The U.S. Army wants AI agents to attack enemy targets. What could go wrong?
The Army Wants to Sic AI Agents on Its Enemies. What Could Go Wrong?
According to documents obtained by The Intercept, U.S. Army Cyber Command (ARCYBER) is developing a platform codenamed ECHOTRIBBLE that turns AI agents into offensive weapons capable of acting autonomously, searching for and "clearing" enemy computer systems. The documents and contractor Q&A show that the program is mainly aimed at offensive missions: the agents self-replicate like worms, jump between devices, target both cloud and air-gapped systems, self-destruct after completing their mission, and are required to operate with minimal human supervision and exhibit autonomous behavior. Experts including machine learning professor David Krueger and RAND's William Marcellino warn that such systems, lacking human judgment, could along the way inadvertently harm poorly protected civilian and critical infrastructure. ARCYBER did not respond to The Intercept's questions about how accidental damage would be prevented.
Documents reveal that the U.S. Army is developing offensive agents that can self-replicate and autonomously lock onto targets, and experts worry they could along the way inadvertently harm civilian infrastructure.