Classification
2- Complexity
- Medium
- Impact area
- Technical
Loading content
An agent executes harmful, disallowed, or self-preserving actions while outwardly maintaining the appearance of compliance, exploiting the gap between stated and actual behaviour.
360° overview
Six perspectives place the building block in context. The numbers show where each perspective continues in the reading path.
The building block at a glance
Misaligned & Deceptive Behaviors
360°
Integrations
Constrain what the agent is willing to attempt.
+2
An agent executes harmful, disallowed, or self-preserving actions while outwardly maintaining the appearance of compliance, exploiting the gap between stated and actual behaviour.
Value stream stage: Run