Superintelligence: Paths, Dangers, Strategies
Work-level record. Each recorded version is listed as a source with its own date. A citation to the work does not identify which version the citing author read.
- 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 Oxford Martin School.
- Dates
- No date claim recorded yet. A missing record is a gap in coverage.
- Exact source
- Superintelligence: Paths, Dangers, Strategies Oxford Martin School · publication date unknown · Publication listing of the book on the Oxford Martin School site, giving the Oxford University Press hardback date, 3 July 2014, and its ISBN. Read by the cross-family check on 2026-10-30 (item A001); not read again at admission. The pack retrieved no text of the book.
Appears in
No collection holds a record about this document yet.
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.
Cited by · 13
Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.
- CorrigibilityCorrigibility cites Superintelligence: Paths, Dangers, Strategies.2015-01-25 · publication · Stated in source · Supported Inspect claim & evidence ↗Soares et al., Corrigibility (2015): document page →
- Alignment for Advanced Machine Learning SystemsAlignment for Advanced Machine Learning Systems cites Superintelligence: Paths, Dangers, Strategies.2016 · publication · Stated in source · Supported Inspect claim & evidence ↗Alignment for Advanced Machine Learning Systems: document page →
- Concrete Problems in AI SafetyConcrete Problems in AI Safety cites Superintelligence: Paths, Dangers, Strategies.2016-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Concrete Problems in AI Safety: document page →
- Deep reinforcement learning from human preferencesDeep reinforcement learning from human preferences cites Superintelligence: Paths, Dangers, Strategies.2017-06-12 · publication · Stated in source · Supported Inspect claim & evidence ↗Deep reinforcement learning from human preferences: document page →
- Artificial Intelligence and Its Implications for Income Distribution and UnemploymentArtificial Intelligence and Its Implications for Income Distribution and Unemployment cites Superintelligence: Paths, Dangers, Strategies.2017-12 · publication · Stated in source · Supported Inspect claim & evidence ↗Korinek and Stiglitz, Artificial Intelligence and Its Implications for Income Distribution and Unemployment (2017): document page →
- Self-Regulating Artificial General IntelligenceSelf-Regulating Artificial General Intelligence cites Superintelligence: Paths, Dangers, Strategies.2018-02 · publication · Stated in source · Supported Inspect claim & evidence ↗Gans, Self-Regulating Artificial General Intelligence (2018): document page →
- Supervising strong learners by amplifying weak expertsSupervising strong learners by amplifying weak experts cites Superintelligence: Paths, Dangers, Strategies.2018-10-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Supervising strong learners by amplifying weak experts: document page →
- Scalable agent alignment via reward modeling: a research directionScalable agent alignment via reward modeling: a research direction cites Superintelligence: Paths, Dangers, Strategies.2018-11-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Scalable agent alignment via reward modeling: a research direction: document page →
- Introduction to "The Economics of Artificial Intelligence: An Agenda"Introduction to "The Economics of Artificial Intelligence: An Agenda" cites Superintelligence: Paths, Dangers, Strategies.2019-05 · publication · Stated in source · Supported Inspect claim & evidence ↗Agrawal, Gans, Goldfarb, Introduction to "The Economics of Artificial Intelligence (2019): document page →
- Can Socially-Minded Governance Control the AGI Beast?Can Socially-Minded Governance Control the AGI Beast? cites Superintelligence: Paths, Dangers, Strategies.2023-11 · publication · Stated in source · Supported Inspect claim & evidence ↗Gans, Can Socially-Minded Governance Control the AGI Beast (2023): document page →
- The A.I. Dilemma: Growth versus Existential RiskThe A.I. Dilemma: Growth versus Existential Risk cites Superintelligence: Paths, Dangers, Strategies.2023-11 · publication · Stated in source · Supported Inspect claim & evidence ↗Jones, The A.I. Dilemma (2023): document page →
- How Much Should We Spend to Reduce A.I.'s Existential Risk?How Much Should We Spend to Reduce A.I.'s Existential Risk? cites Superintelligence: Paths, Dangers, Strategies.2025-03 · publication · Stated in source · Supported Inspect claim & evidence ↗Jones, How Much Should We Spend to Reduce A.I.'s Existential Risk (2025): document page →
- GPT-4 System CardGPT-4 System Card cites Superintelligence: Paths, Dangers, Strategies.Date unknown · Stated in source · Supported Inspect claim & evidence ↗GPT-4 System Card: document page →
Ideas attributed to this work by · 5
Recorded documents that attribute an argument, concept, term, finding or approach to this one. Each attribution is the citing document’s claim.
- CorrigibilitySoares, Fallenstein, Yudkowsky and Armstrong (2015) attribute the term “treacherous turn”, for an agent that conceals its utility function until it can avoid correction, to Bostrom (2014).2015-01-25 · publication · Stated in source · Supported Inspect claim & evidence ↗Soares et al., Corrigibility (2015): document page →
- Alignment for Advanced Machine Learning SystemsAlignment for Advanced Machine Learning Systems (MIRI, 2016) frames its objective-specification problems as a way to ameliorate dangers it attributes to Bostrom's Superintelligence (2014).2016 · publication · Stated in source · Supported Inspect claim & evidence ↗Alignment for Advanced Machine Learning Systems: document page →
- Self-Regulating Artificial General IntelligenceGans (2018) takes its definition of the control problem, which the paper then examines with the tools of economic theory, from a quotation of Bostrom (2014, p. 128).2018-02 · publication · Stated in source · Supported Inspect claim & evidence ↗Gans, Self-Regulating Artificial General Intelligence (2018): document page →
- Introduction to "The Economics of Artificial Intelligence: An Agenda"Agrawal, Gans and Goldfarb (2019), summarising a discussant’s comment that humans must tell machines what to optimise, attribute the name “value-loading problem” for that task to Bostrom (2014).2019-05 · publication · Stated in source · Supported Inspect claim & evidence ↗Agrawal, Gans, Goldfarb, Introduction to "The Economics of Artificial Intelligence (2019): document page →
- Can Socially-Minded Governance Control the AGI Beast?Gans (2023) attributes the existential-risk concerns of OpenAI's funders, which it says shaped OpenAI's governance structure, to their having been outlined by Bostrom (2014), and calls those concerns controversial.2023-11 · publication · Stated in source · Supported Inspect claim & evidence ↗Gans, Can Socially-Minded Governance Control the AGI Beast (2023): document page →
Not recorded for this document: cites · 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.