7.2 > AI possessing dangerous capabilities AI Risks
AI Risk Domain7.2 > AI possessing dangerous capabilities groups 76 AI risk records under 7. AI System Safety, Failures, & Limitations.
Overview
A group of related risks from the AI Risk database.
Records76Records included in this view.
SourcePublicBuilt from public source data.
ModeStaticPrepared as a ready-to-read page.
Domain details
How the MIT AI Risk Repository groups these records.
Domain7. AI System Safety, Failures, & Limitations
Subdomain7.2 > AI possessing dangerous capabilities
Risks76
Top categoryDouble edge components
Top timing2 - Post-deployment
Risk records
Individual risks in this group.
Top 10 of 76View all risks →
2 - Unintentional2 - Post-deployment
2 - Unintentional2 - Post-deployment
1 - Intentional2 - Post-deployment
3 - Other1 - Pre-deployment
Showing 4 of 10
Source evidence
Original public records and references for this page.
Original source
Original source links
Open the public records and source datasets used for this page.