Brief Notes on Hard Takeoff, Value Alignment, and Coherent Extrapolated Volition
Artificial Intelligence
2018-04-24 v2 Computers and Society
Machine Learning
Abstract
I make some basic observations about hard takeoff, value alignment, and coherent extrapolated volition, concepts which have been central in analyses of superintelligent AI systems.
Cite
@article{arxiv.1704.00783,
title = {Brief Notes on Hard Takeoff, Value Alignment, and Coherent Extrapolated Volition},
author = {Gopal P. Sarma},
journal= {arXiv preprint arXiv:1704.00783},
year = {2018}
}
Comments
3 pages