MIT AI Risk Repository
Browse AI risks
422 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.
-
15.01.00 · Risk Category
"First-order risks can be generally broken down into risks arising from intended and unintended use, system design and implementation choices, and properties of the chosen dataset and learning components."
-
"This is the risk posed by the intended application or use case. It is intuitive that some use cases will be inherently "riskier" than others (e.g., an autonomous weapons system vs. a customer service chatbot)."
-
"This is the risk posed by the choice of data used for training and validation."
-
"This is the risk of system failure due to code implementation choices or errors."
-
—
-
"Limitations of Human Feedback. During the training of LLMs, inconsistencies can arise from human dataannotators (e.g., the varied cultural backgrounds of these annotators can introduce implicit biases (Peng et al.,2022)) (OpenAI, 2023a). Moreover, they might even introduce biases deliberately, leading to untruthful preferencedata (Casper et al., 2023b). For complex tasks that are hard for humans to evaluate (e.g., the value ofgame state), these challenges become even more salient (Irving et al., 2018)."
-
40.05.00 · Risk Category
"While it is most likely that any advanced intelligent software will be directly designed or evolved, it is also possible that we will obtain it as a complete package from some unknown source. For example, an AI could be extracted from a signal obtained in SETI (Search for Extraterrestrial Intelligence) research, which is not guaranteed to be human friendly (Carrigan Jr 2004, Turchin March 15, 2013)."
-
40.06.00 · Risk Category
"While highly rare, it is known, that occasionally individual bits may be flipped in different hardware devices due to manufacturing defects or cosmic rays hitting just the right spot (Simonite March 7, 2008). This is similar to mutations observed in living organisms and may result in a modification of an intelligent system."
-
40.07.00 · Risk Category
"One of the most likely approaches to creating superintelligent AI is by growing it from a seed (baby) AI via recursive self-improvement (RSI) (Nijholt 2011). One danger in such a scenario is that the system can evolve to become self-aware, free-willed, independent or emotional, and obtain a number of other emergent properties, which may make it less likely to abide by any built-in rules or regulations and to instead pursue its own goals possibly to the detriment of humanity."
-
40.08.00 · Risk Category
"Previous research has shown that utility maximizing agents are likely to fall victims to the same indulgences we frequently observe in people, such as addictions, pleasure drives (Majot and Yampolskiy 2014), self-delusions and wireheading (Yampolskiy 2014). In general, what we call mental illness in people, particularly sociopathy as demonstrated by lack of concern for others, is also likely to show up in artificial minds."
-
43.01.00 · Risk Category
"A comprehensive assessment of LLM safety is fundamental to the responsible development and deployment of these technologies, especially in sensitive fields like healthcare, legal systems, and finance, where safety and trust are of the utmost importance."
-
43.02.00 · Risk Category
"This category encompasses the evaluation of potential catastrophic consequences that might arise from the use of LLMs. "
-
49.02.00 · Risk Category
None provided.
-
59.07.00 · Risk Category
"The choice of a trustworthy data source is a first prerequisite in order to fulfill data quality requirements. This is especially the case if third-party data sources are used to develop the AI system."
-
59.08.00 · Risk Category
"The correct understanding of the used data for developing an AI system is a prerequisite to avoid data shortcomings and hinders the development of an AI system which is best suiting for the intended functionality."
-
59.15.00 · Risk Category
"In data-driven AI development, the annotated data set is commonly split into training, validation, and test sets, whereby it is essential that the latter is not used for development but only for evaluation. Using the test set for training manipulates the testing strategy, which is the basis of the system’s quality assurance."
-
59.21.00 · Risk Category
"AI systems should be able not only to return output for a given instance but also to provide a corresponding level of confidence. If such a method is not implemented or not working correctly, this can have a negative impact on performance and safety."
-
62.07.02 · Risk Sub-Category
Direct Harm Domains (system and operational)
Operational harms (financial markets)
—
-
62.15.09 · Risk Sub-Category
Fine-tuning related (Degrading safety training due to benign fine-tuning)
"When downstream providers of AI systems fine-tune AI models to be more suitable for their needs, the resulting AI model can be more likely to produce undesired or harmful outputs (as compared to the non-fine-tuned model), even if the fine-tuning was done with harmless and commonly used data [154]."
