The catalog, page 38
Records 9,251 to 9,500 of 10,618. Explained and Verified records first, then newest. Every row carries the label that says how far the checking went.
-
Together We Know How to Achieve: An Epistemic Logic of Know-How
Listed -
Reflexive Oracles and superrationality: Pareto
Listed -
Reflexive Oracles and superrationality: prisoner's dilemma
Listed -
When Will AI Exceed Human Performance? Evidence from AI Experts
Listed -
Reinforcement Learning with a Corrupted Reward Channel
Listed -
Thinking Fast and Slow with Deep Learning and Tree Search
Listed - Listed
-
Acausal trade: conclusion: theory vs practice
Listed -
Acausal trade: full decision algorithms
Listed - Listed
-
Anthropic uncertainty in the Evidential Blackmail
Listed -
Forecasting using incomplete models
Listed - Listed
-
Robot Planning with Mathematical Models of Human State and Action
Listed - Listed
- Listed
-
Informatica: Special Issue on Superintelligence
Listed -
Finding reflective oracle distributions using a Kakutani map
Listed - Listed
-
Highlights from the ICLR conference: food, ships, and ML security
Listed -
Software Engineer Internship / Staff Openings
Listed -
That is not dead which can eternal lie: the aestivation hypothesis for resolving Fermi's paradox
Listed -
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Listed -
Two Major Obstacles for Logical Inductor Decision Theory
Listed -
Intro to caring about AI alignment as an EA cause
Listed -
Ensuring smarter-than-human intelligence has a positive outcome
Listed -
Interpretable Explanations of Black Boxes by Meaningful Perturbation
Listed -
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning
Listed -
Decisions are for making bad outcomes inconsistent
Listed -
Guide to pages on AI timeline predictions
Listed - Listed
- Listed
- Listed
- Listed
-
On the Impossibility of Supersized Machines
Listed - Listed
-
On Automating the Doctrine of Double Effect
Listed - Listed
-
2016 International Symposium on Experimental Robotics
Listed - Listed
-
New paper: “Cheating Death in Damascus”
Listed - Listed
- Listed
-
Progress in general purpose factoring
Listed -
The average utilitarian’s solipsism wager
Listed -
HCH as a measure of manipulation
Listed -
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Listed -
A proposal for ethically traceable artificial intelligence
Listed -
A model of pathways to artificial superintelligence catastrophe for risk and decision analysis
Listed -
Generalizing Foundations of Decision Theory
Listed -
Trends in algorithmic progress
Listed -
Do You Want Your Autonomous Car to Drive Like You?
Listed -
Using machine learning to address AI risk
Listed - Listed
-
Towards A Rigorous Science of Interpretable Machine Learning
Listed -
Don't Fear the Reaper: Refuting Bostrom's Superintelligence Argument
Listed - Listed
-
What Should the Average EA Do About AI Alignment?
Listed -
Changes in funding in the AI safety field
Listed - Listed
- Listed
-
CHCAI/MIRI research internship in AI safety
Listed -
Enabling Robots to Communicate their Objectives
Listed -
Model Mis-specification and Inverse Reinforcement Learning
Listed - Listed
-
“Betting on the Past” by Arif Ahmed
Listed - Listed
-
Changes in funding in the AI safety field
Listed -
My current take on the Paul-MIRI disagreement on alignability of messy AI
Listed -
On motivations for MIRI's highly reliable agent design research
Listed -
Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy
Listed -
Practical Reasoning with Norms for Autonomous Software Agents (Full Edition)
Listed -
New paper: “Toward negotiable reinforcement learning”
Listed -
Interactive Learning from Policy-Dependent Human Feedback
Listed -
A measure-theoretic generalization of logical induction
Listed -
Corrigibility thoughts II: the robot operator
Listed -
Corrigibility thoughts III: manipulating versus deceiving
Listed -
Is it a bias or just a preference? An interesting issue in preference idealization
Listed -
Decision Theory and the Irrelevance of Impossible Outcomes
Listed -
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
Listed -
Response to Cegłowski on superintelligence
Listed -
Latent Variables and Model Mis-specification
