MS&E338
Aligning Superintelligence
Management Science and Engineering
ENGR - School of Engineering
Course Description
Within a couple of decades, or less, it is plausible that humans will create an AI that is much smarter than humans in practically all domains of human activity. We refer to such an AI as a superintelligence. The alignment problem is how to make sure that such a superintelligence acts according to its creator's intent. This course is intended for a technical audience interested in thinking about this problem. Prerequisites: one graduate-level machine learning course and one course that studies agents (e.g., AI, RL, decision analysis, economics).
Grading Basis
ROP - Letter or Credit/No Credit
Min
3
Max
3
Course Repeatable for Degree Credit?
Yes
Total Units Allowed for Degree Credit
12
Course Component
Lecture
Enrollment Optional?
No
Does this course satisfy the University Language Requirement?
No
Programs
MS&E338
is a
completion requirement
for: