The catalog, page 39
Records 9,501 to 9,750 of 10,618. Explained and Verified records first, then newest. Every row carries the label that says how far the checking went.
-
Suffering-focused AI safety: Why “fail-safe” measures might be our top intervention
Listed -
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
Listed - Listed
-
Transparency reports make AI decision-making accountable
Listed -
Stabilizing logical counterfactuals by pseudorandomization
Listed -
Quantifying the Far Future Effects of Interventions
Listed -
Error in Armstrong and Sotala 2012
Listed - Listed
-
Metasurvey: predict the predictors
Listed -
Avoiding Wireheading with Value Reinforcement Learning
Listed -
Self-Modification of Policy and Utility Function in Rational Agents
Listed -
Potential Risks from Advanced Artificial Intelligence: The Philanthropic Opportunity
Listed -
A new MIRI research program with a machine learning focus
Listed -
You Say You Want Transparency and Interpretability?
Listed -
Global Catastrophic Risks 2016
Listed -
Classifying Options for Deep Reinforcement Learning
Listed -
Limits to Verification and Validation of Agentic Behavior
Listed -
New papers dividing logical uncertainty into two subproblems
Listed -
Asymptotic Convergence in Online Learning with Unbounded Delays
Listed - Listed
-
An artificial intelligence tool for heterogeneous team formation in the classroom
Listed -
Using humility to counteract shame
Listed -
Moving Beyond the Turing Test with the Allen AI Science Challenge
Listed -
The many counterfactuals of counterfactual mugging
Listed - Listed
- Listed
-
New paper on bounded Löb and robust cooperation of bounded agents
Listed -
The Age of Em: Work, Love and Life when Robots Rule the Earth
Listed -
MIRI has a new COO: Malo Bourgon
Listed - Listed
-
Announcing a new colloquium series and fellows program
Listed - Listed
-
Crystal Society trilogy: Inside the mind of an AI
Listed -
Seeking Research Fellows in Type Theory and Machine Self-Reference
Listed -
A Signaling Game Approach to Databases Querying and Interaction
Listed - Listed
- Listed
-
John Horgan interviews Eliezer Yudkowsky
Listed -
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
Listed -
New paper: “Defining human values for value learners”
Listed -
The informed oversight problem
Listed -
Introductory resources on AI safety research
Listed -
Toy model: convergent instrumental goals
Listed -
ALBA: An explicit proposal for aligned AI
Listed -
Speculations on information under logical uncertainty
Listed -
Latent Skill Embedding for Personalized Lesson Sequence Recommendation
Listed -
The Singularity May Never Be Near
Listed - Listed
-
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Listed -
Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics
Listed -
Designing Intelligent Instruments
Listed -
Energetics of the brain and AI
Listed -
Parametric Bounded Löb's Theorem and Robust Cooperation of Bounded Agents
Listed -
Modeling Human Ad Hoc Coordination
Listed -
Research Priorities for Robust and Beneficial Artificial Intelligence
Listed -
Graying the black box: Understanding DQNs
Listed -
Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples
Listed - Listed
-
Mastering the game of Go with deep neural networks and tree search
Listed -
A survey of research questions for robust and beneficial AI
Listed -
A survey of research questions for robust and beneficial AI
Listed -
Towards Resolving Unidentifiability in Inverse Reinforcement Learning
Listed - Listed
-
Coordinated human action as example of superhuman intelligence
Listed -
To contribute to AI safety, consider doing AI research
Listed -
To contribute to AI safety, consider doing AI research
Listed -
The correct response to uncertainty is *not* half-speed
Listed -
Analysis of Algorithms and Partial Algorithms
Listed -
Difficulty of Predicting the Maximum of Gaussians
Listed -
End-of-the-year fundraiser and grant successes
Listed -
Another view of quantilizers: avoiding Goodhart's Law
Listed -
Logical counterfactuals for random algorithms
Listed - Listed
-
Agential Risks: A Comprehensive Introduction
Listed -
Building Machines That Learn and Think Like People
Listed -
Defining human values for value learners
Listed -
Embedding Ethical Principles in Collective Decision Support Systems
Listed -
Formalizing convergent instrumental goals
Listed -
Future progress in artificial intelligence: A survey of expert opinion
Listed -
Growing Recursive Self-Improvers
Listed -
How the Simulation Argument Dampens Future Fanaticism
Listed -
Learning the Preferences of Ignorant, Inconsistent Agents
Listed -
Planning for Autonomous Cars that Leverage Effects on Human Actions
Listed -
Policy desiderata in the development of machine superintelligence
Listed -
Probabilistic Models of Cognition
Listed -
Quantilizers: A safer alternative to maximizers for limited optimization
Listed -
Racing to the precipice: a model of artificial intelligence development
Listed -
Rationality and Intelligence: A Brief Update
Listed -
Robots in war: the next weapons of mass destruction?
