Katarina Slama, PhD Katarina Slama is a research scientist at the UK AI Security Institute focused on AI safety, alignment, model evaluation, and emerging risks from advanced AI systems. She previously worked at OpenAI, including on research associated with InstructGPT, and holds a PhD from the University of California, Berkeley.
Katarina Slama, PhD Katarina Slama is a research scientist at the UK AI Security Institute focused on AI safety, alignment, model evaluation, and emerging risks from advanced AI systems. She previously worked at OpenAI, including on research associated with InstructGPT, and holds a PhD from the University of California, Berkeley.
Career
Katarina Slama, PhD holds a PhD from University of California, Berkeley.