Anthropomorphic reasoning about neuromorphic AGI safety. Issue 6 (2nd November 2017)

• Record Type: Journal Article
• Authors: Jilk, David J.; Herd, Seth J.; Read, Stephen J.; O'Reilly, Randall C.
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 29:Issue 6(2017)
• Page Start: 1337
• Page End: 1351
• Publication Date: 2017-11-02
• Subjects: Artificial general intelligence -- neuroscience -- neuromorphic AGI -- AI safety; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2017.1354081
• Languages: English
• ISSNs: 0952-813X

Abstract

Abstract: One candidate approach to creating artificial general intelligence (AGI) is to imitate the essential computations of human cognition. This process is sometimes called 'reverse-engineering the brain' and the end product called 'neuromorphic.' We argue that, unlike with other approaches to AGI, anthropomorphic reasoning about behaviour and safety concerns is appropriate and crucial in a neuromorphic context. Using such reasoning, we offer some initial ideas to make neuromorphic AGI safer. In particular, we explore how basic drives that promote social interaction may be essential to the development of cognitive capabilities as well as serving as a focal point for human-friendly outcomes.