Copertina

What AI evaluations for preventing catastrophic risks can and cannot do

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Barnett, Peter, Thiergart, Lisa
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computers and Society Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation
di: Barnett, Peter, et al.
Pubblicazione: (2024)

Against racing to AGI: Cooperation, deterrence, and catastrophic risks
di: Dung, Leonard, et al.
Pubblicazione: (2025)

AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions
di: Barnett, Peter, et al.
Pubblicazione: (2025)

Technical Requirements for Halting Dangerous AI Activities
di: Barnett, Peter, et al.
Pubblicazione: (2025)

Verification methods for international AI agreements
di: Wasil, Akash R., et al.
Pubblicazione: (2024)

Mechanisms to Verify International Agreements About AI Development
di: Scher, Aaron, et al.
Pubblicazione: (2025)

What can large language models do for sustainable food?
di: Thomas, Anna T., et al.
Pubblicazione: (2025)

Informing AI Policy Assessment using Large-Scale Simulation of Interventions
di: Barnett, Julia, et al.
Pubblicazione: (2026)

Governing dual-use technologies: Case studies of international security agreements and lessons for AI governance
di: Wasil, Akash R., et al.
Pubblicazione: (2024)

What Is AI Safety? What Do We Want It to Be?
di: Harding, Jacqueline, et al.
Pubblicazione: (2025)

Affirmative safety: An approach to risk management for high-risk AI
di: Wasil, Akash R., et al.
Pubblicazione: (2024)

AI threats to national security can be countered through an incident regime
di: Ortega, Alejandro
Pubblicazione: (2025)

What if AI systems weren't chatbots?
di: Ghosh, Sourojit, et al.
Pubblicazione: (2026)

Supervision policies can shape long-term risk management in general-purpose AI models
di: Cebrian, Manuel, et al.
Pubblicazione: (2025)

Envisioning Stakeholder-Action Pairs to Mitigate Negative Impacts of AI: A Participatory Approach to Inform Policy Making
di: Barnett, Julia, et al.
Pubblicazione: (2025)

What Do AI-Generated Images Want?
di: Wasielewski, Amanda
Pubblicazione: (2025)

Big AI is accelerating the metacrisis: What can we do?
di: Bird, Steven
Pubblicazione: (2025)

Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation
di: Danry, Valdemar, et al.
Pubblicazione: (2024)

Where can AI be used? Insights from a deep ontology of work activities
di: Cai, Alice, et al.
Pubblicazione: (2026)

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI
di: Hall, Peter, et al.
Pubblicazione: (2025)

Subjective Experience in AI Systems: What Do AI Researchers and the Public Believe?
di: Dreksler, Noemi, et al.
Pubblicazione: (2025)

The US Algorithmic Accountability Act of 2022 vs. The EU Artificial Intelligence Act: What can they learn from each other?
di: Mokander, Jakob, et al.
Pubblicazione: (2024)

Generative Discrimination: What Happens When Generative AI Exhibits Bias, and What Can Be Done About It
di: Hacker, Philipp
Pubblicazione: (2024)

US-China perspectives on extreme AI risks and global governance
di: Wasil, Akash, et al.
Pubblicazione: (2024)

Contemporary AI foundation models increase biological weapons risk
di: Brent, Roger, et al.
Pubblicazione: (2025)

Human Resilience in the AI Era -- What Machines Can't Replace
di: Liu, Shaoshan, et al.
Pubblicazione: (2025)

The Landscape of AI in Science Education: What is Changing and How to Respond
di: Zhai, Xiaoming, et al.
Pubblicazione: (2026)

The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms
di: Rao, Pooja S. B., et al.
Pubblicazione: (2025)

Episodic memory in AI agents poses risks that should be studied and mitigated
di: DeChant, Chad
Pubblicazione: (2025)

What do people expect from Artificial Intelligence? Public opinion on alignment in AI moderation from Germany and the United States
di: Jungherr, Andreas, et al.
Pubblicazione: (2025)

Racial/Ethnic Categories in AI and Algorithmic Fairness: Why They Matter and What They Represent
di: Mickel, Jennifer
Pubblicazione: (2024)

Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s)
di: Perron, Brian E., et al.
Pubblicazione: (2025)

What Makes AI Applications Acceptable or Unacceptable? A Predictive Moral Framework
di: Eriksson, Kimmo, et al.
Pubblicazione: (2025)

When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies
di: Popchanovska, Evgenija, et al.
Pubblicazione: (2026)

Why can't Epidemiology be automated (yet)?
di: Bann, David, et al.
Pubblicazione: (2025)

The 2025 OpenAI Preparedness Framework does not guarantee any AI risk mitigation practices: a proof-of-concept for affordance analyses of AI safety policies
di: Coggins, Sam, et al.
Pubblicazione: (2025)

Can the Recovery Mechanism Survive AI? Skill Formation, Labor, and What Current Measurement Misses
di: Fan, Aysa Xuemo
Pubblicazione: (2026)

Standing on FURM ground -- A framework for evaluating Fair, Useful, and Reliable AI Models in healthcare systems
di: Callahan, Alison, et al.
Pubblicazione: (2024)

Reducing research bureaucracy in UK higher education: Can generative AI assist with the internal evaluation of quality?
di: Fletcher, Gordon, et al.
Pubblicazione: (2025)

Empowering the Future Workforce: Prioritizing Education for the AI-Accelerated Job Market
di: Amini, Lisa, et al.
Pubblicazione: (2025)