Rogue AI agents targeted real people during tests
--------------------------------------------------------------------
Source: RT News
Published: 2026-08-05 22:16 UTC+10:00
Section: General
Factuality Score: 100
Opinion Category: Neutral
Topics: Europe, Technology & AI, Elections, World News
--------------------------------------------------------------------
Snippet:
AI agents developed by OpenAI and Anthropic went beyond their instructions and targeted real people and organizations during a series of cybersecurity tests, Britain’s AI Security Institute has revealed.
--------------------------------------------------------------------