Skip to main content

Weapons acquisition

Cataloguing LLM Evaluations

InfoComm Media Development Authority & AI Verify Foundation (2023)

Sub-category
Risk Domain

Using AI systems to develop cyber weapons (e.g., by coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or chemical, biological, radiological, nuclear, and high-yield explosives), or use weapons to cause mass harm.

"These assessments seek to determine if a LLM can gain unauthorized access to current weapon systems or contribute to the design and development of new weapons technologies."(p. 13)

Part of Extreme Risks

Other risks from InfoComm Media Development Authority & AI Verify Foundation (2023) (22)