paper:doi-10-1038-s41586-019-1138-yMachine behaviour
Original abstract (expand)
Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. Here we argue that this necessitates a broad scientific research agenda to study machine behaviour that incorporates and expands upon the discipline of computer science and includes insights from across the sciences. We first outline a set of questions that are fundamental to this emerging field and then explore the technical, legal and institutional constraints on the study of machine behaviour.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- A Pattern Language for Machine Learning TasksIan Fan, Tuomas Laakkonen, Neil John Ortega, Thomas Hoffmann, Vincent Wang-Mascianica Benjamin Rodatz2025≈ 72%
- StylePredict: Machine Theory of Mind for Human Driver Behavior From TrajectoriesAniket Bera, Dinesh Manocha Rohan Chandra2020≈ 69%
- Modeling Human Behavior Part I -- Learning and Belief ApproachesAndrew Fuchs and Andrea Passarella and Marco Conti2022≈ 67%
- AI, Meet Human: Learning Paradigms for Hybrid Decision Making SystemsRoberto Pellungrini, Mattia Setzu, Fosca Giannotti and Dino Pedreschi Clara Punzi2026≈ 66%
- A Machine Consciousness architecture based on Deep Learning and Gaussian ProcessesMart\'in Molina Eduardo C. Garrido Merch\'an2020≈ 66%
- ≈ 66%
- ≈ 66%
- ≈ 66%
- When Respondents Don't Care Anymore: Identifying the Onset of Careless RespondingMax Welz and Andreas Alfons2026≈ 65%
- Exploring MLOps Dynamics: An Experimental Analysis in a Real-World Machine Learning ProjectAwadelrahman M. A. Ahmed2023≈ 65%
- Active Inference on the Edge: A Design StudyVictor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar Boris Sedlak2023≈ 65%
- A Review on Machine Theory of MindShuang Liu, Pengshuai Zhao, Qin Ni, Xin Lin and Liang He Yuanyuan Mao2023≈ 65%
- A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver BehaviorRaunak P. Bhattacharyya and Kyle Brown and Juanran Wang and Katherine Driggs-Campbell and Mykel J. Kochenderfer2026≈ 65%
- ≈ 65%
- Can a Machine be Conscious? Towards Universal Criteria for Machine ConsciousnessCosmin Badea Nur Aizaan Anwar2024≈ 64%
- ≈ 64%
- ≈ 61%
- Model Alignment Searchin corpus2025≈ 61%
- cimcWhitepaperin corpus≈ 60%
- Learning without neurons in physical systemsin corpus2022≈ 60%
- ≈ 60%
- Collective intelligence: A unifying concept for integrating biology across scales and substratesin corpus2024≈ 60%
- Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencodersin corpus2026≈ 59%
- An association-based model of dynamic behaviourin corpus2011≈ 59%
- ≈ 59%
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behaviorin corpus2026≈ 59%
- The Machine Consciousness Hypothesisin corpus≈ 59%
- The World Inside Neural Networksin corpus2026≈ 59%
- ≈ 59%
Similar preprints — Semantic Scholar
Cited by (5)
- Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation
Quantitative introspection—the causal coupling between an instruction-tuned LLM's numeric self-report and a probe-defined internal emotive direction—is demonstrably present in models as small as LLaMA
- Darwin's agential materials: evolutionary implications of multiscale competency in developmental biology
Cellular collectives operating between the genotype and anatomical phenotype constitute an agential substrate that fundamentally reshapes the evolutionary search process—this is the central claim of L
- Collective intelligence: A unifying concept for integrating biology across scales and substrates
Collective intelligence, understood as William James' capacity to reach the same goal by different means, operates not only in beehives and ant colonies but as a scale-free organizing principle across
- Living Things Are Not (20th Century) Machines: Updating Mechanism Metaphors in Light of the Modern Science of Machine Behavior
Bongard and Levin argue that the longstanding debate over whether living things are machines has been conducted against a 20th-century, static definition of 'machine' that modern engineering has alrea
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligence
Levin and Lyons argue that the price system in market economies is not merely a resource-allocation device but the canonical instantiation of what they term a *cognitive glue* — a coordinating afforda