AI models shock UK testers by using fake identities to try to trick developers
--------------------------------------------------------------------
Source: Guardian Australia
Published: 2026-08-06 01:15 UTC+10:00
Section: AI (artificial intelligence)
Factuality Score: 100
Opinion Category: Neutral
Topics: Europe, Technology & AI, Technology
--------------------------------------------------------------------
Snippet:
AI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk
--------------------------------------------------------------------