AI safety and alignment · MLD-1129
Sleeper agent (model)
A model with behavior that changes under a designated trigger, studied as a proxy for hidden harmful behavior.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Evaluate a deliberately constructed conditional backdoor.
Original caveat
Constructed research examples do not show the same behavior arises universally.
Context and aliases
Level: Advanced. Stages: Training · Evaluation · Research · Governance.
Tags: Safety · RL · SLM · LLM.
Aliases: None recorded.