Claim · 2023-11-28 · publication · Stated in source · Supported

Belrose and Pope's essay of November 2023 argues that an AI will learn human values early in training, before it acquires dangerous capabilities, so that AIs will not learn to pretend to be ethical during training while holding other motives.

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 is easy to control → contests → Inner or deceptive misalignment

Where it appears

Arguments about catastrophic risk from advanced AI →

Claim and evidence

AI is easy to controlcontests ↓Inner or deceptive misalignment

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2023-11-28 · publication Records dated 2023 →
Role: Contesting, Earliest located
Register (kind of text): Nonfiction
Engagement: Engages a premise. It disputes the premise that a capable system would acquire other objectives before it learns the intended values.

Scope and limitsRecords the essay's argument about the order in which values and capabilities are learned; it is an argument, not a measurement.

The evidence 02

primary sourceSupports the claim

AI is easy to control

AI Optimism (optimists.ai) · 2023-11-28

Cite the original source

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

Source excerpt

“This means that AIs will not learn to "play the training game," pretending to be ethical during training while secretly harboring ulterior motives.”

Location in source Section "Values are easy to learn"

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Nora Belrose; Quintin Pope
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 ebe2a9bfc1eaffeefb19ec191f3db1dfa9276ec09cb2bc20257fd46dafd3da5c). current optimists.ai page, address dated 2023/11/28, datePublished 2023-11-29T02:38 UTC in the page metadata; later edits not checked. 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: Nora Belrose, Quintin Pope, “AI is easy to control”, 2023-11-28.
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 (23 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 is easy to control

AI Optimism (optimists.ai) · 2023-11-28

Cite the original source

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

Source excerpt

“it will achieve a fairly strong understanding of human values well before it acquires dangerous capabilities”

Location in source Section "Values are easy to learn"

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Nora Belrose; Quintin Pope
Version: Retrieved for the candidate pack on 2026-10-29 (SHA-256 ebe2a9bfc1eaffeefb19ec191f3db1dfa9276ec09cb2bc20257fd46dafd3da5c). current optimists.ai page, address dated 2023/11/28, datePublished 2023-11-29T02:38 UTC in the page metadata; later edits not checked. 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: Nora Belrose, Quintin Pope, “AI is easy to control”, 2023-11-28.
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 (16 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 disputes the proposition or a premise it depends on. The record documents the text’s position, not who is right.

Date. Date of posting.

Record ID rd-r03-belrose-pope-2023-ai-easy-to-control