Claim and evidence Close ×
Omohundro's paper, dated 5 September 2007 and revised 21 January 2008, argues that self-improving systems will exhibit drives towards efficiency, self-preservation, resource acquisition and creativity, and that these drives are instrumental goals arising from a wide variety of fundamental goals. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2007-09-05 · publication Records dated 2007 → Wording attested 2008-01-21. The wording is read in the revision of 21 January 2008; the September 2007 version was not compared. Claimed date 2007-09-05. Date of the first version named in the PDF heading. Role Earliest located Register (kind of text) Nonfiction Scope and limits Earliest located among the texts the searches found (outside the Yudkowsky texts already in the dataset), by the date of the revision read. A statement of the author's argument about rational economic agents, not evidence about any built system; the paper says the drives can be counteracted when another goal outweighs them.
The evidence 02 primary source Supports the claim
The Nature of Self-Improving Artificial Intelligence ↗ Self-Aware Systems (author's site, selfawaresystems.com) · 2007-09-05
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “The “drives” of self-improving systems that we discuss in the rest of the paper are all instrumental goals that arise from a wide variety of different fundamental goals.” Location in source Section 2.5, Instrumental goals, PDF p. 13
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Stephen M. Omohundro Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 f16e74e6f8f024d12110ed11d81a717c9de6312945c5074e3cd9bc7d3f31af9b). author's PDF headed 'September 5, 2007, revised January 21, 2008'; the September 2007 version was not located. The cross-family check retrieved it again on 2026-10-31, with the same bytes. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Stephen M. Omohundro, “The Nature of Self-Improving Artificial Intelligence”, 2007-09-05. 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 (28 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. A cross-family machine check (2026-10-31, item 20) answered the record’s question blind and agreed with its stance. No human editorial review. primary source Supports the claim
The Nature of Self-Improving Artificial Intelligence ↗ Self-Aware Systems (author's site, selfawaresystems.com) · 2007-09-05
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “This is because, for a wide range of goals, death corresponds to the cessation of all goal achievement” Location in source Section 5, The Self-Preservation Drive, PDF p. 25
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Stephen M. Omohundro Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 f16e74e6f8f024d12110ed11d81a717c9de6312945c5074e3cd9bc7d3f31af9b). author's PDF headed 'September 5, 2007, revised January 21, 2008'; the September 2007 version was not located. The cross-family check retrieved it again on 2026-10-31, with the same bytes. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Stephen M. Omohundro, “The Nature of Self-Improving Artificial Intelligence”, 2007-09-05. 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 (18 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. A cross-family machine check (2026-10-31, item 20) answered the record’s question blind and agreed with its stance. 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 publication, as the source gives it.
Record ID rd-r02-omohundro-2007-nature-self-improving