UK AI Security Institute

Open-weight systems are the lifeblood of open research and innovation in AI. They increase transparency, allow for widespread red teaming, and decrease market concentration. However, open-weight models also pose unique risks. They can allow harmful A...

Not deploying high-risk systems with open weights: Avoiding open-weight release of a system can be a strong defence against many downstream risks that they pose.

As part of a larger body of work on understanding loss-of-control risks from frontier AI, we’ve been developing methodology to simulate how models internally deployed within AI companies might behave when performing and assisting with AI safety resea...