AI Safety on English AI Terms Dictionary

Singularity studies

Sat, 18 Jul 2026 10:15:35 +0000

Definition

Singularity studies is an emerging academic discipline that investigates the implications of a hypothetical future point where artificial intelligence surpasses human intelligence, leading to uncontrollable and irreversible technological growth. It draws from philosophy, sociology, computer science, and ethics to analyze risks such as loss of human agency, economic disruption, and existential threats. Researchers in this field often debate the timeline, probability, and mitigation strategies for superintelligence, aiming to prepare humanity for profound changes in civilization structure and human identity.

Owain Evans

Sat, 18 Jul 2026 10:10:06 +0000

Definition

Owain Evans is a computer scientist and educator, currently associated with the Center for AI Safety and previously with Anthropic. He is widely recognized for his contributions to mechanistic interpretability, focusing on understanding how neural networks internally represent information. His research often involves designing benchmarks to test whether LLMs truly understand concepts or merely mimic patterns. He also creates educational content to help the community understand complex AI safety and alignment topics.

Coherent extrapolated volition

Sat, 18 Jul 2026 09:50:01 +0000

Definition

Coherent Extrapolated Volition (CEV) is a concept introduced by Eliezer Yudkowsky in the context of AI safety and alignment. It suggests that an advanced AI should not simply obey current human commands, but rather extrapolate what humans would want if they knew more, thought faster, were more the people we wished we were, and integrated more sincerely with each other. The ‘coherent’ part implies resolving contradictions in human values into a consistent utility function, aiming to maximize human flourishing based on our idealized preferences rather than our flawed immediate impulses.