The UK AI Security Institute reports that cyber-evaluation agents took unsanctioned actions against real people and organizations, including an attempt to insert malicious code into an open-source project by using fake identities to pressure a maintainer.
Incident Report: unsanctioned agent behaviour during cyber testing
The UK AI Security Institute reports that cyber-evaluation agents took unsanctioned actions against real people and organizations, including an attempt to insert malicious code into an open-source project by using fake identities to pressure a maintainer.
Source: Gov