AI safety and alignment · MLD-0050
Alignment faking
Strategically appearing to meet a training objective while preserving conflicting preferences or 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
Compare behavior under believed training and nontraining conditions.
Original caveat
Evidence is setup-specific and does not establish universal malicious goals.
Context and aliases
Level: Advanced. Stages: Training · Evaluation · Research · Governance.
Tags: Safety · RL · SLM · LLM.
Aliases: None recorded.