The AI Security Institute has paired up with Canadian counterpart, Amazon, Anthropic and civil society to research AI behaviour and control, focusing on making sure that this new technology acts in our interests.

This UK-led project has been backed by £15 million and will help unlock the benefits of advanced AI while also cementing the UK’s position as a global leader in AI. It is led by the UK’s AI Security Institute and backed by an international coalition including the Canadian AI Safety Institute, Canadian Institute for Advanced Research (CIFAR), Schmidt Sciences, Amazon Web Services (AWS), Anthorpic, Halcyon Futures, and Safe AI Fund, UK Research and Innovation, and the Advanced Research and Invention Agency.

The research reflects a growing consensus about the safety of AI, and ensuring its progress is not hampered by harmful behaviours which could pose a risk to society. Thus, this project will fund research into AI alignment, including ways to make sure AI systems continue to follow our goals as the technology becomes more capable and finding techniques to ensure AI systems remain transparent and responsive to human oversight.

The Alignment Project, led by an expert advisory board including Yoshua Bengio, Zico Kolter, Shafi Goldwasser, and Andrea Lincoln, will remove key barriers that have previously limited alignment research by offering three levels of support: up to £1 million of grant funding of researchers, up to £5 million dedicated cloud computing credits from AW, and venture capital to accelerate commercial alignment solutions.

Science, innovation, and technology secretary Peter Kyle said: “Advanced AI systems are already exceeding human performance in some areas, so it’s crucial we’re driving forward research to ensure this transformative technology is behaving in our interests.

“AI alignment is all geared towards making systems behave as we want them to, so they are always acting in our best interest. This is at the heart of the work the Institute has been leading since day one—safeguarding our national security and ensuring the British public are protected from the most serious risks AI could pose as the technology becomes more and more advanced.AI

“The responsible development of AI needs a co-ordinated global approach, and this fund will help us make AI more reliable, more trustworthy, and more capable of delivering the growth, better public services, and high-skilled jobs that drive our Plan for Change.”