An Overview of Catastrophic AI Risks
A preprint by Dan Hendrycks, Mantas Mazeika and Thomas Woodside, arXiv:2306.12001, dated 21 June 2023. arXiv v1 submission date.
- 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 Dan Hendrycks, Mantas Mazeika and Thomas Woodside.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2023-06-21.
- Exact source
- An Overview of Catastrophic AI Risks arXiv:2306.12001 · published 2023-06-21 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 9df5eca6a17e1c3f1482ccde84eb508cd7dc3c0eb5139cd0770a66a47edb85da). arXiv v1 PDF (2306.12001v1).
Appears in
- 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 · 2
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.
- Existential risk from misalignment or loss of controlThe paper by Hendrycks, Mazeika and Woodside of June 2023 names rogue AIs as a source of catastrophic risk, stating that humans might lose control over AIs as they become more intelligent, through proxy gaming, goal drift, power-seeking and deception.2023-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Existential risk from misalignment or loss of control: propositions page →
- Catastrophic risk from misuseThe paper by Hendrycks, Mazeika and Woodside of June 2023 names malicious use as one of four sources of catastrophic AI risk and states that AI-assisted bioweapons could constitute an existential threat by enlarging the number of people able to create pandemics.2023-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Catastrophic risk from misuse: propositions page →
Contests · 2
Propositions a passage of this document disputes, or a premise they depend on.
- Open models reduce riskHendrycks, Mazeika and Woodside's overview of 21 June 2023 argues that open-sourcing an AI system with biological research capabilities could increase the risk of malicious use, and recommends that developers avoid open-sourcing the most powerful systems in favour of structured access.2023-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Open models reduce risk: propositions page →
- Economic incentives will produce safetyHendrycks, Mazeika and Woodside's overview of 21 June 2023 argues that competitive pressure fuels a corporate AI race in which companies race to offer the first products to market rather than the safest, and recommends safety regulation so that developers do not cut corners.2023-06-21 · publication · Stated in source · Supported Inspect claim & evidence ↗Economic incentives will produce safety: 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.