Human Control: Definitions and Algorithms
How can humans stay in control of advanced artificial intelligence systems? One proposal is corrigibility, which requires the agent to follow the instructions of a human overseer, without inappropriately influencing them. In this paper, we formally define a variant of corrigibility called shutdown instructability, and show that it implies appropriate shutdown behavior, retention of human autonomy, and avoidance of user harm. We also analyse the related concepts of non-obstruction and shutdown alignment, three previously proposed algorithms for human control, and one new algorithm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generating Scientific Definitions with Controllable Complexity
Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new ta…
RerankingGenerating Scientific Definitions with Controllable Complexity
Unfamiliar terminology and complex language can present barriers to understanding science. Natural language processing stands to help address these issues by automatically defining unfamiliar terms. We introduce a new t…
RerankingDatalism and Data Monopolies in the Era of A.I.: A Research Agenda
The increasing use of data in various parts of the economic and social systems is creating a new form of monopoly: data monopolies. We illustrate that the companies using these strategies, Datalists, are challenging the …
Towards Auditing Unsupervised Learning Algorithms and Human Processes For Fairness
Existing work on fairness typically focuses on making known machine learning algorithms fairer. Fair variants of classification, clustering, outlier detection and other styles of algorithms exist. However, an understudie…
ClassificationClusteringFairnessOutlier DetectionThe invisible power of fairness. How machine learning shapes democracy
Many machine learning systems make extensive use of large amounts of data regarding human behaviors. Several researchers have found various discriminatory practices related to the use of human-related machine learning sy…
BIG-bench Machine LearningCultural Vocal Bursts Intensity PredictionFairness