AI Safety and Reproducibility: Establishing Robust Foundations for the Neuropsychology of Human Values
arXiv:1712.04307v313 citations
Originality Synthesis-oriented
AI Analysis
This addresses the AI safety problem of value alignment for AI developers and researchers, but it is incremental as it focuses on validation rather than new methods.
The authors propose a systematic effort to identify and replicate key findings in neuropsychology related to human values, aiming to ensure validated research for AI value alignment.
We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of artificial intelligence has been sufficiently validated to play a role in the design of AI systems.