claim
active
claim:auditing-agents-are-a-promising-way-to-scale-alignment-assessments-and-build-a-reliable-science-of-alignment-auditingAuditing agents are a promising way to scale alignment assessments and build a reliable science of alignment auditing
Conclusion.
Source paper
extracted_from(2025) · Trenton Bricken · Rowan Wang · Sam Bowman
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Core motivation.
- Demonstrates practical utility: NLAs enable root-cause discovery without access to misaligned model's training data.
- Systematic investigation of a model's alignment-relevant propensities.
- Downstream task validating NLA utility for model auditing; agents succeed without access to misalignment training data.
- Speculative vision.
- HHH training framework that Claude was trained with prior to experiments
- Limitation.
- Production assessment.