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 ×
Introducing Superalignment argues that current alignment techniques including RLHF will not scale to superintelligence because they rely on human supervision that the authors expect to become unreliable for much smarter systems. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2023-07-05 · publication Scope and limits An attributed criticism of supervision limits, not rejection of every use of RLHF, proof of the prediction, or a new method’s implementation. Mutable page; exact 2023 expression not authenticated.
The evidence 01 primary source Supports the claim
Introducing Superalignment ↗ OpenAI · 2023-07-05
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 The authors say current alignment techniques, including RLHF, depend on human supervision and will not scale to superintelligence because humans will not reliably supervise much smarter systems.
Location in source Opening problem statement, paragraph beginning “Currently”; footnote B
Machine-checked · 2026-09-25
Source details and check notes Authors Jan Leike; Ilya Sutskever Version Dated announcement as retrieved; mutable current webpage, not an authenticated 2023 snapshot. Canonical address Open the canonical source ↗ Accessed 2026-09-20 Language English (en) Attribution Jan Leike; Ilya Sutskever, Introducing Superalignment (2023-07-05). Reuse No open redistribution licence asserted. Bibliographic metadata and brief attributed paraphrases only; no full source, personal contact details or dataset imported. Check notes Wording corrected with explicit human authorization on 2026-09-25. Source passage inspected by machine; authorization of the wording does not establish human source inspection. 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. Displayed announcement date; retrieved page may have changed subsequently.
Record ID lineage-superalignment-discusses-rlhf