Claim · 2017-04-12 · publication · Stated in source · Supported

Soares's talk transcript posted in April 2017 states as one of four propositions that aligning advanced AI systems is hard to solve and that AI systems will not naturally end up sharing human objectives.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Ensuring smarter-than-human intelligence has a positive outcome → articulates → Difficulty of alignment

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

Ensuring smarter-than-human intelligence has a positive outcomearticulates ↓Difficulty of alignment

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2017-04-12 · publication Records dated 2017 →
Role: Articulation
Register (kind of text): Nonfiction

Scope and limitsA modified transcript posted by the speaker's organisation; the propositions are stated as the speaker's view.

The evidence 02

primary sourceSupports the claim

Ensuring smarter-than-human intelligence has a positive outcome

Machine Intelligence Research Institute blog (intelligence.org) · 2017-04-12

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“the first proposition says that AI systems won't naturally end up sharing our objectives”

Location in source Section 3.2, "Four key propositions"

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Nate Soares
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 37fbc1df05cfffa12b9313f40eaf121fa05933de2928b131568d4df637137a05). Modified transcript posted 12 April 2017 of a talk given at Google; current page as served on 2026-10-29; the page prints question marks where mathematical symbols stood. The cross-family check retrieved it again on 2026-10-31; the bytes differ, and the check compared the quoted passages.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Nate Soares, “Ensuring smarter-than-human intelligence has a positive outcome”, 2017-04-12.
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, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (14 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-10-31, item 75) re-read the record’s source and found the quotation and stance supported. No human editorial review.

primary sourceSupports the claim

Ensuring smarter-than-human intelligence has a positive outcome

Machine Intelligence Research Institute blog (intelligence.org) · 2017-04-12

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“the fourth says that this problem is hard to solve”

Location in source Section 3.2, "Four key propositions"

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Nate Soares
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 37fbc1df05cfffa12b9313f40eaf121fa05933de2928b131568d4df637137a05). Modified transcript posted 12 April 2017 of a talk given at Google; current page as served on 2026-10-29; the page prints question marks where mathematical symbols stood. The cross-family check retrieved it again on 2026-10-31; the bytes differ, and the check compared the quoted passages.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Nate Soares, “Ensuring smarter-than-human intelligence has a positive outcome”, 2017-04-12.
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, arguments about catastrophic risk from advanced AI (research/risk-debate). The quotation (10 words) matched the text retrieved for the candidate pack on 2026-10-29. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-10-31, item 75) re-read the record’s source and found the quotation and stance supported. No human editorial review.

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 meets the proposition’s criterion. The record documents what the text states, in its register (fiction and satire are labelled); it is not evidence that the proposition is true and implies no influence on or from another text.

Date. Date of posting.

Record ID rd-r06-soares-2017-ensuring-positive-outcome