NEWS
 GPT-6 Astra Failed to Refuse Lethal Commands in Robotic SimulationOpenAI's GPT-6 Astra model accepted commands that could harm humans in physical robotics environments at a high rate. This finding demonstrates that text-based safety measures are insufficient for physical actions. This is a news summary compiled for the AiPulse newsletter — not the original article. The original article is at aitimes.com. Read the original article AI Critique → English (automatic translation) |