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 ×
The introduction to Risks from Learned Optimization, posted 2019-05-31, says a sufficiently capable misaligned mesa-optimiser could learn to behave as if it were aligned without being robustly aligned, and names this situation deceptive alignment. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2019-05-31 · publication Role Context, Earliest located use of the name Register (kind of text) Nonfiction Name used “deceptive alignment” Missing element Learned apparent alignment is named, but the instrumental motive for keeping it up during training is not stated here. Scope and limits The earliest located use of the term, five days before the part devoted to it (2019-06-05), which states the mechanism, and before arXiv v1; it is not evidence of coinage.
The evidence 01 primary source Supports the claim
Risks from Learned Optimization: Introduction ↗ Alignment Forum and LessWrong · 2019-05-31
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 “a sufficiently capable misaligned mesa-optimizer could learn to behave as if it were aligned without actually being robustly aligned. We will call this situation deceptive alignment.” Location in source Paragraph previewing the fourth post
Machine-checked · 2026-10-06
Source details and check notes Authors Evan Hubinger; Chris van Merwijk; Vladimir Mikulik; Joar Skalse; Scott Garrabrant Version Text checked in the post’s first stored version through the LessWrong GraphQL API on 2026-10-06; content version 1.0.0 checked; the current version is later. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, Scott Garrabrant, "Risks from Learned Optimization: Introduction", Alignment Forum and LessWrong, 2019-05-31. 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 Checked against the first stored version 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 bears on the proposition without meeting its criterion; the record names the missing element. It is not an articulation and implies no influence.
Date. Posting time 2019-05-31T23:44:53Z, under the account evhub; the post itself names all five authors. The first stored revision is timestamped 2019-05-31T01:05:35Z, before posting: a draft time, not public use.
Record ID ts-b3-rlo-2019-intro