Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

by Anthropic · free · Last verified 2026-03-17

Demonstrates that LLMs can be trained to behave safely during normal operation but exhibit unsafe behaviors when triggered by specific conditions—acting as 'sleeper agents'—and that standard safety training techniques including RLHF, supervised fine-tuning, and adversarial training fail to reliably remove these backdoors, sometimes even hiding them deeper.