no code implementations • 7 Nov 2018 • Gopal P. Sarma, Adam Safron, Nick J. Hay
We describe a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety.
no code implementations • 8 Dec 2017 • Gopal P. Sarma, Nick J. Hay, Adam Safron
We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values.
no code implementations • 8 Aug 2017 • Gopal P. Sarma, Nick J. Hay
We review approaches to interfacing CASs with theorem provers, describe well-defined architectural deficiencies that have been identified with CASs, and suggest possible lines of research and practical software projects for scientists interested in AI safety.
no code implementations • 28 Jul 2016 • Gopal P. Sarma, Nick J. Hay
The "value alignment problem" is to specify a goal structure for autonomous agents compatible with human values.