Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures
Eliezer Yudkowsky’s report published by the Singularity Institute for Artificial Intelligence as version 1.0 on 15 June 2001, read in its 2001 HTML edition and in MIRI’s later reprint.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source records list Eliezer Yudkowsky.
- Dates
- No date claim recorded yet. The source records give the publication date as 2001-06-15.
- Exact source
- Creating Friendly AI 1.0, section 4: Beyond anthropomorphism (2001 HTML edition) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Raw Internet Archive capture of 2001-08-10, retrieved 2026-10-08 (SHA-256 bb3cdcc34934a50b9a404600d9a0f412eae00f0a66f390d8110b0ad56cbd965a); used to date wording also quoted from MIRI’s reprint, not quoted itself.Archived copy, captured 2001-08-10: Creating Friendly AI 1.0, section 4: Beyond anthropomorphism (2001 HTML edition). Captured 56 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2001-08-10. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-08.
- Creating Friendly AI 1.0, section 2: Challenges of Friendly AI (2001 HTML edition) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Raw Internet Archive capture of 2001-06-26, retrieved 2026-10-08 (SHA-256 e910a4f4aec9673a1dc69d006a40d44315acb6279f10fc9e6e3d79f5701dc603); used to date wording also quoted from MIRI’s reprint, not quoted itself.Archived copy, captured 2001-06-26: Creating Friendly AI 1.0, section 2: Challenges of Friendly AI (2001 HTML edition). Captured 11 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2001-06-26. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-08.
- Creating Friendly AI 1.0, glossary (2001 HTML edition) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Raw Internet Archive capture of 2001-06-17, retrieved 2026-10-06; MIRI’s reprint carries the same definition with changed cross-references.Archived copy, captured 2001-06-17: Creating Friendly AI 1.0, glossary (2001 HTML edition). Captured 2 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2001-06-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.
- Creating Friendly AI 1.0, section 6: Policy implications (2001 HTML edition) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Raw Internet Archive capture of 2001-06-17, retrieved 2026-10-08 (SHA-256 7cb989b7408e084950daf9cb6f758b79eb5bb85e3d5c652e0bca7aa746b632ca); used to date wording also quoted from MIRI’s reprint, not quoted itself.Archived copy, captured 2001-06-17: Creating Friendly AI 1.0, section 6: Policy implications (2001 HTML edition). Captured 2 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2001-06-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-08.
- Creating Friendly AI 1.0, section 3.3: Seed AI goal systems (2001 HTML edition) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Raw Internet Archive capture of 2001-06-17, retrieved 2026-10-06 with the hash recorded by the 1996–2022 candidate search. Section 3.3 here is section 5.3 in MIRI’s reprint.Archived copy, captured 2001-06-17: Creating Friendly AI 1.0, section 3.3: Seed AI goal systems (2001 HTML edition). Captured 2 days after the recorded publication date. An archive copy shows only what the archive retrieved on 2001-06-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-06.
- Creating Friendly AI 1.0 (MIRI reprint) Singularity Institute for Artificial Intelligence · published 2001-06-15 · Singularity Institute, MIRI reprint, retrieved 2026-10-06 (SHA-256 51f21b8b70c2b7324c20de85edea40b2ef224cadff56ef7e0a3aa2a08dba2752). Release date from the reprint; an open-commentary version was announced on SL4 on 2001-04-18, so some wording may be earlier than this date. Reprint wording is not authenticated for 2001 unless a capture was compared.
Appears in
- Propositions about superintelligence, 1863–2022 →5 records on this document
- Eliezer Yudkowsky’s arguments on common claims about AI, 1996–2026 →9 records on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Articulates · 5
Propositions whose criterion a passage of this document meets. The record says what the text states, in its register; it is not evidence that the proposition is true.
Contests · 4
Propositions a passage of this document disputes, or a premise they depend on.
Bears on · 5
Propositions a passage comes close to without meeting the criterion; each record names what is missing.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.