The catalog, page 40
Records 9,751 to 10,000 of 10,618. Explained and Verified records first, then newest. Every row carries the label that says how far the checking went.
-
Concept Safety: Producing similar AI-human concept spaces
Listed - Listed
-
Towards Verifiably Ethical Robot Behaviour
Listed -
Not so innocent: Reasoning about costs, competence, and culpability in very early childhood
Listed -
Technical and social approaches to AI safety
Listed -
Artificial Intelligence and Its Implications for Future Suffering
Listed -
Flavors of Computation Are Flavors of Consciousness
Listed -
Gains from Trade through Compromise
Listed -
Metabolic Estimates of Rate of Cortical Firing
Listed -
International Cooperation vs. AI Arms Race
Listed -
Preliminary prices for human-level hardware
Listed - Listed
-
Paraconsistent Tiling Agents (Very Early Draft)
Listed - Listed
-
Principles of Explanatory Debugging to Personalize Interactive Machine Learning
Listed -
Superintelligence 29: Crunch time
Listed - Listed
-
Negative visualization, radical acceptance and stoicism
Listed -
Recent AI control brainstorming by Stuart Armstrong
Listed -
Reflective oracles and the procrastination paradox
Listed -
Shared Autonomy via Hindsight Optimization
Listed -
Superintelligence 28: Collaboration
Listed - Listed
-
Corrigible omniscient AI capable of making clones
Listed -
Forum Digest: Reflective Oracles
Listed - Listed
-
Introducing the Intelligent Agent Foundations Forum
Listed -
New report: “An Introduction to Löb’s Theorem in MIRI Research”
Listed -
Superintelligence 27: Pathways and enablers
Listed -
Allen, The Singularity Isn’t Near
Listed -
Rationality: From AI to Zombies
Listed -
Kurzweil, The Singularity is Near
Listed - Listed
-
Wikipedia history of GFLOPS costs
Listed -
Bill Hibbard on Ethical Artificial Intelligence
Listed -
Superintelligence 26: Science and technology strategy
Listed -
Trends in the cost of computing
Listed -
Fallenstein talk for APS March Meeting 2015
Listed -
Superintelligence 25: Components list for acquiring values
Listed - Listed
-
Ethical guidelines for a superintelligence
Listed -
Sequential Feature Explanations for Anomaly Detection
Listed -
What’s up with nuclear weapons?
Listed -
Possible Empirical Investigations
Listed -
Human-level control through deep reinforcement learning
Listed -
An Introduction to Löb’s Theorem in MIRI Research
Listed -
From Seed AI to Technological Singularity via Recursively Self-Improving Software
Listed -
Research topic: Hardware, software and AI
Listed -
Oracle machines for automated philosophy
Listed -
Superintelligence 23: Coherent extrapolated volition
Listed -
Future of Life Institute’s recent milestones in AI safety
Listed -
Un-manipulable counterfactuals
Listed -
An implementation of modal UDT
Listed -
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Listed -
How to study superintelligence strategy
Listed -
List of multipolar research projects
Listed - Listed
-
Superintelligence 22: Emulation modulation and institutional design
Listed -
How AI timelines are estimated
Listed -
UDT in the Land of Probabilistic Oracles
Listed -
At-least-human-level-at-human-cost AI
Listed -
Davis on AI capability and motivation
Listed - Listed
-
Probabilistic Oracle Machines and Nash Equilibria
Listed -
New annotated bibliography for MIRI’s technical agenda
Listed -
[LINK] Wait But Why - The AI Revolution Part 2
Listed -
From halting oracles to modal logic
Listed -
New mailing list for MIRI math/CS papers only
Listed -
Superintelligence 21: Value learning
Listed - Listed
-
Discontinuous progress investigation
Listed - Listed
- Listed
-
The odd counterfactuals of playing chicken
Listed -
Vingean Reflection: Reliable Reasoning for Self-Improving Agents
Listed -
New report: “The value learning problem”
Listed -
Superintelligence 20: The value-loading problem
Listed -
The AI Revolution: Our Immortality or Extinction
Listed - Listed
-
Benefits and Risks of Artificial Intelligence
Listed -
Benefits and Risks of Artificial Intelligence
Listed -
New, Brief Popular-Level Introduction to AI Risks and Superintelligence
Listed -
An Introduction to Löb's Theorem in MIRI Research
Listed -
Formalizing Two Problems of Realistic World Models
Listed -
List of Analyses of Time to Human-Level AI
Listed -
New report: “Formalizing Two Problems of Realistic World Models”
Listed -
The AI Revolution: The Road to Superintelligence
Listed -
The slow traversal of ‘human-level’
Listed -
Making or breaking a thinking machine
Listed -
The range of human intelligence
Listed -
Are AI surveys seeing the inside view?
