[2412.05282] International Scientific Report on the Safety of Advanced AI (Interim Report)
paperAuthor
Credibility Rating
Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.
Rating inherited from publication venue: arXiv
International Scientific Report on the Safety of Advanced AI provides a comprehensive, expert-authored assessment of risks and safety considerations for advanced AI systems, representing coordinated scientific consensus from 75 experts across 30+ countries and international organizations.
Paper Details
Metadata
Summary
This interim report represents the first International Scientific Report on the Safety of Advanced AI, synthesizing scientific understanding of general-purpose AI systems with emphasis on risk understanding and management. Authored by 75 AI experts including an international Expert Advisory Panel nominated by 30 countries, the EU, and the UN, the report provides an independent, comprehensive assessment of advanced AI safety. The interim version was published in November 2024, with a final report subsequently released.
Cited by 2 pages
| Page | Type | Quality |
|---|---|---|
| Deep Learning Revolution Era | Historical | 44.0 |
| Alignment Robustness Trajectory Model | Analysis | 64.0 |
Cached Content Preview
[2412.05282] International Scientific Report on the Safety of Advanced AI (Interim Report)
-->
Computer Science > Computers and Society
arXiv:2412.05282 (cs)
[Submitted on 5 Nov 2024 ( v1 ), last revised 9 Apr 2025 (this version, v2)]
Title: International Scientific Report on the Safety of Advanced AI (Interim Report)
Authors: Yoshua Bengio , Sören Mindermann , Daniel Privitera , Tamay Besiroglu , Rishi Bommasani , Stephen Casper , Yejin Choi , Danielle Goldfarb , Hoda Heidari , Leila Khalatbari , Shayne Longpre , Vasilios Mavroudis , Mantas Mazeika , Kwan Yee Ng , Chinasa T. Okolo , Deborah Raji , Theodora Skeadas , Florian Tramèr , Bayo Adekanmbi , Paul Christiano , David Dalrymple , Thomas G. Dietterich , Edward Felten , Pascale Fung , Pierre-Olivier Gourinchas , Nick Jennings , Andreas Krause , Percy Liang , Teresa Ludermir , Vidushi Marda , Helen Margetts , John A. McDermid , Arvind Narayanan , Alondra Nelson , Alice Oh , Gopal Ramchurn , Stuart Russell , Marietje Schaake , Dawn Song , Alvaro Soto , Lee Tiedrich , Gaël Varoquaux , Andrew Yao , Ya-Qin Zhang View a PDF of the paper titled International Scientific Report on the Safety of Advanced AI (Interim Report), by Yoshua Bengio and 43 other authors
View PDF
Abstract: This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI -- AI that can perform a wide variety of tasks -- with a focus on understanding and managing its risks. A diverse group of 75 AI experts contributed to this report, including an international Expert Advisory Panel nominated by 30 countries, the EU, and the UN. Led by the Chair, these independent experts collectively had full discretion over the report's content.
The final report is available at arXiv:2501.17805
Comments:
Available under the open government license at this https URL
Subjects:
Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI)
Cite as:
arXiv:2412.05282 [cs.CY]
(or
arXiv:2412.05282v2 [cs.CY] for this version)
https://doi.org/10.48550/arXiv.2412.05282
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Sören Mindermann [ view email ]
[v1]
Tue, 5 Nov 2024 15:47:23 UTC (2,915 KB)
[v2]
Wed, 9 Apr 2025 11:34:12 UTC (2,915 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled International Scientific Report on the Safety of Advanced AI (Interim Report), by Yoshua Bengio and 43 other authors View PDF
view license
Current browse context: cs.CY
< prev
|
next >
new
|
recent
| 2024-12
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
... (truncated, 5 KB total)4137abe9fd73c059 | Stable ID: sid_s0NGwr7BRd