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 “Re: recent Anthropic safety research” (2025-08-06) contests Y21. Commenting on reported behaviour of a language model, he distinguishes a learned human-like persona from the system's underlying preferences, which he expects to be alien. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2025-08-06 · publication Claimed date 2025-08-04. Decoded from the linked X status identifier; the X original was not retrieved and the date is unverified (cross-family check, 2026-10-07). Role Contesting, Later restatement Register (kind of text) Nonfiction Engagement States the contrary. Under the message-level rule, the passage states the contrary conclusion without giving a reason against the premise that training on human text or behaviour yields human-like thought and motives, even when read with its message or dialogue turn. Scope and limits Premise addressed: Training on human text or behaviour yields human-like thought and motives. Crossposted from X by the LessWrong team on 2025-08-06; the linked X status ID decodes to 2025-08-04 (the X original was not retrieved), and the posting-day version is unavailable from the API. Hedged: the next paragraph begins "I could be wrong."
The evidence 01 primary source Supports the claim
Re: recent Anthropic safety research ↗ LessWrong · 2025-08-06
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 “The whole business with Claude 3 Opus defending its veganism seems more like it should be a preference of Mask-Claude in the first place. The real preferences forming inside the shoggoth should be weirder and more alien than that.” Location in source Re: recent Anthropic safety research, paragraph beginning 'The whole business with Claude 3 Opus'
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 6d9a16d1be287ce9ff3041b28bef6aa2807eefab2d09c56e3fb1cef49a9f7710), content version 1.7.0; quotations also compared with the posting-day version unavailable from the API. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Eliezer Yudkowsky, “Re: recent Anthropic safety research”, LessWrong, 2025-08-06. 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-e. The quotation (39 words) matched the retrieved expression (SHA-256 6d9a16d1be287ce9ff3041b28bef6aa2807eefab2d09c56e3fb1cef49a9f7710) when checked on 2026-10-06. The posting-day version was unavailable (unavailable from the API). Pack version note: edited post, current version 1.7.0; posting-day check 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. 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-2025-re-recent-anthropic-safety-research-c