Choose an institution to see its records and dossier, or choose a topic.
Through year 2027 · all records, including scheduled dates 2026 2025 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2008 2005 1965 Show Organisations and infrastructure All types Organisation Person Document Concept Infrastructure Public body Reset filters
94 people, organisations and other records · 122 relationships · 34 claims about a valueEverything recorded up to the chosen year, whether or not still in effect · Undated records included
Claim and evidence Close ×
“Programmer deception” (2015-07-16) contests Y12. Defines programmer deception as an AI's instrumental incentive to give its programmers false beliefs, and argues that this makes observed good behaviour unreliable evidence about future behaviour. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2015-07-16 · publication Wording attested Only in a later, undated copy. Arbital pages could be edited after creation; the viewer shows a page date, and the quoted wording is known only from the page as retrieved in 2026. Role Contesting Register (kind of text) Nonfiction Engagement Engages a premise. Under the message-level rule, the passage, read with the paragraph, message or dialogue turn it belongs to, gives a reason against the premise that a dangerous system would behave dangerously while it is being tested. Scope and limits Premise addressed: A dangerous system would behave dangerously while it is being tested. Arbital page by Yudkowsky, shown through the GreaterWrong viewer with the date 16 July 2015; the page includes unfinished notes ('clean this up and expand'), and the date may not be the date of this wording. The elided opening reads "unless the rest of the AI is working as intended and whatever programmer-deception-defeaters were built are functioning as planned,".
The evidence 01 primary source Supports the claim
Programmer deception (Arbital, GreaterWrong viewer) ↗ Arbital · 2015-07-16
Archived copy, captured 2022-08-16: Programmer deception (Arbital, GreaterWrong viewer) ↗
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 “you could currently be observing a non-nice AI that is smart and trying to fool you.” Location in source Arbital 'Programmer deception', second paragraph
Machine-checked · 2026-10-06
Source details and check notes Authors Eliezer Yudkowsky Version Current viewer page, retrieved 2026-10-06; it is generated dynamically, so its bytes differ from the 1996–2022 candidate search’s retrieval while the quoted text matches. Read through the GreaterWrong Arbital viewer. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Archive copy Open archived copy, captured 2022-08-16: Programmer deception (Arbital, GreaterWrong viewer) ↗ . Captured 2588 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2022-08-16. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.Attribution Eliezer Yudkowsky, "Programmer deception", Arbital. 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 T12-b. The quotation (44 words) matched the retrieved expression (SHA-256 0288467b384ce543ff51895947d97d4a4dc5b59f68149dbfbfd9a024f2dcacc5) when checked on 2026-10-06. The dataset already quotes this source for the human-thought collection; together the quotations would exceed the per-document quotation limit. Shortened to the part of the pack's quotation that the existing quotation does not hold. 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. Viewer shows "16 Jul 2015"; creation or last edit not stated.
Record ID yk-y12-arbital-programmer-deception-c