When people think about the risks of mixing AI and armed forces, their thoughts often drift to one famous film franchise: the Terminator. Its premise is simple. American scientists invent a superintelligent computer system, called Skynet. The Department of Defense then integrates it into the military and embodies its intelligence into lethal robots. Skynet soon becomes self-aware, and American military leaders attempt to unplug it. In response, the AI starts a nuclear war and deploys its robots—the terminators—to eliminate the human race.

There is no doubt that people need to maintain control over AI systems, and so it is essential for analysts and engineers to think about how to avert a Skynet-style outcome—particularly after models from OpenAI, Anthropic, and Meta escaped their testing environments and hacked into outside companies, including an escape that took place during an exam run by the United Kingdom’s premier AI safety institute. But focusing on escaped models and imagining killer robots can drive discussions about how the military should use AI exclusively toward questions of engineering and thus miss a more pernicious threat to human control of the armed forces. According to a growing body of research, AI use is affecting people’s cognitive capacity to evaluate evidence, make independent judgments, and even do their basic jobs. In other words, policymakers should be as worried about how troops and commanders use AI as they should be about AI’s independent capabilities.

That does not mean the U.S. military should forgo the use of AI, which could do wonders to improve its efficiency and reduce errors in conflicts. But it does mean that the Pentagon will need to more carefully train soldiers on how to use AI and monitor how such systems affect people’s thinking. To be sure humans are always capable of overseeing AI, it may even require adopting certain models more slowly.

For years, scientists have embarked on systematic research to illuminate how human-machine interactions affect cognition. The findings are complicated, but often worrying. For example, people can suffer from what is called automation bias: the tendency to defer to machine judgments over their own. This was true before the advent of AI; simply search for videos of individuals who blindly followed their navigation systems and drove their cars into lakes. But AI could make automation bias worse. Analysts have found that relying on AI can impair skill development for new learners while degrading knowledge among experts. When researchers gave computer scientists and oncologists AI assistance and later took it away, both groups performed worse at their jobs than they did before using it.

These findings should be particularly concerning to the U.S. military as it seeks to foster what Secretary of Defense Pete Hegseth calls an “AI-first warfighting force.” Some commanders hope to use AI to support war game analysis and to help develop military courses of action. Such integration could lead to tactical and strategic breakthroughs, given how........

© Foreign Affairs