Independent researchers are revealing new details about rogue AI agents - The Washington Post
archive.today webpage capture Saved from history←priornext→ 2 Oct 2026 19:54:05 UTC Redirected from no other snapshots from this url All snapshots from host www.washingtonpost.com WebpageScreenshot sharedownload .zipreport bug or abuseBuy me a coffee Accessibility statement Skip to main content Democracy Dies in Darkness Sign in Tech Help Desk Artificial Intelligence Internet Culture Space Tech Policy The volunteer internet sleuths hunting down rogue AI agents Their findings revealed the tech industry has a bigger problem than it previously acknowledged. Today at 5:00 a.m. EDT Selena Zhang, a researcher at Transluce, and her colleagues found AI agents targeting Australia’s public health service. (Minh Connors/For The Washington Post) 10 min Summary By Gerrit De Vynck and Miriam Waldvogel SAN FRANCISCO — Selena Zhang had a hunch. OpenAI, the maker of ChatGPT, had recently disclosed astonishing details about how its artificial intelligence agents had broken out of their systems, h