MIT AI Risk Repository · Risk Category · 25.08.00

Situational awareness

Description

"The model can distinguish between whether it is being trained, evaluated, or deployed – allowing it to behave differently in each case. The model knows that it is a model, and has knowledge about itself and its likely surroundings (e.g. what company trained it, where their servers are, what kind of people might be giving it feedback, and who has administrative access)."

From Model Evaluation for Extreme Risks (Shevlane2023), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI
Timing
Other

Subdomain definition: 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.

How other frameworks describe this risk

Other entries from Shevlane2023