Inaugural report pioneered by AI Security Institute gives clearest picture yet of capabilities of most advanced AI

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.

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.