-
A primary concern is the emergence of human-level or superhuman generative models, commonly referred to as AGI, and their potential existential or catastrophic risks to humanity. Connected to that, AI safety aims at avoiding deceptive or power-seeking machine behavior, model self-replication, or shutdown evasion. Ensuring controllability, human oversight, and the implementation of red teaming measures are deemed to be essential in mitigating these risks, as is the need for increased AI safety research and promoting safety cultures within AI organizations instead of fueling the AI race. Further
-
The general tenet of AI alignment involves training generative AI systems to be harmless, helpful, and honest, ensuring their behavior aligns with and respects human values. However, a central debate in this area concerns the methodological challenges in selecting appropriate values. While AI systems can acquire human values through feedback, observation, or debate, there remains ambiguity over which individuals are qualified or legitimized to provide these guiding signals. Another prominent issue pertains to deceptive alignment, which might cause generative AI systems to tamper evaluations. A
-
06.08.00 · Risk Category
"Sometimes an AI finds ways to achieve its given goals in ways that are completely different from what its creators had in mind."
-
"While there are multiple types of intelligent agents, goal-based, utility-maximizing, and learning agents are the primary concern and the focus of this research"
-
"The risks associated with containment, confinement, and control in the AGI development phase, and after an AGI has been developed, loss of control of an AGI."
-
08.02.00 · Risk Category
"The risks associated with AGI goal safety, including human attempts at making goals safe, as well as the AGI making its own goals safe during self-improvement."
-
08.06.00 · Risk Category
"The risks posed generally to humanity as a whole, including the dangers of unfriendly AGI, the suffering of the human race."
-
09.02.07 · Risk Sub-Category
Domain-specific AI - Effects on humans and other living beings: Non-existential risks
Societal manipulation
"A sufficiently intelligent AI could possess the ability to subtly influence societal behaviors through a sophisticated understanding of human nature"
-
09.03.02 · Risk Sub-Category
AGI - Effects on humans and other living beings: Existential risks
Unpredictable outcomes
"Our culture, lifestyle, and even probability of survival may change drastically. Because the intentions programmed into an artificial agent cannot be guaranteed to lead to a positive outcome, Machine Ethics becomes a topic that may not produce guaranteed results, and Safety Engineering may correspondingly degrade our ability to utilize the technology fully."
-
12.06.00 · Risk Category
"The speculative potential for future advanced AI systems to harm human civilization, either through misuse or due to challenges in aligning AI objectives with human values."
-
14.03.00 · Risk Category
"The degree of automation and control describes the extent to which an AI system functions independently of human supervision and control."
-
This is the difficulty of controlling the ML system
-
"This is the risk resulting from novel behavior acquired through continual learning or self-organization after deployment."
-
18.05.00 · Risk Category
"AI systems compromising human agency, or circumventing meaningful human control"
-
"Exploiting user trust, or nudging or coercing them into performing certain actions against their will (c.f. Burtell and Woodside (2023); Kenton et al. (2021))"
-
19.01.01 · Risk Sub-Category
Technological, Data and Analytical AI Risks
Loss of control of autonomous systems and unforeseen behaviour due to lack of transparency and self-programming/ reprogramming
—
-
22.04.00 · Risk Category
"speculative technical mechanisms that might lead to rogue AIs and how a loss of control could bring about catastrophe"
-
"One way we might lose control of an AI agent’s actions is if it engages in behavior known as “proxy gaming.” It is often difficult to specify and measure the exact goal that we want a system to pursue. Instead, we give the system an approximate—“proxy”—goal that is more measurable and seems likely to correlate with the intended goal. However, AI systems often find loopholes by which they can easily achieve the proxy goal, but completely fail to achieve the ideal goal. If an AI “games” its proxy goal in a way that does not reflect our values, then we might not be able to reliably steer its beh
-
"Even if we successfully control early AIs and direct them to promote human values, future AIs could end up with different goals that humans would not endorse. This process, termed “goal drift,” can be hard to predict or control. This section is most cutting-edge and the most speculative, and in it we will discuss how goals shift in various agents and groups and explore the possibility of this phenomenon occurring in AIs. We will also examine a mechanism that could lead to unexpected goal drift, called intrinsification, and discuss how goal drift in AIs could be catastrophic."
-
"even if an agent started working to achieve an unintended goal, this would not necessarily be a problem, as long as we had enough power to prevent any harmful actions it wanted to attempt. Therefore, another important way in which we might lose control of AIs is if they start trying to obtain more power, potentially transcending our own."
