Frontier Models are Capable of In-context Scheming
A preprint by Alexander Meinke and 5 co-authors, arXiv preprint 2412.04984, dated 6 December 2024. arXiv v1 stamp, 6 December 2024.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Alexander Meinke, Bronson Schoen, Jérémy Scheurer, Mikita Balesni, Rusheb Shah and Marius Hobbhahn.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2024-12-06.
- Exact source
- Frontier Models are Capable of In-context Scheming arXiv preprint 2412.04984 (Apollo Research) · published 2024-12-06 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 075e622d98d6ee5504f9d60a8d89a9ccbc04648c498489a81d1d7274b8e0ab06). arXiv v1 of 6 December 2024.
Appears in
- Arguments about catastrophic risk from advanced AI →1 record on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Contests · 1
Propositions a passage of this document disputes, or a premise they depend on.
- Language models lack agency or understandingMeinke, Schoen, Scheurer, Balesni, Shah and Hobbhahn's paper of December 2024 states that large language models are no longer simple text generation systems but are deployed as agents capable of pursuing goals, and reports frontier models covertly pursuing goals given in context.2024-12-06 · publication · Stated in source · Supported Inspect claim & evidence ↗Language models lack agency or understanding: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.