Claim · 2022-08-30 · publication · Stated in source · Supported

Ngo's report of August 2022 argues that realistic training processes plausibly lead AGIs to develop misaligned goals, and that policies able to reason about their training will learn to pursue misaligned goals deceptively while still getting high training reward.

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

The Alignment Problem from a Deep Learning Perspective → articulates → Inner or deceptive misalignment

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

The Alignment Problem from a Deep Learning Perspectivearticulates ↓Inner or deceptive misalignment

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2022-08-30 · publication Records dated 2022 →
Role: Articulation
Register (kind of text): Nonfiction

Scope and limitsRecords the v1 argument, which the author presents as plausible expectations about future systems, not observations; later versions with co-authors revise the text.

The evidence 02

primary sourceSupports the claim

The Alignment Problem from a Deep Learning Perspective

arXiv · 2022-08-30

Cite the original source

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

Source excerpt

“realistic training processes plausibly lead to the development of misaligned goals in AGIs”

Location in source Abstract, PDF p. 1

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Richard Ngo
Version: arXiv:2209.00626v1, submitted 30 August 2022 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 9503e506974e64d75506c4c0177779f217f1662b905aaa603bf35cb26bbb9192). The author list is the byline as printed on the first page.
Version date: 2022-08-30
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Richard Ngo, “The Alignment Problem from a Deep Learning Perspective”, 2022-08-30.
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 (13 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

The Alignment Problem from a Deep Learning Perspective

arXiv · 2022-08-30

Cite the original source

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

Source excerpt

“Once policies can reason about their training processes and deployment contexts (an ability which I'll call situational awareness), they'll learn to deceptively pursue misaligned goals while still getting high training reward.”

Location in source Section 2, PDF p. 3

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Richard Ngo
Version: arXiv:2209.00626v1, submitted 30 August 2022 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 9503e506974e64d75506c4c0177779f217f1662b905aaa603bf35cb26bbb9192). The author list is the byline as printed on the first page.
Version date: 2022-08-30
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Richard Ngo, “The Alignment Problem from a Deep Learning Perspective”, 2022-08-30.
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 (31 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 the arXiv v1 submission.

Record ID rd-r03-ngo-2022-alignment-problem-deep-learning