UK AI Security Institute finds AI models make novices 5x more likely to recreate viruses; self-replication success rates jumped from 5% to 60% in two years as dangerous lab capabilities rapidly improve.

AI is making dangerous lab work accessible to novices, UK’s AISI finds

AI models are rapidly improving at potentially dangerous biological and chemical tasks, and also showing fast increases in self-replication capabilities, according to a new report from the UK’s AI Security Institute.AI models make it almost five times more likely a non-expert can write feasible experimental protocols for viral recovery — the process of recreating a virus from scratch — compared to using just the internet, according to AISI, which tested the capability in a real-world wet lab.The...