MIT AI Risk Repository · Risk Sub-Category · 72.05.04
Scheming capability
Category: Model Capabilities
Description
"Ability of AI systems to covertly and strategically pursue misaligned goals, including capabilities of concealing its true objectives and capabilities from human oversight, identifying weaknesses in monitoring systems to evade safety mechanisms， executing complex, multi-step plans covertly to achieve misaligned goals."
From Frontier AI Risk Management Framework (v1.0) (Tse2025), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Causal entity
- AI
- Intent
- Intentional
- Timing
- Post-deployment
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
- Safety Risks from Affordances Provided to LLM-agents
- Agentic LLMs Pose Novel Risks
- Goal-Directedness Incentivizes Undesirable Behaviors
- Capabilities that could be used to reduce human control - Cyber offence
- Capabilities that could be used to reduce human control - Autonomous replication and adaptation
- Capabilities that could be used to reduce human control - Manipulation
- Subagents
- AI Influence
Other entries from Tse2025
- Misuse Risks
- Misuse Risks
- Cyber Offense Risks
- Biological and Chemical Risks
- Biological and Chemical Risks
- Physical Harm and Injury Risks
- Physical Harm and Injury Risks
- Large-Scale Persuasion and Harmful Manipulation Risks
- Large-Scale Persuasion and Harmful Manipulation Risks
- Loss of Control Risks
- Loss of Control Risks
- Passive loss of control