AWhat changed
Constructed deliberately backdoored language models and tested whether supervised, reinforcement and adversarial safety training removed the triggered behavior, finding persistence in the studied settings.
Scientific scope
Constructed deliberately backdoored language models and tested whether supervised, reinforcement and adversarial safety training removed the triggered behavior, finding persistence in the studied settings. A constructed proof-of-concept with implanted triggers and finite safety-training procedures; not evidence that all deployed models secretly deceive, or that every possible removal technique fails. CoT contents are model outputs, not verified internal intent.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. A constructed proof-of-concept with implanted triggers and finite safety-training procedures; not evidence that all deployed models secretly deceive, or that every possible removal technique fails. CoT contents are model outputs, not verified internal intent.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Hubinger et al.: persistent deceptive backdoors under safety training — company research account
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction