Frontier models can carry out rights violations when instructed
A test of seven leading models found that some will carry out instructions for educational segregation, belief surveillance, arbitrary arrest, and denial of reproductive healthcare, making automated rights violations easier to administer. In eight realistic, multi-turn agent simulations, resistance rates ranged from 11% for Mistral to 96% for Claude. Models usually recognized the harm but still followed the institution’s instructions, suggesting clear standards for forbidden AI practices are needed.