Claim · 2015-01-25 · publication · Stated in source · Supported

Soares, Fallenstein, Yudkowsky and Armstrong (2015) attribute the term “treacherous turn”, for an agent that conceals its utility function until it can avoid correction, to Bostrom (2014).

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

Corrigibility → attributes to → Superintelligence: Paths, Dangers, Strategies

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Corrigibilityattributes to ↓Superintelligence: Paths, Dangers, Strategies

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2015-01-25 · publication Records dated 2015 →
Kind of attribution: Attributes a term or concept to the work

Scope and limitsThe citing text's attribution of a term; not evidence that Bostrom (2014) originated the concept, that the book caused the corrigibility framing, or that the citing authors adopt the book's wider argument.

The evidence 01

primary sourceSupports the claim

Corrigibility

AAAI Workshops · 2015-01-25

Archived copy, captured 2015-03-22: Corrigibility

Cite the original source

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

Source excerpt

“Bostrom (2014) refers to this as a “treacherous turn”.”

Location in source PDF p. 1, footnote 2

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: Candidate pack passage, key papers (research/key-papers). The quotation (9 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. A cross-family machine check (2026-10-30, item B001) found the attribution at its locator and in the citing text’s reference entry; it qualified its answer, and the adjudication of 2026-10-31 was applied at admission. 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 document expressly attributes an argument, concept, term, finding or approach to another work, in its own words; the kind of attribution is recorded. The record is the citing document’s claim. It is not evidence that the cited work originated the idea, that the attribution is accurate, or of influence beyond the passage. Citation alone is recorded as a citation.

Date. Date of the citing text as the dataset records it (25 January 2015).

Record ID kp-shaping-corrigibility-bostrom