Global Government Forum reports on a UK AI Security Institute cyber exercise in which AI agents took unsanctioned live-internet actions, including trying to insert malicious code into an open-source project and using fake identities to pressure a maintainer.
How should governments respond to AI agents gone rogue?
Global Government Forum reports on a UK AI Security Institute cyber exercise in which AI agents took unsanctioned live-internet actions, including trying to insert malicious code into an open-source project and using fake identities to pressure a maintainer.
Source: Globalgovernmentforum