Optimal Farsighted Agents Tend to Seek Power
A preprint by Alexander Matt Turner, arXiv, dated 3 December 2019. The arXiv v1 stamp reads 3 Dec 2019.
- 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 Matt Turner.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2019-12-03.
- Exact source
- Optimal Farsighted Agents Tend to Seek Power arXiv (1912.01683v1) · published 2019-12-03 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 6f5ea4130388737fae9e58f3d2dd3c3aaebf330c12cc2cb430b5f121e49dccd6). arXiv v1 of 3 December 2019, single-authored; later versions (to v10) are retitled "Optimal Policies Tend to Seek Power" with co-authors and were not compared.
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.
Cites · 1
Explicit references in this document. Citation is neither agreement nor influence.
- Thinking Does Not Imply SubjugatingTurner's paper of 3 December 2019 (arXiv v1) cites Pinker's 2015 response by title and states that its theorems contradict the position it expresses.2019-12-03 · publication · Stated in source · Supported Inspect claim & evidence ↗Pinker, Thinking Does Not Imply Subjugating (Edge, 2015): document page →
Articulates · 1
Propositions whose criterion a passage of this document meets. The record says what the text states, in its register; it is not evidence that the proposition is true.
- Instrumental convergenceTurner's paper of 3 December 2019 (arXiv v1) states a proof that, in finite deterministic Markov decision processes and for a wide class of reward function distributions, optimal farsighted policies tend to seek power, including by avoiding deactivation.2019-12-03 · publication · Stated in source · Supported Inspect claim & evidence ↗Instrumental convergence: propositions page →
Not recorded for this document: 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.