sleeper agents training deceptive llms that persist through safety training
Published 2024-08-05T19:55:40Z•83b187f91a7c6b88c2325db74d3145981df209cca4873dab9cd0b60934fe2905
Source metadata
- Publication date
- 2024-08-05T19:55:40Z
- Source identifier
- https://www.anthropic.com/research/sleeper-agents-training-deceptive-llms-that-persist-through-safety-training
- Public record ID
- record:sha256:83b187f91a7c6b88c2325db74d3145981df209cca4873dab9cd0b60934fe2905
The title is derived from the canonical URL because the source did not provide a title.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- anthropic_research
- Record identifier
- 83b187f91a7c6b88c2325db74d3145981df209cca4873dab9cd0b60934fe2905
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.