AI is easy to control
An essay by Nora Belrose and Quintin Pope, AI Optimism, dated 28 November 2023. The address carries 2023/11/28; the page metadata gives datePublished 2023-11-29T02:38:05 UTC.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Nora Belrose and Quintin Pope.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2023-11-28.
- Exact source
- AI is easy to control AI Optimism (optimists.ai) · published 2023-11-28 · 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.
Appears in
- Propositions about superintelligence, 1863–2022 →1 record on this document
- Arguments about catastrophic risk from advanced AI →4 records on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Articulates · 1
Propositions whose criterion a passage of this document meets. The record says what the text states, in its register; it is not evidence that the proposition is true.
- Advanced AI can be kept under control by designBelrose and Pope's essay of 28 November 2023 argues that AI, even superhuman AI, will remain much more controllable than humans for the foreseeable future, because neural networks are white boxes open to gradient descent and other control methods, and that it will be easy to instil human values into AI.2023-11-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Advanced AI can be kept under control by design: propositions page →
Contests · 3
Propositions a passage of this document disputes, or a premise they depend on.
- Treacherous turnBelrose and Pope's essay of November 2023 argues that gradient descent sees all of an AI's computation, so that a secret plan to harm its overseers would be noticed and trained away, and that such plans do not improve performance on the tasks AIs are trained for.2023-11-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Treacherous turn: propositions page →
- Inner or deceptive misalignmentBelrose 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.2023-11-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Inner or deceptive misalignment: propositions page →
- Difficulty of alignmentBelrose and Pope's essay of November 2023 argues that AI, even superhuman AI, will remain much more controllable than humans for the foreseeable future, and that it will be easy to instill human values into an AI.2023-11-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Difficulty of alignment: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.