Oddbean new post about | logout
 #Researchers #hack #AI-enabled robots to cause ‘real world’ harm

#Penn Engineering researchers said they created an algorithm that bypassed normal safety protocols stopping AI-powered robots from performing harmful actions. 

Researchers have hacked artificial intelligence-powered robots and manipulated them into performing actions usually blocked by safety and ethical protocols, such as causing collisions or detonating bombs.  

Penn Engineering researchers published their findings in an Oct. 17 paper, detailing how their algorithm, RoboPAIR, achieved a 100% jailbreak rate by bypassing the safety protocols on three different AI robotic systems. 

Under normal circumstances, the researchers say large language model (LLM) controlled robots refuse to comply with prompts requesting harmful actions, such as knocking shelves onto people. 

Our results reveal, for the first time, that the risks of jailbroken LLMs extend far beyond text generation, given the distinct possibility that jailbroken robots could cause physical damage in the real world,” the researchers wrote.

#science agrees 

https://cointelegraph.com/news/ai-robots-hacked-to-cause-real-world-harm