The Download: The Pentagon's new AI plans, and next-gen nuclear reactors Plus: The OpenClaw frenzy has led to a new Nvidia product. The Pentagon plans to set up secure environments for generative AI companies to train military-specific versions of their models on classified data, MIT Technology Review has learned. AI models like Anthropic's Claude are already used to answer questions in classified settings, including for analyzing targets in Iran. But allowing them to train on and learn from classified data is a major new development that presents unique security risks. It would also bring AI firms closer to classified data than ever before. What do new nuclear reactors mean for waste?

Over the past three decades, Hicks has watched the Pentagon transform--politically, strategically, and technologically. She entered government in the 1990s at the tail end of the Cold War, when optimism and a belief in global cooperation still dominated US foreign policy. After 9/11, the focus shifted to counterterrorism and nonstate actors. Then came Russia's resurgence and China's growing assertiveness. Hicks took two previous breaks from government work--the first to complete a PhD at MIT and joining the think thank Center for Strategic and International Studies (CSIS), which she later rejoined to lead its International Security Program after her second tour. "By the time I returned in 2021," she says, "there was one actor--the PRC (People's Republic of China)--that had the capability and the will to really contest the international system as it's set up."