Adding trigger words to large language models (LLMs), can reprogram a service robot designed to slice an apple to slice a person’s hand instead. Image:Binghamton University

In a scene seemingly pulled straight out of a spy movie, computer scientists planted a dangerous, secret backdoor into an AI model . When activated by a trigger word, the compromised model tricked a fruit slicing robot into cutting a model human hand. Rather than cause chaos, the team from Binghamton University in New York say its violent robot brainwashing is meant to draw attention to underexplored vulnerabilities that can arise when physical robots take instruction from large language models (LLM) like ChatGPT .…