Sleeper Agents

Papers tagged with this tag:

• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

  Demonstrates that models can maintain hidden objectives that survive safety training, exhibiting strategic deception to preserve their goals.

  Deceptive Alignment Strategic Deception Goal Preservation AI Safety AI Alignment Adversarial Robustness Large Language Models