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 post “Challenges to Christiano’s capability amplification proposal” (2018-05-19) contests Y21. Discussing imitation-based alignment, he argues that inexact imitation of humans does not carry over properties such as being a good person, and exact imitation is harder than surpassing human capability. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2018-05-19 · publication Claimed date 2018-03-16. The post describes itself as "a basically unedited summary I wrote up on March 16"; published 2018-05-19. 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 training on human text or behaviour yields human-like thought and motives. Scope and limits Premise addressed: Training on human text or behaviour yields human-like thought and motives. Single-author post (2018-05-19) that also contains interleaved replies by Paul Christiano; the quoted paragraph is in Yudkowsky's own text. Concerns imitation learning generally, before large language models. A critique of the imitation assumption in Christiano's amplification scheme, not a claim about models pretrained on human text.
The evidence 01 primary source Supports the claim
Challenges to Christiano’s capability amplification proposal ↗ LessWrong · 2018-05-19
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 seems to me that having an AI output a high-fidelity imitation of human behavior, sufficiently high-fidelity to preserve properties like "being smart" and "being a good person" … is a pretty huge ask.” Location in source Challenges to Christiano's capability amplification proposal, paragraph beginning 'Speaking of inexact imitation'
Machine-checked · 2026-10-06
Source details and check notes Authors Eliezer Yudkowsky Version Post body retrieved through the LessWrong GraphQL API on 2026-10-06 (SHA-256 19de389fa9005f7c634dc127be9892fd108a366a7af3a69c0c8ac3eee08deb53), content version 1.0.0. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Eliezer Yudkowsky, “Challenges to Christiano’s capability amplification proposal”, LessWrong, 2018-05-19. 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 T21-b. The quotation (34 words) matched the retrieved expression (SHA-256 19de389fa9005f7c634dc127be9892fd108a366a7af3a69c0c8ac3eee08deb53) 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. LessWrong postedAt.
Record ID yk-y21-lw-2018-challenges-to-christianos-capability-amplification-proposal-c