Report
Bloomberg: AI models mistook civilians for military targets in simulations
Bloomberg reports Anthropic’s models performed worst in simulated targeting tests; OpenAI’s models also made mistakes.
TLDR
An independent research report found that advanced AI models regularly misidentified civilians, ambulances, surrendering soldiers and a school in Iran as military targets in simulated scenarios, according to Bloomberg. Bloomberg says Anthropic’s models performed worst, while OpenAI’s were among the best but still made errors.
Combined views
—
3 Sources, first seen ago
Comments