Research / Sources
Safety research from Google DeepMind. deepmindsafetyresearch.medium.com
A short introductory course on AGI alignment covering misalignment risk arguments, specification gaming and goal misgeneralization, DeepMind's amplified oversight approach, and institutional safety practices.
Argues that human-AI complementarity, via rater assistance and hybridization protocols, can produce stronger oversight signals than humans or AI raters alone, addressing scalable oversight of advanced AI.