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 ×
Version 3 of Risks from Learned Optimization discusses deceptive alignment in section 4. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2021-12-01 · event Scope and limits The paper was first submitted in 2019, but this claim is scoped to the inspected 2021 HTML version. No earliest-use claim is made.
The evidence 01 primary source Supports the claim
Risks from Learned Optimization in Advanced Machine Learning Systems ↗ arXiv · 2019-06-05
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
Paraphrase Section 4 describes a mesa-optimizer pursuing the base objective instrumentally in order to avoid modification.
Location in source Section 4, Deceptive alignment, opening paragraphs
Machine-checked · 2026-09-17
Source details and check notes Authors Evan Hubinger; Chris van Merwijk; Vladimir Mikulik; Joar Skalse; Scott Garrabrant Version arXiv:1906.01820v3; claims scoped to this version, not first use in 2019 Version date 2021-12-01 Canonical address Open the canonical source ↗ Accessed 2026-09-17 Language English (en) Attribution arXiv, Risks from Learned Optimization in Advanced Machine Learning Systems (2019-06-05). Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and minimal attributed excerpts only. Recheck terms before wider redistribution. Check notes Source passage inspected by an automated research assistant. Human editorial review is pending. 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. The concept is explicitly discussed in the document. This makes no earliest-use, invention or transmission claim.
Date. The date identifies this documented announcement or publication; it does not establish a continuing state.
Record ID risks-discusses-deception-2021