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 ×
“Orthogonality Thesis” (2015-03-10) contests Y02. States one of two policy consequences of the Orthogonality Thesis: a failed attempt at a nice AI does not self-correct into niceness, because intelligence does not fix an agent's goals. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2015-03-10 · 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 greater intelligence by itself brings benevolent goals. Scope and limits Premise addressed: Greater intelligence by itself brings benevolent goals. Arbital page by Yudkowsky read through the GreaterWrong viewer, which dates it 10 Mar 2015; Arbital pages were revised after creation, so the cached wording may be later than 2015. Comments by others on the page are not used.
The evidence 01 primary source Supports the claim
Orthogonality Thesis ↗ Arbital · 2015-03-10
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 “It is possible to screw up when trying to build a nice AI, and if you do, the AI will not automatically decide to be nice instead.” Location in source Introduction; second of the 'two highly important policy-relevant propositions'
Machine-checked · 2026-10-06
Source details and check notes Authors Eliezer Yudkowsky Version Arbital (GreaterWrong viewer), retrieved 2026-10-06 (SHA-256 f5f43a86f8b37ec82fae35bed5c07d95ad653fe8bcca9fc42c1eea197eff5cde). Viewer shows "10 Mar 2015", probably the creation date; the body uses later terminology ("AGI alignment"), so the cached wording may be a later revision. Comments on the page are by others. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Eliezer Yudkowsky, “Orthogonality Thesis”, Arbital (GreaterWrong viewer), 2015-03-10. 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 T02-a. The quotation (27 words) matched the retrieved expression (SHA-256 f5f43a86f8b37ec82fae35bed5c07d95ad653fe8bcca9fc42c1eea197eff5cde) 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. Viewer shows "10 Mar 2015", probably the creation date; the body uses later terminology ("AGI alignment"), so the cached wording may be a later revision. Comments on the page are by others.
Record ID yk-y02-arbital-orthogonality-c