Listed - Listed
-
Designing a Safe Autonomous Artificial Intelligence Agent based on Human Self-Regulation
Listed - Listed
- Listed
-
A Psychoanalytic Approach to the Singularity: Why We Cannot Do Without Auxiliary Constructions
Listed - Listed
-
Artificial General Intelligence: Timeframes & Policy White Paper
Listed -
Can the Singularity Be Patented? (And Other IP Conundrums for Converging Technologies)
Listed -
Computer Simulations as a Technological Singularity in the Empirical Sciences
Listed - Listed
-
Diminishing Returns and Recursive Self Improving Artificial Intelligence
Listed -
Energy, Complexity, and the Singularity
Listed -
How Change Agencies Can Affect Our Path Towards a Singularity
Listed -
Implicitly Assisting Humans to Choose Good Grasps in Robot to Human Handovers
Listed -
Introduction to the technological singularity
Listed -
Learning Robot Objectives from Physical Human Interaction
Listed -
Liability For Present And Future Robotics Technology
Listed -
Modeling and interpreting expert disagreement about artificial superintelligence
Listed -
Moral Decision Making Frameworks for Artificial Intelligence
Listed -
New paper: “Optimal polynomial-time estimators”
Listed -
Pervasive Spurious Normativity
Listed -
Pricing Externalities to Balance Public Risks and Benefits of Research
Listed -
Responses to the Journey to the Singularity
Listed - Listed
-
Risks of the Journey to the Singularity
Listed -
Security solutions for intelligent and complex systems
Listed -
Strategic implications of openness in AI development
Listed -
Strategic Implications of Openness in AI Development
Listed - Listed
- Listed
-
The Wisdom of Nature: An Evolutionary Heuristic for Human Enhancement
Listed - Listed
-
Individual Project Fund: Further Details
Listed -
Pursuing convergent instrumental subgoals on the user's behalf doesn't always require good priors
Listed -
AI Alignment: Why It’s Hard, and Where to Start
Listed -
AI Safety Highlights from NIPS 2016
Listed - Listed
-
Thinking Outside One’s Paradigm
Listed - Listed
-
Faulty Reward Functions in the Wild
Listed -
Neuro-symbolic EDA-based Optimisation using ILP-enhanced DBNs
Listed -
Extortion and trade negotiations
Listed -
2016 Expert Survey on Progress in AI
Listed -
Concrete AI tasks for forecasting
Listed -
2016 AI Risk Literature Review and Charity Comparison
Listed - Listed
-
Experiments in Handwriting with a Neural Network
Listed -
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Listed - Listed
-
Joscha Bach on remaining steps to human-level AI
Listed -
Improving Policy Gradient by Exploring Under-appreciated Rewards
Listed -
Predicting HCH using expert advice
Listed - Listed
- Listed
- Listed
-
A stochastically verifiable autonomous control architecture with reasoning
Listed - Listed
-
Neural Architecture Search with Reinforcement Learning
Listed - Listed
-
Nonparametric General Reinforcement Learning
Listed -
Vector-Valued Reinforcement Learning
Listed -
Universal adversarial perturbations
Listed -
Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures
Listed -
Learning to Protect Communications with Adversarial Neural Cryptography
Listed -
White House submissions and report on AI safety
Listed -
Transitive negotiations with counterfactual agents
Listed - Listed
-
Deconvolution and Checkerboard Artifacts
Listed -
OpenAI unconference on machine learning
Listed - Listed
-
MIRI AMA, and a talk on logical induction
Listed - Listed
-
Situational Awareness by Risk-Conscious Skills
Listed -
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
Listed -
CSRBAI talks on agent models and multi-agent dilemmas
Listed -
Xception: Deep Learning with Depthwise Separable Convolutions
Listed -
Logical inductor limits are dense under pointwise convergence
Listed - Listed
-
Backup utility functions as a fail-safe AI technique
Listed -
Information gathering actions over human internal state
Listed -
Looking back at my grad school journey
Listed -
The set of Logical Inductors is not Convex
Listed -
UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS
Listed -
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Listed -
Would You Hand Over a Decision to a Machine?
