What is the MIT AI Risk Repository?

A living database of AI risks extracted from 74 frameworks, taxonomies and papers, classified by a causal taxonomy (entity, intent, timing) and a domain taxonomy (7 domains, 24 subdomains). Published by the MIT AI Risk Initiative under CC BY 4.0.

Can I download the filtered risk list?

Yes. Apply filters and use Export CSV or Export JSON; the file carries the source, licence and citation so it can be reused with attribution.

MIT AI Risk Repository

Browse AI risks

Name: MIT AI Risk Repository: AI Risk Database (browseable copy)
Creator: MIT AI Risk Initiative
License: https://creativecommons.org/licenses/by/4.0/

12 risk entries extracted from 74 frameworks, coded by domain, subdomain, causal entity, intent and timing. Filter, then export the current selection with its licence and citation attached.

Export CSV Export JSON

12 entries

53.01.00 · Risk Category

Alignment failures in existing ML systems

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Unintentional Other
53.01.01 · Risk Sub-Category

Alignment failures in existing ML systems

Faulty reward functions in the wild

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 Human Unintentional Post-deployment
53.01.02 · Risk Sub-Category

Alignment failures in existing ML systems

Specification gaming

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Other
53.01.03 · Risk Sub-Category

Alignment failures in existing ML systems

Reward model overoptimization

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Other
53.01.04 · Risk Sub-Category

Alignment failures in existing ML systems

Instrumental convergence

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Post-deployment
53.01.05 · Risk Sub-Category

Alignment failures in existing ML systems

Goal misgeneralization

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Unintentional Other
53.01.06 · Risk Sub-Category

Alignment failures in existing ML systems

Inner misalignment

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Other Pre-deployment
53.01.07 · Risk Sub-Category

Alignment failures in existing ML systems

Language model misalignment

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Other Other
53.02.03 · Risk Sub-Category

Dangerous capabilities in AI systems

Acquisition of goals to seek power and control

"cases where AI systems converge on optimal policies of seeking power over their environment;135"

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Other
53.03.01 · Risk Sub-Category

Direct catastrophe from AI

Existential disaster because of misaligned superintelligence or power-seeking AI

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Post-deployment
53.03.03 · Risk Sub-Category

Direct catastrophe from AI

Extreme “suffering risks” because of a misaligned system

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Intentional Post-deployment
53.03.04 · Risk Sub-Category

Direct catastrophe from AI

Existential disaster because of conflict between AI systems and multi-system interactions

-

From Advancing AI Governance: A Literature Review of Problems, Options, and Proposals (Maas2023)

Domain 7 7.1 AI Other Post-deployment

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.