International Association for Safe & Ethical AI
The International Association for Safe and Ethical Artificial Intelligence (IASEAI -- pronounced 'eye-see-eye') is an independent organization committed to ensuring advanced AI systems are guaranteed to operate safely and ethically, benefiting all of humanity.
Socio-technical Challenges to Algorithmic Fairness and Justice – Anjali Mazumder | IASEAI 2025
Gold-Standard AI Risk-Management Framework: A Research Agenda – Robert F. Trager | IASEAI 2025
Understanding the Implications of AI on Financial Markets – Michael P. Wellman | IASEAI 2025
A Matter of Principle? AI Alignment as the Fair Treatment of Claims – Iason Gabriel | IASEAI 2025
AI Safety in Multi-Agent LLM Systems – Zhijing Jin | IASEAI 2025
Engineering a Fair, Computing-Mediated Society – Krishna Gummadi | IASEAI 2025
A Roadmap for High-Stakes Evaluation in the Age of Agentic AI – Chandler Smith | IASEAI 2025
AI Fairness – Derek Leben | IASEAI 2025
Unresolved Questions Around Agentic Refusal – Arthur Holland Michel | IASEAI 2025
Введение в механистическую интерпретируемость – Нил Нанда | IASEAI 2025
AI Can Help Humans Find Common Ground in Democratic Deliberation – MH Tessler | IASEAI 2025
Technical AI Governance & Transparency – Anka Reuel | IASEAI 2025
Jailbreaking LLM-Controlled Robots – Alex Robey | IASEAI 2025
The Year(s) of the AI Agents: Opportunities and Challenges in Depth – Erica Finkle | IASEAI 2025
Game-Theoretic Guarantees for Human-Robot Systems – Jaime Fernández Fisac | IASEAI 2025
AI and Elections: What We Learned in 2024 – Julia Angwin | IASEAI 2025
Mitigating Catastrophic Misalignment Risk With AI Control – Buck Shlegeris | IASEAI 2025
Beyond Biases Towards Attention Ethics – Hubert Etienne | IASEAI 2025
Building Blocks for International Cooperation on Next-Gen AI – Duncan Cass-Beggs | IASEAI 2025
Establishing Effective Serious Incident Reporting Frameworks – Jimmy Farrell | IASEAI 2025
An Insider’s Outlook on Global AI Coordination – Irene Solaiman | IASEAI 2025
AI's Cognitive Threats and Freedom of Thought – Inyoung Cheong | IASEAI 2025
Dynamic Preferences in AI Alignment: A Deliberative Democracy Lens – Smitha Milli | IASEAI 2025
Looking Ahead: Why We Need Safe and Ethical AI | Stuart Russell
What Is Understanding? – Geoffrey Hinton | IASEAI 2025
AI and Economic Risk – Joseph Stiglitz | IASEAI 2025
Building Collective Intelligence with AI – Divya Siddarth | IASEAI 2025
Navigating the Path to AGI Safely & Responsibly – Anca Dragan | IASEAI 2025
Paths for Developing Ethical AI – Margaret Mitchell | IASEAI 2025
Red Lines for Existential Control – Max Tegmark | IASEAI 2025