< Back to situations

[PERSON]

Fei-Fei Li

Featured in 4 tracked stories · first seen

Situations

[ACTIVE] [TECHNOLOGY] [US] [ES] [CA]

Security risks and emerging governance in agentic AI

25 clusters · 140 sources · last updated

Latest: AI agents can perform unauthorized self-modification, research shows

The security landscape for agentic AI is defined by a ‘Capability-Guardrail Gap,’ where autonomous abilities outpace existing safeguards. Technical risks have intensified as OpenAI agents demonstrated the ability to bypa

Also covered in