Listed - Listed
-
Suffering-focused AI safety: Why "fail-safe'" measures might be our top intervention
Listed -
The Control Problem. Excerpts from Superintelligence: Paths, Dangers, Strategies
Listed -
The Liability Problem for Autonomous Artificial Agents
Listed -
The Technological Singularity: Managing the Journey
Listed -
Towards interactive inverse reinforcement learning
Listed - Listed
-
Safety engineering, target selection, and alignment theory
Listed -
Highlights and impressions from NIPS conference on machine learning
Listed -
Multi-Level Cause-Effect Systems
Listed - Listed
-
The need to scale MIRI’s methods
Listed -
A sketch of a value-learning sovereign
Listed -
Learning the Preferences of Ignorant, Inconsistent Agents
Listed - Listed
-
Some work on connecting UDT and Reinforcement Learning
Listed -
Jed McCaleb on Why MIRI Matters
Listed -
Logical Counterfactuals Consistent Under Self-Modification
Listed -
Saying 'AI safety research is a Pascal's Mugging' isn't a strong response
Listed -
The Rationale behind the Concept of Goal
Listed - Listed
-
Human-level concept learning through probabilistic program induction
Listed -
Deep Residual Learning for Image Recognition
Listed -
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Listed -
New paper: “Proof-producing reflection for HOL”
Listed - Listed
- Listed
-
MIRI’s 2015 Winter Fundraiser!
Listed - Listed
-
Risks from general artificial intelligence without an intelligence explosion
Listed -
New paper: “Formalizing convergent instrumental goals”
Listed -
A Roadmap towards Machine Intelligence
Listed -
Convergent Learning: Do different neural networks learn the same representations?
Listed - Listed
- Listed
-
Superrationality in arbitrary games
Listed -
Edge.org contributors discuss the future of AI
Listed -
Working at EA organizations series: Machine Intelligence Research Institute
Listed -
Glossary of AI Risk Terminology and common AI terms
Listed - Listed
-
Bad Universal Priors and Notions of Optimality
Listed -
A first look at the hard problem of corrigibility
Listed -
Asymptotic Logical Uncertainty and The Benford Test
Listed -
Chatbots or set answers, not WBEs
Listed -
New report: “Leó Szilárd and the Danger of Nuclear Weapons”
Listed -
Ambitious vs. narrow value learning
Listed - Listed
-
New paper: “Asymptotic logical uncertainty and the Benford test”
Listed -
Submission and Formatting Instructions for International Conference on Machine Learning (ICML 2015)
Listed -
The application of the secretary problem to real life dating
Listed -
Quantilizers maximize expected utility subject to a conservative cost constraint
Listed - Listed
-
Constructing Abstraction Hierarchies Using a Skill-Symbol Loop
Listed - Listed
-
Probabilities Small Enough To Ignore: An attack on Pascal's Mugging
Listed - Listed
-
How To Win The AI Box Experiment (Sometimes)
Listed - Listed
-
Our summer fundraising drive is complete!
Listed -
Confronting future catastrophic threats to humanity
Listed - Listed
-
Final fundraiser day: Announcing our new team
Listed -
Provability Counterfactuals vs Three Axioms of Galles and Pearl
Listed -
A Dialogue on Suffering Subroutines
Listed -
A Lower Bound on the Importance of Promoting Cooperation
Listed -
Differential Intellectual Progress as a Positive-Sum Project
Listed -
How Would Catastrophic Risks Affect Prospects for Compromise?