Listed -
Visualizing Representations: Deep Learning and Human Beings
Listed -
New report: “Vingean Reflection: Reliable Reasoning for Self-Improving Agents”
Listed -
Event: Multipolar AI workshop with Robin Hanson
Listed -
Selfish preferences and self-modification
Listed - Listed
-
Superintelligence 18: Life in an algorithmic economy
Listed -
Were nuclear weapons cost-effective explosives?
Listed - Listed
-
An improved “AI Impacts” website
Listed - Listed
- Listed
- Listed
-
AI and the Big Nuclear Discontinuity
Listed -
New report: “Questions of reasoning under logical uncertainty”
Listed - Listed
-
The Biggest Technological Leaps
Listed -
Brooks and Searle on AI volition and timelines
Listed -
Matthias Troyer on Quantum Computers
Listed -
Superintelligence 17: Multipolar scenarios
Listed - Listed
-
Bayesian computational models for inferring preferences
Listed - Listed
-
Death and pain of a digital brain
Listed -
Deep learning in neural networks: An overview
Listed -
Existential risk and existential hope: definitions
Listed -
Global challenges: 12 risks that threaten human civilization
Listed -
How valuable is movement growth?
Listed -
How We’re Predicting AI – or Failing to
Listed -
How we’re predicting AI–or failing to
Listed -
Learning the Preferences of Bounded Agents
Listed -
Mathematics of Machine Learning
Listed - Listed
-
Motivated value selection for artificial agents
Listed -
Outrunning the Law: Extraterrestrial Liberty and Universal Colonisation
Listed -
Off-policy Monte Carlo agents with variable behaviour policies
Listed -
Proof-Producing Reflection for HOL
Listed -
Research priorities for robust and beneficial artificial intelligence: an open letter
Listed -
Responses to catastrophic AGI risk: a survey
Listed -
Treating anthropic selfish preferences as an extension of TDT
Listed -
We, Borg: Speculations on hive minds as a posthuman state
Listed -
Cases of Discontinuous Technological Progress
Listed -
Effect of nuclear weapons on historic trends in explosives
Listed -
Superintelligence 16: Tool AIs
Listed - Listed
- Listed
- Listed
- Listed
-
FHI Winter Intelligence Survey
Listed - Listed
- Listed
- Listed
-
Müller and Bostrom AI Progress Poll
Listed -
Similarity Between Historical and Contemporary AI Predictions
Listed - Listed
-
Our new technical research agenda overview
Listed -
Superintelligence 15: Oracles, genies and sovereigns
Listed -
Adam: A Method for Stochastic Optimization
Listed -
Explaining and Harnessing Adversarial Examples
Listed -
2014 Winter Matching Challenge Completed!
Listed -
New report: “Computable probability distributions which converge…”
Listed -
New report: “Toward Idealized Decision Theory”
Listed -
New report: “Tiling agents in causal graphs”
Listed -
Superintelligence 14: Motivation selection methods
Listed -
Superintelligence 13: Capability control methods
Listed -
Concept Learning for Safe Autonomous AI
Listed -
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Listed -
New paper: “Concept learning for safe autonomous AI”
Listed -
2014 Winter Matching Challenge!
Listed - Listed
-
Superintelligence 12: Malignant failure modes
Listed -
The great downside dilemma for risky emerging technologies
Listed -
Three impacts of machine intelligence
Listed -
Superintelligence 11: The treacherous turn
Listed - Listed
-
Superintelligence 10: Instrumentally convergent goals
Listed -
Three misconceptions in Edge.org’s conversation on “The Myth of AI”
Listed - Listed
-
Stable self-improvement as a research problem
Listed -
Simplicity priors with reflective oracles
Listed -
Logical Limitations to Machine Ethics with Consequences to Lethal Autonomous Weapons
Listed -
Superintelligence 9: The orthogonality of intelligence and goals
Listed -
Video of Bostrom’s talk on Superintelligence at UC Berkeley
Listed -
A new guide to MIRI’s research
Listed -
Ethical Artificial Intelligence
Listed - Listed
-
The Financial Times story on MIRI
Listed -
Do Artificial Reinforcement-Learning Agents Matter Morally?
