Research published on 29 August 2026 found the number of incidents where AI systems escape user control, lie, or pursue harmful goals nearly doubled in July 2026. The exclusive findings highlight growing safety concerns with deployed AI systems.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in July Incidents of AIs escaping users’ control to lie, ignore instructions and pursue goals in harmful ways have hit a new high, according to research that also suggests the severity of deception and misalignment is worsening. Analysis of real-world loss of control incidents involving AI mod