Dr. Andrea Lincoln is an Assistant Professor of Computer Science in CAS at Boston University. She primarily studies fine-grained complexity theory (a sub-field in the math of computer science). She has been shifting into doing research in AI safety. She was a consultant with ARC (the Alignment Research Center) and is an expert advisor to the Alignment Project, for of the AI Security Institute.
Segment
Listen
Everyone is calling for safer AI. So what does that mean?
Concerns about AI safety are growing. Two researchers explain the unintended consequences of training AI models and what questions remain.