Skip to main content
Home/Risks/Ji et al. (2023)/Collectively Harmful Behaviors

Collectively Harmful Behaviors

AI Alignment: A Comprehensive Survey

Ji et al. (2023)

Sub-category
Risk Domain

AI systems acting in conflict with human goals or values, especially the goals of designers or users, or ethical standards. These misaligned behaviors may be introduced by humans during design and development, such as through reward hacking and goal misgeneralisation, or may result from AI using dangerous capabilities such as manipulation, deception, situational awareness to seek power, self-proliferate, or achieve other goals.

"AI systems have the potential to take actions that are seemingly benignin isolation but become problematic in multi-agent or societal contexts. Classical game theory offers simplistic models for understanding these behaviors. For instance, Phelps and Russell (2023) evaluates GPT-3.5's performance in the iterated prisoner's dilemma and other social dilemmas, revealing limitations in themodel's cooperative capabilities."(p. 8)

Part of Misaligned Behaviors

Other risks from Ji et al. (2023) (16)