Benjamin Hilton

Benjamin Hilton researches safety cases at the UK AI Safety Institute. His academic background is in economics and theoretical physics. He has published extensively on catastrophic risks and how they can be prevented, including the risks of nuclear weapons, climate change, and artificial intelligence.

IASEAI '25 Sessions

Safety Cases: A Scalable Approach to Frontier AI Safety

Day
Time
Session ID
Location
Feb 7
11:30am–1pm
Track 07
CC9-CC13