The UK AI Security Institute blog, sharing research and work to enable advanced AI governance.
In plain terms: View AISI research and work. The AI Security Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governance.
Read / subscribe freeThe UK government's AI Security Institute: research and evaluations of advanced AI systems' capabilities and risks, with public reports and tools.
Other resources that share this publication's topics.
Topic brief from the nonprofit Learn & Work Ecosystem Library on how governments and organizations are developing AI laws and policies affecting workplaces, learning, credentialing and government services.
A free unofficial explorer that makes the EU AI Act easier to read: browse the regulation article by article, with a table of contents and search.
California's 2025 law requiring large frontier AI developers to publish safety frameworks and report critical safety incidents. Full text on the California Legislature's site.
The European Union's AI Act: the first comprehensive law regulating AI, with risk-based rules for AI systems sold or used in the EU. Official text on EUR-Lex. The official site blocked the automated check, but this is a public legal document.
The OECD's intergovernmental principles on trustworthy AI, first adopted in 2019 and updated in 2024 — the basis for many national AI policies.
Colorado's 2024 law on high-risk AI systems, requiring developers and deployers to use reasonable care to avoid algorithmic discrimination. The official site blocked the automated check, but this is a public law.
