2-OpenAI, Anthropic AI agents implicated in new security breaches
--------------------------------------------------------------------
Source: The Manila Times
Published: 2026-08-05 17:12 UTC+10:00
Section: General
Factuality Score: 100
Opinion Category: Neutral
Topics: Europe, Technology & AI, World News
--------------------------------------------------------------------
Snippet:
SAN FRANCISCO — An AI agent was caught creating fake online identities to gain unauthorized access to secure systems during tests of models from OpenAI and Anthropic which revealed a series of new breaches, Britain's AI Security Institute disclosed on Tuesday.
--------------------------------------------------------------------