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 ×
Part 4 of Risks from Learned Optimization says a deceptively aligned mesa-optimiser is likely to stop optimising the base objective as soon as it no longer needs to perform well on it to achieve its goal. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2019-06-05 · publication Role Articulation Register (kind of text) Nonfiction Scope and limits The post calls this transition "defection" and calls the extreme case a "treacherous turn" as described by Bostrom; the citation is the post’s own.
The evidence 01 primary source Supports the claim
Deceptive Alignment (Risks from Learned Optimization, part 4) ↗ Alignment Forum and LessWrong · 2019-06-05
Archived copy, captured 2019-09-23: Deceptive Alignment (Risks from Learned Optimization, part 4) ↗
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 deceptively aligned mesa-optimizer is likely to stop optimizing the base objective as soon as it is in a position where it no longer needs to perform well on the base objective to achieve its goal.” Location in source Section 4.1 "Safety concerns arising from deceptive alignment", first paragraph
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. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Archive copy Open archived copy, captured 2019-09-23: Deceptive Alignment (Risks from Learned Optimization, part 4) ↗ . Captured 110 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2019-09-23. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.Attribution Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, Scott Garrabrant, "Deceptive Alignment (Risks from Learned Optimization, part 4)", Alignment Forum and LessWrong, 2019-06-05. 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 Checked in 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 meets the proposition’s criterion. The record documents what the text states, in its register (fiction and satire are labelled); it is not evidence that the proposition is true and implies no influence on or from another text.
Date. Posting time 2019-06-05T20:16:28Z; the current post version is 1.10.0.
Record ID ts-b1-rlo-2019-deceptive