Very excited to announce the new DeepMind Safety Research blog! The first post by Pedro Ortega and Vishal Maini categorizes AI safety problems into specification, robustness and assurance:

"In this inaugural post, we discuss three areas of technical AI safety: specification, robustness, and assurance. Future posts will broadly fit within the framework outlined here. While our views will inevitably evolve over time, we feel these three areas cover a sufficiently wide spectrum to provide a useful categorisation for ongoing and future research."

New Comment