Examining the Differential Risk from High-level Artificial Intelligence and the Question of Control
Artificial Intelligence (AI) is one of the most transformative technologies of the 21st century. The extent and scope of future AI capabilities remain a key uncertainty, with widespread disagreement on timelines and potential impacts. As nations and technology companies race toward greater complexity and autonomy in AI systems, there are concerns over the extent of integration and oversight of opaque AI decision processes. This is especially true in the subfield of machine learning (ML), where systems learn to optimize objectives without human assistance. Objectives can be imperfectly specified or executed in an unexpected or potentially harmful way. This becomes more concerning as systems increase in power and autonomy, where an abrupt capability jump could result in unexpected shifts in power dynamics or even catastrophic failures. This study presents a hierarchical complex systems framework to model AI risk and provide a template for alternative futures analysis. Survey data were collected from domain experts in the public and private sectors to classify AI impact and likelihood. The results show increased uncertainty over the powerful AI agent scenario, confidence in multiagent environments, and increased concern over AI alignment failures and influence-seeking behavior.
Code (0)
등록된 구현이 없습니다.
Tasks
AI AgentSimilar Papers 제목 키워드 기반
Generating Artificial Data for Private Deep Learning
In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use generative adversarial network to draw p…
BIG-bench Machine LearningDeep LearningGenerative Adversarial NetworkPrivacy PreservingConstructing Runge-Kutta Methods with the Use of Artificial Neural Networks
A methodology that can generate the optimal coefficients of a numerical method with the use of an artificial neural network is presented in this work. The network can be designed to produce a finite difference algorithm …
Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks
Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge th…
Can artificial neural networks supplant the polygene risk score for risk prediction of complex disorders given very large sample sizes?
Genome-wide association studies (GWAS) provide a means of examining the common genetic variation underlying a range of traits and disorders. In addition, it is hoped that GWAS may provide a means of differentiating affec…
Privacy-Utility Trade-offs in Neural Networks for Medical Population Graphs: Insights from Differential Privacy and Graph Structure
We initiate an empirical investigation into differentially private graph neural networks on population graphs from the medical domain by examining privacy-utility trade-offs at different privacy levels on both real-world…