Claim and evidence Close ×
Carlsmith's report of November 2023 examines whether advanced AIs that perform well in training will do so in order to gain power later, and concludes that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme. 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 2023-11-14 · publication Records dated 2023 → Role Most developed Register (kind of text) Nonfiction Scope and limits The report also states that there are reasons for comfort; its conclusion is the author's judgement, not a measured frequency.
The evidence 03 primary source Supports the claim
Scheming AIs: Will AIs fake alignment during training in order to get power? ↗ arXiv preprint 2311.08379 (Open Philanthropy report) · 2023-11-14
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 “This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later” 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 Joseph Carlsmith Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 ff546752a0b14d17cd05e20e1d2ff553b1f431a440a1e48241a842955df597bb). arXiv v1 of 14 November 2023. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Joseph Carlsmith, “Scheming AIs: Will AIs fake alignment during training in order to get power?”, 2023-11-14. 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 Supports the claim
Scheming AIs: Will AIs fake alignment during training in order to get power? ↗ arXiv preprint 2311.08379 (Open Philanthropy report) · 2023-11-14
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 “I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme” 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 Joseph Carlsmith Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 ff546752a0b14d17cd05e20e1d2ff553b1f431a440a1e48241a842955df597bb). arXiv v1 of 14 November 2023. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Joseph Carlsmith, “Scheming AIs: Will AIs fake alignment during training in order to get power?”, 2023-11-14. 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 source Context only
Scheming AIs: Will AIs fake alignment during training in order to get power? ↗ arXiv preprint 2311.08379 (Open Philanthropy report) · 2023-11-14
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 “However, I also think there are reasons for comfort.” 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 Joseph Carlsmith Version Retrieved for the candidate pack on 2026-10-29 (SHA-256 ff546752a0b14d17cd05e20e1d2ff553b1f431a440a1e48241a842955df597bb). arXiv v1 of 14 November 2023. Canonical address Open the canonical source ↗ Accessed 2026-10-29 Language English (en) Attribution Joseph Carlsmith, “Scheming AIs: Will AIs fake alignment during training in order to get power?”, 2023-11-14. 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 (9 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-carlsmith-2023-scheming-ais