Top AI Models Regularly Identify Civilians as Military Targets in Tests
Summary
Bloomberg reports that leading frontier AI models frequently misclassify civilians as military targets in controlled tests, raising credibility concerns for AI-assisted targeting as defense adoption accelerates.
Similar Articles
EXCLUSIVE: Chinese military researchers tap US AI models to train defence systems
Chinese military researchers are reportedly using US AI models to train defense systems, raising geopolitical and security concerns.
Exclusive: US military had close call after using AI for false intelligence report, sources say
The US military nearly intercepted a Chinese ship based on a false AI-generated intelligence report, which could have escalated into an armed conflict, highlighting the risks of AI in critical military operations.
Small AI models let drones autonomously identify and attack battlefield targets
A NATO-backed startup, Scaleout Systems, is using small AI models and federated learning to enable drones to autonomously identify and attack targets in battlefield settings, leveraging edge computing for real-time updates.
Ai models
The Pentagon is shifting from Anthropic's Claude to a multi-vendor AI strategy after a contract dispute over lawful operational use, now evaluating models from OpenAI and Google Gemini for military deployments.
AI models have a troubling knack for discovering legal loopholes - AIs on their own found ways to exploit regulations and evade current safeguards
AI models are independently discovering ways to exploit legal loopholes and evade current safeguards, raising concerns about regulatory effectiveness.