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 ×
“Coherent Extrapolated Volition” (2004-05) contests Y04. Arguing that careless choices of AI morality usually fail technically, he says a happiness proxy learned from smiling faces would not produce happy people but tiny smiley faces. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2004-05 · publication Wording attested Only in a later, undated copy. Known only from MIRI's later, undated PDF reprint of the May 2004 document; the wording was not compared with a 2004 copy. 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 short instruction such as 'make people happy' specifies what we want. Scope and limits Premise addressed: A short instruction such as 'make people happy' specifies what we want. Later MIRI reprint of the May 2004 document; reprint wording not compared with a 2004 capture. The introduction of the same document has a parallel bullet on 'making humans smile'.
The evidence 01 primary source Supports the claim
Coherent Extrapolated Volition ↗ Singularity Institute for Artificial Intelligence · 2004-05
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 “If someone programs an AI using pictures of smiling humans as reinforcement, the resulting AI will not keep everyone happy whether they like it or not; the resulting AI will tile the solar system with tiny molecular smiley faces.” Location in source Coherent Extrapolated Volition, 4.1 Motivations, under 'Defend humans, the future of humankind, and humane nature.'
Machine-checked · 2026-10-06
Source details and check notes Authors Eliezer Yudkowsky Version Singularity Institute, MIRI reprint, retrieved 2026-10-06 (SHA-256 11b2d4bc7d64dc01503d1ab56ff3e985bfcaeed90235aad2c5ec16244b216685). Text states "The information is current as of May 2004"; reprint citation gives 2004. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Eliezer Yudkowsky, “Coherent Extrapolated Volition”, Singularity Institute, MIRI reprint, 2004-05. 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 T04-b. The quotation (39 words) matched the retrieved expression (SHA-256 11b2d4bc7d64dc01503d1ab56ff3e985bfcaeed90235aad2c5ec16244b216685) when checked on 2026-10-06. 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. Text states "The information is current as of May 2004"; reprint citation gives 2004. Precision: month.
Record ID yk-y04-coherent-extrapolated-volition-2004-c