Listed -
Logical Inductors that trust their limits
Listed - Listed
-
A Formal Solution to the Grain of Truth Problem
Listed - Listed
-
Long-Term Trends in the Public Perception of Artificial Intelligence
Listed - Listed
-
(C)IRL is not solely a learning process
Listed - Listed
-
New paper: “Logical induction”
Listed - Listed
-
Attention and Augmented Recurrent Neural Networks
Listed -
Conversation with Tom Griffiths
Listed -
Tom Griffiths on Cognitive Science and AI
Listed -
Grant announcement from the Open Philanthropy Project
Listed - Listed
-
Sources of advantage for digital agents over biological agents
Listed -
What if you turned the world’s hardware into AI minds?
Listed -
Formalizing preference utilitarianism in physical world models
Listed -
CSRBAI talks on preference specification
Listed -
Why does deep and cheap learning work so well?
Listed -
Highlights from the Deep Learning Summer School
Listed - Listed
-
Wireheading Done Right: Stay Positive Without Going Insane
Listed -
Modeling the capabilities of advanced AI systems as episodic reinforcement learning
Listed -
Deepmind Plans for Rat-Level AI
Listed -
Superintelligence via whole brain emulation
Listed -
Examples of early action on risks
Listed -
Towards Evaluating the Robustness of Neural Networks
Listed -
CSRBAI talks on robustness and error-tolerance
Listed -
A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems.
Listed -
Generating Plans that Predict Themselves.
Listed -
Inferring and Assisting with Constraints in Shared Autonomy.
Listed -
Optimal Polynomial-Time Estimators: A Bayesian Notion of Approximation Algorithm
Listed -
Implicitly Assisting Humans to Choose Good Grasps in Robot to Human Handovers.
Listed -
Information Gathering Actions Over Human Internal State.
Listed -
MDPs with Unawareness in Robotics.
Listed -
Planning for Autonomous Cars that Leverage Effects on Human Actions.
Listed -
Sufficient Conditions for Causality to be Transitive.
Listed -
Friendly AI as a global public good
Listed -
Andrew Critch: Logical induction — progress in AI alignment
Listed -
Max Tegmark: Risks and benefits of advanced artificial intelligence
Listed - Listed
- Listed
-
Costs of extinction risk mitigation
Listed - Listed
-
Clopen AI: Openness in different aspects of AI development
Listed - Listed
-
Do Artificial Reinforcement-Learning Agents Matter Morally?
Listed - Listed
-
New paper: “Alignment for advanced machine learning systems”
Listed -
A Model of Pathways to Artificial Superintelligence Catastrophe for Risk and Decision Analysis
Listed -
Submission to the OSTP on AI outcomes
Listed -
Predicting Enemy's Actions Improves Commander Decision-Making
Listed - Listed
- Listed
-
Exploiting Vagueness for Multi-Agent Consensus
Listed -
The Naive Utility Calculus: Computational Principles Underlying Commonsense Psychology
Listed -
Adversarial examples in the physical world
Listed - Listed
- Listed
-
A Hybrid POMDP-BDI Agent Architecture with Online Stochastic Planning and Plan Caching
Listed -
The Unilateralist’s Curse and the Case for a Principle of Conformity
Listed -
New paper: “A formal solution to the grain of truth problem”
Listed -
Towards A Virtual Assistant That Can Be Taught New Tasks In Any Domain By Its End-Users
Listed - Listed
-
Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units
Listed -
Towards Verified Artificial Intelligence
Listed -
Artificial Fun: Mapping Minds to the Space of Fun
Listed -
New AI safety research agenda from Google Brain
Listed -
Visualizing Dynamics: from t-SNE to SEMI-MDPs
Listed -
Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation
Listed -
Cooperative Inverse Reinforcement Learning vs. Irrational Human Preferences
Listed -
Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction
Listed -
Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models
Listed -
Unsupervised Risk Estimation Using Only Conditional Independence Structure
Listed - Listed
-
In memoryless Cartesian environments, every UDT policy is a CDT+SIA policy
Listed -
Generative Adversarial Imitation Learning
Listed -
The Mythos of Model Interpretability
Listed -
Learning Language Games through Interaction
Listed -
Fundamental lssues Of Artificial Intelligence
Listed - Listed
-
New paper: “Safely interruptible agents”
Listed