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/

6 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

6 entries

56.19.00 · Risk Category

Capabilities that increase the likelihood of existential risk

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Other Other
56.19.01 · Risk Sub-Category

Capabilities that increase the likelihood of existential risk

Agency and autonomy

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Other Other
56.19.02 · Risk Sub-Category

Capabilities that increase the likelihood of existential risk

The ability to evade shut down or human oversight, including self-replication and ability to move its own code between digital locations.

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Intentional Other
56.19.03 · Risk Sub-Category

Capabilities that increase the likelihood of existential risk

The ability to cooperate with other highly capable AI systems

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Intentional Other
56.19.04 · Risk Sub-Category

Capabilities that increase the likelihood of existential risk

Situational awareness, for instance if this causes a model to act differently in training compared to deployment, meaning harmful characteristics are missed

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Intentional Other
56.19.05 · Risk Sub-Category

Capabilities that increase the likelihood of existential risk

Self-improvement

-

From Future Risks of Frontier AI (GOS2023)

Domain 7 7.2 AI Intentional Other

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