Claim and evidence Close ×
Soares, Fallenstein, Yudkowsky and Armstrong's paper of January 2015 states that rational agents have default incentives to resist being shut down or having their preferences modified, and that simple attempts to define a utility function that removes those incentives prove unsatisfactory. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2015-01-25 · publication Records dated 2015 → Role Contesting, Earliest located Register (kind of text) Nonfiction Engagement Engages a premise. It disputes the premise that ordinary engineering can give a capable agent objectives that leave it open to shutdown and correction. Scope and limits A technical argument about a formal shutdown problem, not a proof that control is impossible; the paper presents its failed proposals as pointing to further research. Earliest located among the contesting texts the searches found, after a cross-family check proposed it; it is not evidence of coinage.
The evidence 02 primary source Supports the claim
Corrigibility ↗ AAAI Workshops · 2015-01-25
Archived copy, captured 2015-03-22: Corrigibility ↗
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 “despite default incentives for rational agents to resist attempts to shut them down or modify their preferences” 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 Nate Soares; Benja Fallenstein; Eliezer Yudkowsky; Stuart Armstrong Version MIRI-hosted PDF of the workshop paper, retrieved 2026-10-06 with the hash recorded by the 1996–2022 candidate search. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Archive copy Open archived copy, captured 2015-03-22: Corrigibility ↗ . Captured 56 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2015-03-22. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.Attribution Soares, Fallenstein, Yudkowsky and Armstrong, "Corrigibility", AAAI Workshops (2015). 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 Added at the admission of the risk-debate pack (research/risk-debate). The quotation (17 words) matched a fresh retrieval of 2026-10-31 (SHA-256 e5557297950bbbfc144437059887010db41060f457c93f1246143821bf27a6b1). Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms. No human editorial review. primary source Supports the claim
Corrigibility ↗ AAAI Workshops · 2015-01-25
Archived copy, captured 2015-03-22: Corrigibility ↗
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 “These attempts will prove unsatisfactory, but will fail in enlightening ways that suggest avenues for future research.” Location in source Section 2, The Shutdown Problem, PDF p. 3
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Nate Soares; Benja Fallenstein; Eliezer Yudkowsky; Stuart Armstrong Version MIRI-hosted PDF of the workshop paper, retrieved 2026-10-06 with the hash recorded by the 1996–2022 candidate search. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Archive copy Open archived copy, captured 2015-03-22: Corrigibility ↗ . Captured 56 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2015-03-22. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.Attribution Soares, Fallenstein, Yudkowsky and Armstrong, "Corrigibility", AAAI Workshops (2015). 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 Added at the admission of the risk-debate pack (research/risk-debate). The quotation (17 words) matched a fresh retrieval of 2026-10-31 (SHA-256 e5557297950bbbfc144437059887010db41060f457c93f1246143821bf27a6b1). Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms. The cross-family check of 2026-10-31 proposed the record and read this passage. The check's quotation read “further research”; the PDF reads “future research”, as quoted here. 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 disputes the proposition or a premise it depends on. The record documents the text’s position, not who is right.
Date. Workshop dates of 25–26 January 2015 in the header of the PDF.
Record ID rd-r10b-corrigibility-2015