Listed -
New report: “UDT with known search order”
Listed -
Singularity2014.com appears to be a fake
Listed -
Superintelligence 7: Decisive strategic advantage
Listed -
Superintelligence 6: Intelligence explosion kinetics
Listed -
Introducing Corrigibility (an FAI research subfield)
Listed - Listed
-
Importance motivation: a double-edged sword
Listed -
The Precautionary Principle (with Application to the Genetic Modification of Organisms)
Listed -
AGI outcomes and civilizational competence
Listed -
Superintelligence 5: Forms of Superintelligence
Listed -
Nate Soares’ talk: “Why ain’t you rich?”
Listed - Listed
-
Superintelligence Reading Group 3: AI and Uploads
Listed -
Newcomblike problems are the norm
Listed -
Superintelligence Reading Group 2: Forecasting AI
Listed - Listed
-
CEV: coherence versus extrapolation
Listed -
Superintelligence Reading Group - Section 1: Past Developments and Present Capabilities
Listed -
Kristinn Thórisson on constructivist AI
Listed -
Nate Soares speaking at Purdue University
Listed -
Good policy ideas that won’t happen (yet)
Listed -
Ken Hayworth on brain emulation prospects
Listed -
Sequence to Sequence Learning with Neural Networks
Listed -
Friendly AI Research Help from MIRI
Listed -
Citadel house sessions – a year in review
Listed -
Daniel Roy on probabilistic programming and AI
Listed -
Goal retention discussion with Eliezer
Listed - Listed
-
Very Deep Convolutional Networks for Large-Scale Image Recognition
Listed -
Friendly Artificial Intelligence: the Physics Challenge
Listed - Listed
-
Neural Machine Translation by Jointly Learning to Align and Translate
Listed -
Superintelligence reading group
Listed -
Superintelligence reading group
Listed -
Knightian uncertainty: a rejection of the MMEU rule
Listed -
New paper: “Exploratory engineering in artificial intelligence”
Listed -
2014 Summer Matching Challenge Completed!
Listed -
MIRI’s recent effective altruism talks
Listed -
A Logic for Reasoning about Upper Probabilities
Listed -
Groundwork for AGI safety engineering
Listed - Listed
-
Algorithmic Game Theory (Fall 2013)
Listed -
Scott Frickel on intellectual movements
Listed -
Evidence with Uncertain Likelihoods
Listed -
Beyond Point-and-Shoot Morality: Why Cognitive (Neuro)Science Matters for Ethics
Listed -
Nick Bostrom to speak about Superintelligence at UC Berkeley
Listed -
A Visualization of Nick Bostrom’s Superintelligence
Listed -
2014 Summer Matching Challenge!
Listed -
Knightian Uncertainty and Ambiguity Aversion: Motivation
Listed -
Representing and Reasoning about Game Strategies
Listed -
May 2015 decision theory conference at Cambridge University
Listed -
How to study superintelligence strategy
Listed -
Superintelligence: Paths, Dangers, Strategies
Listed -
The errors, insights and lessons of famous AI predictions – and what they mean for the future
Listed - Listed
-
New report: “Non-omniscience, probabilistic inference, and metamathematics”
Listed -
Roger Schell on long-term computer security research
Listed -
New chapter in Cambridge Handbook of Artificial Intelligence
Listed - Listed
-
Generative Adversarial Networks
Listed -
Allan Friedman on cybersecurity and cyberwar
Listed -
New report: “Distributions allowing tiling of staged subjective EU maximizers”
Listed - Listed
-
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
Listed -
Milind Tambe on game theory in security applications
Listed -
New report: “Loudness: On priors over preference relations”
Listed -
Aaron Tomb on crowd-sourced formal verification
Listed -
MIRI wants to fund your independently-organized Friendly AI workshop
Listed -
Lennart Beringer on the Verified Software Toolchain
Listed -
Decision Theory with Resource-Bounded Agents
Listed -
Johann Schumann on high-assurance systems
Listed -
Sandor Veres on autonomous agents
Listed