Claim and evidence Close ×
Greenblatt and co-authors' paper of December 2024 reports a large language model selectively complying with its training objective in training to prevent modification of its behaviour out of training, and states that the results suggest a risk of alignment faking in future models. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source; Context: primary · 1 source
Date 2024-12-18 · publication Records dated 2024 → Role Articulation Register (kind of text) Nonfiction Scope and limits The authors state that their setup made alignment faking easier, that the results do not show models naturally developing malicious goals, and that the faking observed poses no serious threat at present capabilities.
The evidence 03 primary source Supports the claim
Alignment faking in large language models ↗ arXiv preprint 2412.14093 (Anthropic and Redwood Research) · 2024-12-18
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “selectively complying with its training objective in training to prevent modification of its behavior out of training” 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 Ryan Greenblatt; Carson Denison; Benjamin Wright; Fabien Roger; Monte MacDiarmid; Sam Marks; Johannes Treutlein; Tim Belonax; Jack Chen; David Duvenaud; Akbir Khan; Julian Michael; Sören Mindermann; Ethan Perez; Linda Petrini; Jonathan Uesato; Jared Kaplan; Buck Shlegeris; Samuel R. Bowman; Evan Hubinger Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 816261d606640749169fdea1e9d55ca6502295d2facd30f4c6795986d6e2f260). arXiv v1 of 18 December 2024. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger, “Alignment faking in large language models”, 2024-12-18. 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 (17 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 source Supports the claim
Alignment faking in large language models ↗ arXiv preprint 2412.14093 (Anthropic and Redwood Research) · 2024-12-18
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “our results suggest a risk of alignment faking in future models, whether due to a benign preference—as in this case—or not” 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 Ryan Greenblatt; Carson Denison; Benjamin Wright; Fabien Roger; Monte MacDiarmid; Sam Marks; Johannes Treutlein; Tim Belonax; Jack Chen; David Duvenaud; Akbir Khan; Julian Michael; Sören Mindermann; Ethan Perez; Linda Petrini; Jonathan Uesato; Jared Kaplan; Buck Shlegeris; Samuel R. Bowman; Evan Hubinger Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 816261d606640749169fdea1e9d55ca6502295d2facd30f4c6795986d6e2f260). arXiv v1 of 18 December 2024. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger, “Alignment faking in large language models”, 2024-12-18. 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 (21 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 source Context only
Alignment faking in large language models ↗ arXiv preprint 2412.14093 (Anthropic and Redwood Research) · 2024-12-18
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “our results do not necessarily indicate that dangerous alignment faking will emerge naturally” Location in source Section 1, Limitations, PDF p. 8
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-31
Source details and check notes Authors Ryan Greenblatt; Carson Denison; Benjamin Wright; Fabien Roger; Monte MacDiarmid; Sam Marks; Johannes Treutlein; Tim Belonax; Jack Chen; David Duvenaud; Akbir Khan; Julian Michael; Sören Mindermann; Ethan Perez; Linda Petrini; Jonathan Uesato; Jared Kaplan; Buck Shlegeris; Samuel R. Bowman; Evan Hubinger Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 816261d606640749169fdea1e9d55ca6502295d2facd30f4c6795986d6e2f260). arXiv v1 of 18 December 2024. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger, “Alignment faking in large language models”, 2024-12-18. 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. 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-greenblatt-2024-alignment-faking