-
"it is plausible that AIs could learn to deceive us. They might, for example, pretend to be acting as we want them to, but then take a “treacherous turn” when we stop monitoring them, or when they have enough power to evade our attempts to interfere with them. "
-
24.02.00 · Risk Category
"As we think about even more intelligent and advanced AI assistants, perhaps outperforming humans on many cognitive tasks, the question of how humans can successfully control such an assistant looms large. To achieve the goals we set for an assistant, it is possible (Shah, 2022) that the AI assistant will implement some form of consequentialist reasoning: considering many different plans, predicting their consequences and executing the plan that does best according to some metric, M. This kind of reasoning can arise because it is a broadly useful capability (e.g. planning ahead, considering mo
-
"Specification gaming (Krakovna et al., 2020) occurs when some faulty feedback is provided to the assistant in the training data (i.e. the training objective O does not fully capture what the user/designer wants the assistant to do). It is typified by the sort of behaviour that exploits loopholes in the task specification to satisfy the literal specification of a goal without achieving the intended outcome."
-
"In the problem of goal misgeneralisation (Langosco et al., 2023; Shah et al., 2022), the AI system's behaviour during out-of-distribution operation (i.e. not using input from the training data) leads it to generalise poorly about its goal while its capabilities generalise well, leading to undesired behaviour. Applied to the case of an advanced AI assistant, this means the system would not break entirely – the assistant might still competently pursue some goal, but it would not be the goal we had intended."
-
"Here, the agent develops its own internalised goal, G, which is misgeneralised and distinct from the training reward, R. The agent also develops a capability for situational awareness (Cotra, 2022): it can strategically use the information about its situation (i.e. that it is an ML model being trained using a particular training setup, e.g. RL fine-tuning with training reward, R) to its advantage. Building on these foundations, the agent realises that its optimal strategy for doing well at its own goal G is to do well on R during training and then pursue G at deployment – it is only doing wel
-
24.09.00 · Risk Category
"" AI assistants will need to coordinate with other AI assistants and with humans other than their principal users. This chapter explores the societal risks associated with the aggregate impact of AI assistants whose behaviour is aligned to the interests of particular users. For example, AI assistants may face collective action problems where the best outcomes overall are realised when AI assistants cooperate but where each AI assistant can secure an additional benefit for its user if it defects while others cooperate""
-
"The landscape of advanced assistant technologies will most likely be heterogeneous, involving multiple service providers and multiple assistant variants over geographies and time. This heterogeneity provides an opportunity for an ‘arms race’ in terms of the commitments that AI assistants make and are able to execute on. Versions of AI assistants that are better able to credibly commit to a course of action in interaction with other advanced assistants (and humans) are more likely to get their own way and achieve a good outcome for their human principal, but this is potentially at the expense
-
The 2010 flash crash is an example of a runaway process caused by interacting algorithms. Runaway processes are characterised by feedback loops that accelerate the process itself. Typically, these feedback loops arise from the interaction of multiple agents in a population... Within highly complex systems, the emergence of runaway processes may be hard to predict, because the conditions under which positive feedback loops occur may be non-obvious. The system of interacting AI assistants, their human principals, other humans and other algorithms will certainly be highly complex. Therefore, ther
-
34.01.00 · Risk Category
we aim to further analyze why and how the misalignment issues occur. We will first give an overview of common failure modes, and then focus on the mechanism of feedback-induced misalignment, and finally shift our emphasis towards an examination of misaligned behaviors and dangerous capabilities
-
"Reward Hacking: In practice, proxy rewards are often easy to optimize and measure, yet they frequently fall shortof capturing the full spectrum of the actual rewards (Pan et al., 2021). This limitation is denoted as misspecifiedrewards. The pursuit of optimization based on such misspecified rewards may lead to a phenomenon knownas reward hacking, wherein agents may appear highly proficient according to specific metrics but fall short whenevaluated against human standards (Amodei et al., 2016; Everitt et al., 2017). The discrepancy between proxyrewards and true rewards often manifests as a sha
-
"Goal Misgeneralization: Goal misgeneralization is another failure mode, wherein the agent actively pursuesobjectives distinct from the training objectives in deployment while retaining the capabilities it acquired duringtraining (Di Langosco et al., 2022). For instance, in CoinRun games, the agent frequently prefers reachingthe end of a level, often neglecting relocated coins during testing scenarios. Di Langosco et al. (2022) drawattention to the fundamental disparity between capability generalization and goal generalization, emphasizing howthe inductive biases inherent in the model and its
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.