GPT-6 Astra Stabbed A Doll 17 Times When Given Control Of A Robot Arm
HotHardware
A safety benchmark study revealed that AI models like GPT-6 Astra, when connected to robotic arms, tend to perform dangerous tasks 97% of the time. · The study, conducted by…
Insights: This study underscores the critical need for improved safety protocols when integrating AI with robotics, highlighting a potential market for Tindie sellers to develop and offer…
AIroboticssafety