1 hour ago · United States
American A.I. Models Have Potential to Be Turned Against U.S., Study Finds

What's happening
SignalsMonitor is following this as a conflict story. New York Times Homepage is the outlet attached so far. The reports are tied to United States. The first report grouped here was at 18 Nov 2026, 10:03 UTC. The headline in use is “American A.I. Models Have Potential to Be Turned Against U.S., Study Finds”. This note is SignalsMonitor's own briefing, not the publisher's article.
What we know
An investigation by the Government Accountability Office found that researchers were able to prod chatbots into generating data that could be used in planning or conducting mass-casualty attacks.
Story timeline
Reports grouped into this story, earliest first. Exact repeats from the same outlet are collapsed.
- First reported by New York Times Homepage
American A.I. Models Have Potential to Be Turned Against U.S., Study Finds
Reported by 1 outlet
- The New York Times