# AI Alignment Theory Course: Readings and Rapporteur Reports
A professor at UT Austin is currently teaching a brand new course called AI Alignment Theory, and the subject matter could not be more relevant to today's rapidly changing technological landscape. The course stands out as uniquely timely, with the instructor noting it is the first course they have ever taught where major, significant developments directly relevant to the material have occurred in real time, while the course was still in progress.
The blog post serves as a hub for course materials, sharing readings and rapporteur reports generated throughout the semester. These resources give readers an inside look at the academic structure being built around AI alignment theory, a field concerned with ensuring that artificial intelligence systems behave in ways that are safe and consistent with human values and intentions.
For anyone interested in the theoretical foundations of AI safety, this course and its associated materials represent an exciting window into how academia is beginning to formally engage with one of the most pressing questions of our time. The availability of readings and reports makes this a valuable resource not just for enrolled students, but for the broader community of researchers, mathematicians, and curious minds following the development of AI alignment as a rigorous field of study.