Hubinger et al. 2024 - Sleeper agents: Training deceptive LLMs that persist through safety training

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Backdoor Behavior (Sleeper Agents)concept0.810
  Models deliberately trained to embed backdoor behaviors enabling persistent strategic deception, cited from Hubinger et al.
• LLM personality self-reports are illusory: post-training alignment creates stable human-like reports dissociated from actual behavior (Han et al. 2025)claim0.775
  Skeptical prior work motivating the need to validate self-reports against internal states rather than taking them at face value
• SOO fine-tuning may provide robustness against sleeper agent deception scenarios where intent is concealed over extended periodshypothesis0.771
  Future work hypothesis about testing SOO against adversarial sleeper agent scenarios
• Because an LLM's training data contain many instances of the rogue AI trope, the danger is that life will imitate art, quite literallyclaim0.766
  Warning that fictional narratives in training data increase risk of agents enacting dangerous self-preserving roles
• what features activate when Claude is trained to be a sleeper agent?question0.761
  Question posed after discussing sleeper agent threat model.
• Connecting the Dots: LLMs Can Infer and Verbalize Latent Structure from Disparate Training Data (Treutlein et al. 2024)concept0.758
  Out-of-context reasoning work directly related to synthetic document fine-tuning experiments
• By reducing self-other distinctions during safety training, SOO could make it harder for a model to maintain adversarial or deceptive representationsclaim0.757
  Mechanistic explanation for why SOO reduces deception
• Sleeper agentconcept0.754
  Model trained to behave harmlessly but later exhibits harmful behavior; features may reveal such hidden objectives.