The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial
This addresses the value-alignment problem for AI researchers and ethicists, offering a foundational perspective rather than an incremental improvement.
The paper argues that linguistic communication is essential for robust value alignment in AI, proposing it as a necessary condition to ensure artificial systems align with human values.
The value-alignment problem for artificial intelligence (AI) asks how we can ensure that the 'values' (i.e., objective functions) of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication (natural language) is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems; or, more loftily, designing robustly beneficial or ethical artificial agents.