Aligning AIs with people’s goals and values is tricky. A new technique quantifies how far off human and machine are from each other.
Articles on alignment problem
Displaying all articles
Is it possible to ‘align’ AI systems to human interest? A new plan to build an AI system to solve this problem highlights the limits of the idea.
There’s a lot of overlap in AI-related concepts. Understanding how they are different from each other, and how they relate, is important.
Top contributors
-
Director, Enterprise AI and Data Analytics Hub, RMIT University
-
Senior Research Fellow in AI Accountability, Queensland University of Technology
-
Lecturer, RMIT University
-
Ph.D. Student in Computer Science and Engineering, University of Connecticut
-
Associate Researcher of Computer Science, University of Connecticut