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 ×
Christiano’s post rejects AGI Ruin’s item 13, holding that the problem of AIs changing their outer behaviour to look more aligned and deceive their programmers can be studied in advance. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2022-06-19 · publication Role Contesting Register (kind of text) Nonfiction Scope of the passage Holds that deliberate aligned-looking behaviour can be studied in advance. Engagement Engages a premise. Read as a whole, the post gives a reason against a failure mechanism behind the premise, arguing that foreseeable AI is trained continuously as capability gradually increases rather than through a drastic transfer from low to high intelligence. Scope and limits A conditional disagreement about what can be learned before dangerous capability, not a claim that good behaviour is reliable evidence. The post also accepts wider limits on behavioural evidence. The engagement rests on the post as read in its current version 1.12.0 on 2026-10-16; whether its first version already contains that argument was not verified.
The evidence 01 primary source Supports the claim
Where I agree and disagree with Eliezer ↗ Alignment Forum and LessWrong · 2022-06-19
Archived copy, captured 2022-06-19: Where I agree and disagree with Eliezer ↗
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 “List of lethalities #13 makes a particular argument that we won’t see many AI problems in advance [...] it seems possible to study the problem that AIs may “change [their] outer behavior to deliberately look more aligned and deceive the programmers” Location in source Section "Disagreements", bullet on List of Lethalities #13
Machine-checked · 2026-10-06
Source details and check notes Authors Paul Christiano 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 2022-06-19: Where I agree and disagree with Eliezer ↗ . Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2022-06-19. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.Attribution Paul Christiano, "Where I agree and disagree with Eliezer", Alignment Forum and LessWrong, 2022-06-19. 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 Checked against the first stored version on 2026-10-06; the inner quotation is Christiano’s quotation of AGI Ruin. 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. Posting time 2022-06-19T19:15:55Z; the quotes also match a capture of the posting day.
Record ID ts-b5-christiano-2022-contests