 Misalignment or misuse? The AGI alignment tradeoffPhilosophical Studies (Philos. Stud.), 2025 |
 |
 Universal AI maximizes Variational EmpowermentArtificial General Intelligence (AGI), 2025 |
 Learning to Assist Humans without Inferring RewardsNeural Information Processing Systems (NeurIPS), 2024 |
 RL, but don't do anything I wouldn't doConference on Uncertainty in Artificial Intelligence (UAI), 2024 |
 Beyond Preferences in AI AlignmentPhilosophical Studies (Philos. Stud.), 2024 |
 |
 Contestable AI needs Computational ArgumentationInternational Conference on Principles of Knowledge Representation and Reasoning (KR), 2024 |
 |
 Improving Generalization of Alignment with Human Preferences through
Group Invariant LearningInternational Conference on Learning Representations (ICLR), 2023 |
 |
 Human Control: Definitions and AlgorithmsConference on Uncertainty in Artificial Intelligence (UAI), 2023 |
 Incentivizing honest performative predictions with proper scoring rulesConference on Uncertainty in Artificial Intelligence (UAI), 2023 |
 Selection for short-term empowerment accelerates the evolution of
homeostatic neural cellular automataAnnual Conference on Genetic and Evolutionary Computation (GECCO), 2023 |
 |
