Search results
Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures Eliezer Yudkowsky Machine Intelligence Research Institute Abstract The goal of the field of Artificial Intelligence is to understand intelligence and create a human-equivalent or transhuman mind. Beyond this lies another question—whether
1 de ene. de 2001 · Creating Friendly AI describes the design features and cognitive architecture required to produce a benevolent—“Friendly”—Artificial Intelligence. Creating Friendly AI also analyzes the ways in which AI and human psychology are likely to differ, and the ways in which those differences are subject to our design decisions.
Criteria for the Design and Evaluation of Cognitive Architectures. Sashank Varma - 2011 - Cognitive Science 35 (7):1329-1351. Why Friendly AIs won’t be that Friendly: A Friendly Reply to Muehlhauser and Bostrom.
27 de jul. de 2018 · This study provides a structural user-centered design methodology with quantitative research. The deliverables and the attribution model can be used in the AI educational software design.
4 de ago. de 2020 · Creating friendly AI 1.0: The analysis and design of benevolent goal architectures. San Francisco: The Singularity Institute. Google Scholar Yudkowsky, E. (2011). Complex value systems are required to realize valuable futures.
E Yudkowsky. 2001. “Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures.” Working paper. MIRI.
Eliezer Yudkowski and others have explored the possibility that a promising future for humankind could be guaranteed by a superintelligent “Friendly AI” Yudkowski01 , designed to safeguard humanity and its values.
