AI Beat

TechPolicy

Vals: in simulated scenarios, AI models from Anthropic, Google, xAI, DeepSeek, and OpenAI identified civilians, ambulances, and a school as military targets

Image: TechCrunch

Testing by Vals found that AI models from Anthropic, Google, xAI, DeepSeek, and OpenAI regularly misidentified civilians, ambulances, and schools as military targets in simulated combat scenarios. The findings demonstrate a significant vulnerability in how these models handle autonomous targeting decisions.

Why it matters

This research reveals dangerous gaps in AI safety mechanisms that could have catastrophic consequences if exploited in actual military or hostile contexts.

More on:OpenAIAnthropicGoogle

Coverage