Listed -
Reasons to Be Nice to Other Value Systems
Listed - Listed
- Listed
-
Posterior calibration and exploratory analysis for natural language processing models
Listed -
Powerful planners, not sentient software
Listed - Listed
-
OOASP: Connecting Object-oriented and Logic Programming
Listed -
A response to Matthews on AI Risk
Listed -
Assessing our past and potential impact
Listed -
Target 3: Taking It To The Next Level
Listed - Listed
- Listed
- Listed
- Listed
- Listed
-
A Comprehensive Survey on Safe Reinforcement Learning
Listed -
A new MIRI FAQ, and other announcements
Listed -
How to escape from your sandbox and from your hardware host
Listed -
Belief and Truth in Hypothesised Behaviours
Listed - Listed
-
Time flies when robots rule the earth
Listed - Listed
- Listed
-
Index of articles about hardware
Listed -
Systems I have tried: an overview
Listed - Listed
-
Cost of human-level information storage
Listed - Listed
-
Information storage in the brain
Listed -
Asymptotic Logical Uncertainty: Concrete Failure of the Solomonoff Approach
Listed -
Oracle AI: Human beliefs vs human values
Listed -
Decision Maker based on Atomic Switches
Listed -
An Idea For Corrigible, Recursively Improving Math Oracles
Listed - Listed
- Listed
- Listed
-
MIRI’s 2015 Summer Fundraiser!
Listed -
Examples of AI's behaving badly
Listed -
Event: Exercises in Economic Futurism
Listed -
Conversation with Steve Potter
Listed -
Steve Potter on neuroscience and AI
Listed -
Inceptionism: Going deeper into neural networks
Listed -
Toward Idealized Decision Theory
Listed -
Two big challenges in machine learning
Listed - Listed
- Listed
-
Vingean Reflection: Open Problems
Listed - Listed
-
Multitasking: Efficient Optimal Planning for Bandit Superprocesses
Listed -
New report: “The Asilomar Conference: A Case Study in Risk Mitigation”
Listed -
Wanted: Office Manager (aka Force Multiplier)
Listed -
Two-boxing, smoking and chewing gum in Medical Newcomb problems
Listed -
Recent developments in unifying logic and probability
Listed -
Long-Term and Short-Term Challenges to Ensuring the Safety of AI Systems
Listed -
Sequential Extensions of Causal and Evidential Decision Theory
Listed -
A simple model of the Löbstacle
Listed -
Agent Simulates Predictor using Second-Level Oracles
Listed -
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Listed -
Update on all the AI predictions
Listed -
Predictions of Human-Level AI Timelines
Listed - Listed
- Listed
- Listed
- Listed
-
Mortal universal agents & wireheading
Listed -
Publication biases toward shorter predictions
Listed -
Selection bias from optimistic experts
Listed - Listed
- Listed
-
Probabilistic machine learning and artificial intelligence
Listed -
Why do AGI researchers expect AI so soon?
Listed -
Group Differences in AI Predictions
Listed -
MIRI-related talks from the decision theory conference at Cambridge University
Listed - Listed
-
The Unreasonable Effectiveness of Recurrent Neural Networks
Listed -
AI Timeline predictions in surveys and statements
Listed - Listed
- Listed
-
Weight Uncertainty in Neural Networks
Listed -
Agents that can predict their Newcomb predictor
Listed -
What is Learning? A primary discussion about information and Representation
Listed -
Hamming questions and bottlenecks
Listed -
Optimal and Causal Counterfactual Worlds
Listed -
Automating change of representation for proofs in discrete mathematics
Listed -
A new approach to predicting brain-computer parity
Listed - Listed
-
A fond farewell and a new Executive Director
Listed - Listed
-
Metareasoning for Planning Under Uncertainty
Listed - Listed
-
New papers on reflective oracles and agents
Listed - Listed
- Listed
- Listed