AI safety via debate
Proposal for training through debate, including a toy experiment; no claim of reliable debate at superhuman capability.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Dates
- Published 2018-05-02
- Exact source
- AI safety via debate arXiv · published 2018-05-02 · arXiv:1805.00899v1; first-submission date from version history. Later revisions are not substituted.
Appears in
No collection holds a record about this document yet.
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.
Issue and authorship records
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.
Cited by · 3
Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.
Not recorded for this document: cites · 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.