Claim · 2016-12-28 · publication · Stated in source · Supported

Yudkowsky's talk transcript posted in December 2016 states that advanced AIs are not going to be aligned automatically and that AI alignment is difficult in the way rockets and space probes are difficult.

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

AI Alignment: Why It's Hard, and Where to Start → articulates → Difficulty of alignment

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

AI Alignment: Why It's Hard, and Where to Startarticulates ↓Difficulty of alignment

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2016-12-28 · publication Records dated 2016 →
Claimed date: 2016-05. Talk given at Stanford University in May 2016, according to the post; the transcript is dated by the post.
Role: Articulation
Register (kind of text): Nonfiction

Scope and limitsThe transcript is abridged and was posted by the speaker's organisation, not the event host; the wording is dated by the post.

The evidence 02

primary sourceSupports the claim

AI Alignment: Why It's Hard, and Where to Start

Machine Intelligence Research Institute blog (intelligence.org) · 2016-12-28

Cite the original source

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

Source excerpt

“They're not going to be aligned automatically.”

Location in source Section 3.1, "Why is alignment necessary?"

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Eliezer Yudkowsky
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 829f9c018dc638c51e0b0a9b63f4c7a87a080068a7f81adf4f173c1592e1956d). Abridged transcript posted 28 December 2016 of a talk given at Stanford University in May 2016; current page as served on 2026-10-29.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Eliezer Yudkowsky, “AI Alignment: Why It's Hard, and Where to Start”, 2016-12-28.
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 (7 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. No human editorial review.

primary sourceSupports the claim

AI Alignment: Why It's Hard, and Where to Start

Machine Intelligence Research Institute blog (intelligence.org) · 2016-12-28

Cite the original source

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

Source excerpt

“The message is: AI alignment is difficult like rockets are difficult.”

Location in source Section 3.3

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Eliezer Yudkowsky
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 829f9c018dc638c51e0b0a9b63f4c7a87a080068a7f81adf4f173c1592e1956d). Abridged transcript posted 28 December 2016 of a talk given at Stanford University in May 2016; current page as served on 2026-10-29.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Eliezer Yudkowsky, “AI Alignment: Why It's Hard, and Where to Start”, 2016-12-28.
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 (11 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. 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-yudkowsky-2016-alignment-why-its-hard