Testing the limits of what’s possible (and what isn’t) with AI

Testing the limits of what’s possible (and what isn’t) with AI Sarah Collins Tue, 07/14/2026 - 10:00 The researchers, from the University of Cambridge and the University of California Santa Barbara, designed ‘adversarial’ mathematical systems designed to fool any AI algorithm. Like ethical hackers stress-testing the security of a network, these adversarial systems were designed to map out exactly where and why AI prediction breaks down. Many real-world systems – like those in oceans, the human brain, or robotics – are too complex to describe neatly with equations, so researchers often learn ho