Skip to main content

Safe learning

AGI Safety Literature Review

Everitt. Lea & Hutter (2018)

Category
Risk Domain

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

"AGIs should avoid making fatal mistakes during the learning phase. Subproblems include safe exploration and distributional shift (DeepMind, OpenAI), and continual learning (Berkeley)."(p. 9)

Other risks from Everitt. Lea & Hutter (2018) (8)