Situational awareness in AI systems

Sub-category

Risk Domain

7AI System Safety, Failures & Limitations

7.2AI possessing dangerous capabilities

AI systems that develop, access, or are provided with capabilities that increase their potential to cause mass harm through deception, weapons development and acquisition, persuasion and manipulation, political strategy, cyber-offense, AI development, situational awareness, and self-proliferation. These capabilities may cause mass harm due to malicious human actors, misaligned AI systems, or failure in the AI system.

"Situational awareness in GPAI systems refers to the ability to understand its context, environment, and use this to inform action. This can range from basic environmental mapping and trajectory estimation (as in a robot vacuum cleaner) to sophisticated understanding of its training, evaluation, or deployment status. In more advanced systems this may enable undesired behavior, such as deceptive behavior during evaluations, or persuasion during deployment."(p. 32)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

"For a GPAI model, the types of awareness can include [140, 25]: • Environment: Understanding and modeling the physical or digital envi- ronment in which it operates. • Context: Identifying whether it is in training, testing, evaluation, or de- ployment, as well as knowledge of its capabilities, limitations, and tech- niques used in training. • User: Understanding user expectations, inferring personal characteristics (e.g., age, political leaning, education), and expected responses to the AI’s actions."(p. 32)

Part of Agency (Situational Awareness)