We are now the AI Security Institute
Please enable javascript for this website.
AISI brand artwork

How can safety cases be used to help with frontier AI safety?

Safety Cases

February 10, 2025

Our new papers show how safety cases can help AI developers turn plans in their safety frameworks into action

Safety case template for ‘inability’ arguments

Safety Cases

November 14, 2024

How to write part of a safety case showing a system does not have offensive cyber capabilities

Safety cases at AISI

Safety Cases

August 23, 2024

As a complement to our empirical evaluations of frontier AI models, AISI is planning a series of collaborations and research projects sketching safety cases for more advanced models than exist today, focusing on risks from loss of control and autonomy. By a safety case, we mean a structured argument that an AI system is safe within a particular training or deployment context.