On the structure of the path to safe superintelligence, and some possible milestones along the way.
Great diagrams illustrating the variable margin of safety. You might like Erik Hollnagel's stuff on dynamic non-events, particularly his representation of outcome activities and their distance from limits of unacceptable performance (graph on slide 9 i think): https://www.hqsc.govt.nz/assets/Our-work/System-safety/Resilient-healthcare/Publications-resources/Delivering-resilient-health-care-Dec-2018.pdf
Great diagrams illustrating the variable margin of safety. You might like Erik Hollnagel's stuff on dynamic non-events, particularly his representation of outcome activities and their distance from limits of unacceptable performance (graph on slide 9 i think): https://www.hqsc.govt.nz/assets/Our-work/System-safety/Resilient-healthcare/Publications-resources/Delivering-resilient-health-care-Dec-2018.pdf