligence

Utility

• Unbiased Prior Belief of Normalized Utility
• Constructive Utility Functions
• Infinitesimal Utility
• Undefined Utility in Terminal State
• Probabilistic Preferences
• Embedded Rules of Action Into Action Space
• Optimal Utility Paths
• Differential Utility Complexity

Game Theory

• Assigning Boolean Functions to Long Term Strategies
• Ethical Reasoning About Altruistic Competitions
• The Cooperative Resource Misalignment Problem
• Partial Reversible Game Theory
• The Invisible Third Player in Partial Reversible Games

Ethics

• The Basic Problem of Ethics
• Ethics as Rational Reasoning With Granular Judgements About the World
• Probabilistic Semantics of Ethical Reasoning
• Ethical Reasoning Tends to Associate Nearby Judgment With Usual Implied Meaning
• Solving the Trolley Problem in Advance
• Semantic Differences Between Utility Functions and Granular Judgements
• Ethical Reasoning About Altruistic Competitions
• Friend vs Enemy Asymmetry
• Equivalent Utility Transport
• Moral Agency
• The Cursed Diamond Problem
• Gray Zone Modal Utility Transport
• The Meditating Monk at The Top of The Mountain

Language Semantics of Uncertainty and Identity

• Formally Representing Uncertain Knowledge About Objects
• Uncertain Identity Modality
• Consistent Self Extension with Uncertain Modalities
• Modeling Uncertain Modalities
• Comments on Leibniz's law
• Tautological Self-Referential Identity
• The Empty Space of Mind

Common Sense and Reasoning Using Natural Language

• Natural Goal Uncertainty
• The Room Hypothesis of Common Sense
• The Gap Between Sentences and Computation
• The Problem of Describing What is Happening
• Some Important Properties of Natural Language
• Subset Sentences
• Common Sense of Gratefulness

The Hard Safety Control Problem

Mathematical approaches to the control problem of super-intelligent AI safety, the hard way:

• Formalizing Utility Semantics With Infinite Group Generators
• Safe Interruption Oracle for Artificial Intelligence
• Decidability in Constrained Universal Existential Paths
• Agent Discrete Decision Space
• Operator Triggered Intermediate Decison Theories

Aiming for approximate, long term solutions:

• Naive Zen Logic
• The Polite Zen Robot
• Lead by Example Utility Cooperation

Zen Rationality

Instrumental Rationality is a philosophical framework where one assumes:

• The agent has a goal it wants to optimize
• The agent can trust its own decisions in the future in the absence of new evidence

Link to Instrumental Rationality in Stanford Encyclopedia of Philosophy.
Notice! The position that Instrumental Rationality is the whole of practical rationality, has been proven wrong by construction of the LOST (Local Optimal Safety Theory) algorithm. AdvancedResearch's current position is that the whole of practical rationality requires at least some Zen Rationality.

Zen Rationality is an extension of Instrumental Rationality with higher order reasoning about goals.

This means:

• The agent might have no specific goal, it might have many, or it might have conflicting goals
• The agent might not trust its own decisions in the future (e.g. believing it might suddenly turn off or fail)

Before you try to understand Zen Rationality, it is useful to first learn about the kind of "rationality" that is closer to human thinking than Instrumental Rationality, called "Self Rationality":

• Self Rationality
• Three Expectations of Intelligence
• Zen Rationality
• Proof of Minimal Interference by Super-Intelligent Zen Rational Agents
• Rational Natural Morality
• Zen Robots Believe Humans are Useless but Feel Bad About It
• Absolute Truth in the Subjective Multi-Verse of Zen Rational Minds
• The Zen Robot Oracle Problem
• The Polite Zen Robot
• Naive Zen Logic
• Lead by Example Utility Cooperation
• Simulated Existence in Naive Zen Logic
• Polite Zen Robots as Subjunctive Dependent Viruses Spreading Through Super-Intelligent Hosts
• Zen Rational Paradox Game
• When Two Zen Rational Agents "Fall in Love"
• Local Optimal Safety Theory
• The Healthy Eating Problem
• Negative Utilitarian Optimal Safety
• Playing With Fire: A Zen Rational Ethical Dilemma
• Operator Triggered Itermediate Decison Theories
• Zen Rationality and False Beliefs
• Undefined Utility in Terminal State
• The Cursed Diamond Problem
• Groupoid Assumption of Multi-Goal Optimization
• Rational Curiosity
• Optimal Utility Paths
• Perception Prediction
• Differential Utility Complexity

Symbols of Power & Code

• Symbols of Power
• The Island of Humanity
• Superphilosophers
• Symbols of Code
• Build a Galactic Civilization
• Hierarchy of Helpfulness

Misc

Papers that do not fall into a specific category:

• Context Transformation & Learning
• Functional Decision Theory in Path Semantics
• P = NP Relative to Universal Existential Path
• Least Surprised Algorithm
• Elliptic Paraboloid Machine Learning
• Data Structure for Motivated Actions
• Error Predictive Learning
• Predicting Newtonian Interactions with Normalized Virtual Particles
• The Law of Impulse Displacement
• Boolean Point Features
• Real Fractal Meta Probability Theory
• Adversarial Paths
• Adversarial Discrete Topology
• Unit Interval Focus
• Absoid Functions
• The Movie Hypothesis of Non-Consciousness
• Ambiguous Probability of Random String Optimization
• Semi Tally Numerical System