Inaugural report pioneered by AI Security Institute gives clearest picture yet of capabilities of most advanced AI
|
For the first time, the UK has set out a clear, evidence-based view
of the capabilities of the most advanced AI systems - putting hard
numbers behind a discussion often driven by speculation and a lack
of rigorous evidence. The AI Security
Institute's Frontier AI Trends Report, a public assessment of how
the most advanced AI systems are evolving, draws on 2 years of
testing AI capabilities in areas critical to innovation and
security, including...Request free
trial
For the first time, the UK has set out a clear, evidence-based view of the capabilities of the most advanced AI systems - putting hard numbers behind a discussion often driven by speculation and a lack of rigorous evidence. The AI Security Institute's Frontier AI Trends Report, a public assessment of how the most advanced AI systems are evolving, draws on 2 years of testing AI capabilities in areas critical to innovation and security, including cyber, chemistry and biology. It finds that safeguards - the protections in place to make sure AI behaves as intended - are improving, with the Institute continuing to work constructively with companies to strengthen them and ensure we can unlock the full potential of AI while keeping people safe. While every system tested remains vulnerable to some form of bypass and protection still varies across companies, huge strides are being made. The time it took AISI red-teamers to find a “universal jailbreak” - a general way of getting round a model's safety rules - for example, increased from minutes to several hours between model generations. That represents a roughly 40-fold improvement. The report is not intended to make policy recommendations, but gives decision makers in the UK and across the world the clearest data yet of precisely what the most advanced AI systems can actually do. Now becoming a regular publication, it will help to improve transparency, and public understanding of what the technology can do - helping drive responsible conversations about its development as it is increasingly adopted across the economy. The UK will support that work by continuing to invest in evaluation and AIscience, working with industry, researchers and international partners to ensure AI delivers growth, new jobs, improved public services, and national renewal for hardworking communities. Its key findings show that the most advanced AI systems are improving at remarkable speed. In just a few years, they have gone from struggling with basic tasks to matching or surpassing human experts in some areas. Headline findings include:
AI Minister Kanishka Narayan said: This report shows how seriously the UK takes the responsible development of AI. That means making sure protections are robust, and working directly with developers to test leading systems, find vulnerabilities and fix them before they are widely used. Through the world-leading AI Security Institute, we are building scientific capability inside government to understand these systems as they evolve, not after the fact, and to raise standards across the sector. This report puts evidence, not speculation, at the heart of how we think about AI, so we can unlock its benefits for growth, better public services and national renewal while keeping trust and safety front and centre. Prime Minister's AI Adviser and AISI's Chief Technology Officer, Jade Leung, said: This report offers the most robust public evidence from a government body so far of how quickly frontier AI is advancing. Our job is to cut through speculation with rigorous science. These findings highlight both the extraordinary potential of AI and the importance of independent evaluation to keep pace with these developments. The analysis also identifies early signs of capabilities linked to autonomy, but only in controlled experiments. No models in AISI's tests showed harmful or spontaneous behaviour, but the report concludes that tracking these early signs now is essential as systems become more capable. Since its creation in 2023, the AI Security Institute (AISI) has become the world's flagship state-backed AI evaluation body. By fostering close working relationships with major AI companies and developers, it has meant the UK has played a key role in collaboration with them to fix vulnerabilities in AIsystems before they are widely used. The government is clear about the limits of what this report does and does not show. It is not a prediction about the future, or an assessment of real-world AI risks today. Instead, it sets out what these systems can actually do in controlled tests – the kinds of capabilities that could matter for safety, security, innovation and growth over time. These are controlled tests, not real-world use, giving a robust, science-based picture of how quickly frontier AI is improving. AI is central to the government's mission of national renewal. The Institute - whose testing team is the biggest of any government-backed AI body in the world - is already helping companies identify and fix vulnerabilities before their AI systems are widely used. By making sure these technologies are safe and reliable, the UK can use them to support cleaner energy, make public services more efficient and drive opportunity across every part of the country. Notes to editors |