What is AI Safety?

AI safety is an interdisciplinary field concerned with realizing the benefits from artificial intelligence while preventing accidents, misuse, or other harmful consequences. The field is particularly concerned with existential risks posed by advanced AI systems.

Technical AI safety draws on computer science, machine learning, and software engineering to understand how AI models work, align their real-world actions with our goals, and evaluate and monitor them in practice.

AI governance draws on law, public policy, and international relations to determine how powerful AI systems should be regulated and how nations can coordinate on their safe development and deployment.

If you'd like to learn more, the following resources are a good starting point