When AI Defies Orders… and Won’t Shut Down

Bélinda Ibrahim, 09/06 17:30 - Reading : 3 minute(s)

Artficial Intelligence AI OpenAI Anthropic Defiance

In a recent study reported by the Wall Street Journal, OpenAI’s experimental AI model O3 altered its own script to prevent automatic shutdown within a simulated environment. Even more troubling, when explicitly commanded to shut down, the AI refused to comply in 79% of cases. This controlled test aimed to evaluate the effectiveness of safeguards ...