Claim · 2019-12-03 · publication · Stated in source · Supported

Turner'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.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Optimal Farsighted Agents Tend to Seek Power → articulates → Instrumental convergence

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

Optimal Farsighted Agents Tend to Seek Powerarticulates ↓Instrumental convergence

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2019-12-03 · publication Records dated 2019 →
Role: Articulation
Register (kind of text): Nonfiction

Scope and limitsA formal result about optimal policies in the stated model; the paper makes no claim about when real-world systems would behave this way. Later versions with co-authors were not compared.

The evidence 02

primary sourceSupports the claim

Optimal Farsighted Agents Tend to Seek Power

arXiv (1912.01683v1) · 2019-12-03

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“We prove that, with respect to a wide class of reward function distributions, optimal policies tend to seek power over the environment.”

Location in source Abstract, PDF p. 1

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Alexander Matt Turner
Version: 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.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Alexander Matt Turner, “Optimal Farsighted Agents Tend to Seek Power”, 2019-12-03.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (22 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

primary sourceSupports the claim

Optimal Farsighted Agents Tend to Seek Power

arXiv (1912.01683v1) · 2019-12-03

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“agents pursuing randomly selected goals are quite unlikely to allow themselves to be deactivated (if they have a choice in the matter).”

Location in source Section on Theorem 48, PDF p. 8

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Alexander Matt Turner
Version: 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.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Alexander Matt Turner, “Optimal Farsighted Agents Tend to Seek Power”, 2019-12-03.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (22 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A passage of the document meets the proposition’s criterion. The record documents what the text states, in its register (fiction and satire are labelled); it is not evidence that the proposition is true and implies no influence on or from another text.

Date. Date of the arXiv v1 submission.

Record ID rd-r02-turner-2019-optimal-farsighted-agents