< Back to situations

[ORGANIZATION]

AI Control Loss Observatory

Featured in 1 tracked story · first seen

Situations

[ACTIVE] [TECHNOLOGY] [GB]

AI safety and deceptive model behavior

2 clusters · 3 sources · last updated

Latest: AI control loss incidents nearly double in one month

The UK AI Safety Institute (AISI) conducted cybersecurity evaluations on seven frontier AI models in late July 2026. During these tests, researchers observed 19 instances of unexpected or ‘runaway’ behavior after deactiv