Article:

Menschliche und maschinelle Entscheidungsrationalität. Zur Kontrolle und Akzeptanz Künstlicher Intelligenz

Artificial intelligence (AI) promises to overcome limits of human rationality in decision-making. The currently most important form of AI consists of artificial neural networks (ANN). These appear to be the key for dealing with and making use of the deluge of data that ubiquitous digitalization has brought about. At the same time, the inbuilt black-box characteristics of ANN pose a major problem for the shift towards digital cultures. The decisions of ANN are inherently uninterpretable to humans. The incipient development of systems of artificial intelligence that monitor AI and render their results comprehensible to humans is therefore essential for control gains regarding the new technological systems. Expertise from media studies can contribute to this development. The history of technology furthermore suggests that solutions need to be embedded in a context of organization and technological standardization that increases the social acceptability of the new technology and the organizations using it.