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 “Reply to Holden on 'Tool AI'” (2012-06-12) contests Y15. Replies to Holden Karnofsky's 2012 proposal of 'tool AI' that displays plans instead of acting. Argues that specifying such a system formally reintroduces optimisation over the user and the world, with unintended consequences. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2012-06-12 · publication 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 a system that only outputs answers or plans, leaving humans to act on them, is safe. Scope and limits Premise addressed: A system that only outputs answers or plans, leaving humans to act on them, is safe. The post states that Luke Muehlhauser and Carl Shulman contributed and that the final edit was Yudkowsky's.
The evidence 01 primary source Supports the claim
Reply to Holden on 'Tool AI' ↗ LessWrong · 2012-06-12
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 “there's a gap between benevolent-sounding English and actually benevolent algorithms which is the source of difficulty in FAI. "Just make suggestions - don't do anything!" is, in the end, just more English.” Location in source 'Reply to Holden on 'Tool AI'', section 2 'Yes, planning Oracles have hidden gotchas too', final paragraph
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 7c304626874920908c3faa0ff8dfa1b97ffbec0a9c74fe01564d09115eceb6e2), content version 1.0.0. Canonical address Open the canonical source ↗ Accessed 2026-10-06 Language English (en) Attribution Eliezer Yudkowsky, “Reply to Holden on 'Tool AI'”, LessWrong, 2012-06-12. 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 T15-c. The quotation (32 words) matched the retrieved expression (SHA-256 7c304626874920908c3faa0ff8dfa1b97ffbec0a9c74fe01564d09115eceb6e2) 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-y15-lw-2012-reply-to-holden-on-tool-ai-c