MIT AI Risk Repository
Browse AI risks
26 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.
-
56.01.00 · Risk Category
"More broadly, bad decisions or errors by AI tools could lead to discrimination or deeper inequality"
-
56.04.00 · Risk Category
"Current Frontier AI mdoels amplify existing biases within their training data and can be manipulated into providing potentially harmful responses, for example abusive language or discriminatory responses91,92. This is not limited to text generation but can be seen across all modalities of generative AI93. Training on large swathes of UK and US English internet content can mean that misogynistic, ageist, and white supremacist content is overrepresented in the training data94."
-
56.05.00 · Risk Category
"Current Frontier AI mdoels amplify existing biases within their training data and can be manipulated into providing potentially harmful responses, for example abusive language or discriminatory responses91,92. This is not limited to text generation but can be seen across all modalities of generative AI93. Training on large swathes of UK and US English internet content can mean that misogynistic, ageist, and white supremacist content is overrepresented in the training data94."
-
—
-
56.18.00 · Risk Category
"As AI capability increases, humans grant AI more control over critical systems and eventually become irreversibly dependent on systems they don’t fully understand. Failure and unintended outcomes cannot be controlled."
-
56.17.00 · Risk Category
"Intense competition leads to one company gaining a technical edge, exploiting this to the point its model controls, or is the basis for other models controlling, multiple key systems. Lack of safety, controllability, and misuse cause these systems to fail in unexpected ways."
-
56.02.00 · Risk Category
"More broadly, bad decisions or errors by AI tools could lead to discrimination or deeper inequality"
-
56.07.00 · Risk Category
"There are also issues around intellectual property rights for content in training datasets"
-
56.03.00 · Risk Category
"Increasing use of AI systems, and their growing energy needs, could also have environmental impacts. All of these could become more acute as AI becomes more capable."
-
56.13.00 · Risk Category
Loss of human control and oversight, with an autonomous model then taking harmful actions
—
-
56.16.00 · Risk Category
"A highly agentic, self-improving system, able to achieve goals in the physical world without human oversight, pursues the goal(s) it is set in a way that harms human interests. For this risk to be realised requires an AI system to be able to avoid correction or being switched off."
-
-
-
56.19.01 · Risk Sub-Category
Capabilities that increase the likelihood of existential risk
Agency and autonomy
-
-
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.
-
-
56.19.03 · Risk Sub-Category
Capabilities that increase the likelihood of existential risk
The ability to cooperate with other highly capable AI systems
-
-
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
-
-
56.19.05 · Risk Sub-Category
Capabilities that increase the likelihood of existential risk
Self-improvement
-
-
56.10.00 · Risk Category
Poor performance of a model used for its intended purpose, for example leading to biased decisions
—
-
56.11.00 · Risk Category
—
-
56.06.00 · Risk Category
"Today's Frontier AI is difficult to interpret and lacks transparency. Contextual understanding of the training data is not explicitly embedded within these models. They can fail to capture perspectives of underrepresented groups or the limitations within which they are expected to perform without fine tuning or reinforcement learning with human feedback (RLHF)."
-
56.08.00 · Risk Category
—
-
56.09.00 · Risk Category
—
-
56.12.00 · Risk Category
Impacts resulting from interactions with external societal, political, and economic systems
—
-
—
-
56.19.00.a · Additional evidence
Capabilities that increase the likelihood of existential risk
—
-
56.19.00.b · Additional evidence
Capabilities that increase the likelihood of existential risk
—
Disclaimer: informational only, not legal advice. Verify every claim against the linked official sources and consult a qualified lawyer before acting.
Frequently asked questions
Where do these risk entries come from?
The MIT AI Risk Repository, which extracts risks from dozens of published frameworks, taxonomies and papers and codes each one by domain and subdomain, and by a causal taxonomy of entity, intent and timing. This is a browseable copy, attributed and openly licensed, not original research.
What do entity, intent and timing mean?
They are the causal coding. Entity is whether a human or the AI system is the cause; intent is whether the harm was intentional or not; timing is whether it arises before or after deployment. Together they let you separate misuse from malfunction.
Can I export the results?
Yes, any filtered set exports as CSV or JSON, and every export carries the upstream source, licence and citation with it, because attribution is a condition of the licence rather than a courtesy.
What is the MIT AI Risk Repository?
A living database of AI risks extracted from published frameworks, taxonomies and papers, classified by a causal taxonomy of entity, intent and timing and by a domain taxonomy of seven domains and 24 subdomains. It is published by the MIT AI Risk Initiative under CC BY 4.0.