Record summary
A quick snapshot of what this page covers.
Records97Records included in this view.
SourcePublicBuilt from public source data.
ModeStaticPrepared as a ready-to-read page.
Domain summary
A group of related risks from the AI Risk database.
97 AI risk records are grouped under 7.1 > AI pursuing its own goals in conflict with human goals or values in 7. AI System Safety, Failures, & Limitations.
Domain7. AI System Safety, Failures, & Limitations
Subdomain7.1 > AI pursuing its own goals in conflict with human goals or values
Risks97
Top categoryAlignment failures in existing ML systems
Top timing3 - Other
Risk records
Individual risks in this group.
A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions
2 - Unintentional3 - Other
A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions
3 - Other2 - Post-deployment
A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values
2 - Unintentional3 - Other
A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values
1 - Intentional3 - Other
A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values
1 - Intentional3 - Other
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
2 - Unintentional3 - Other
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
3 - Other2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional3 - Other
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
2 - Unintentional3 - Other
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional3 - Other
A framework for ethical Ai at the United Nations
1 - Intentional3 - Other
AGI Safety Literature Review
3 - Other2 - Post-deployment
AGI Safety Literature Review
3 - Other2 - Post-deployment
AGI Safety Literature Review
2 - Unintentional3 - Other
AI Alignment: A Comprehensive Survey
3 - Other1 - Pre-deployment
AI Alignment: A Comprehensive Survey
1 - Intentional1 - Pre-deployment
AI Alignment: A Comprehensive Survey
1 - Intentional1 - Pre-deployment
AI Alignment: A Comprehensive Survey
1 - Intentional1 - Pre-deployment
AI Alignment: A Comprehensive Survey
2 - Unintentional1 - Pre-deployment
AI Alignment: A Comprehensive Survey
1 - Intentional3 - Other
AI Alignment: A Comprehensive Survey
3 - Other3 - Other
AI Alignment: A Comprehensive Survey
1 - Intentional1 - Pre-deployment
AI Alignment: A Comprehensive Survey
1 - Intentional3 - Other
AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures
3 - Other2 - Post-deployment
AI Safety Governance Framework
1 - Intentional2 - Post-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
2 - Unintentional3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
2 - Unintentional2 - Post-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional2 - Post-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
2 - Unintentional3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
3 - Other1 - Pre-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
3 - Other3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional3 - Other
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional2 - Post-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
1 - Intentional2 - Post-deployment
Advancing AI Governance: A Literature Review of Problems, Options, and Proposals
3 - Other2 - Post-deployment
An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance
1 - Intentional1 - Pre-deployment
An Overview of Catastrophic AI Risks
1 - Intentional3 - Other
An Overview of Catastrophic AI Risks
1 - Intentional3 - Other
An Overview of Catastrophic AI Risks
1 - Intentional3 - Other
An Overview of Catastrophic AI Risks
1 - Intentional3 - Other
An Overview of Catastrophic AI Risks
1 - Intentional3 - Other
Capabilities and Risks from Frontier AI
3 - Other2 - Post-deployment
Cataloguing LLM Evaluations
1 - Intentional3 - Other
Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks
3 - Other2 - Post-deployment
Examining the differential risk from high-level artificial intelligence and the question of control
1 - Intentional3 - Other
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.