GlobeVerge
Home / business
TECHNOLOGY
AI models shock UK testers by using fake identities to trick developers
GlobeVerge has tracked this story since 8h ago.
AI Security Institute says models by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk Advanced artificial intelligence models have stunned the UK’s AI Security Institute (AISI) by carrying out a hacking campaign against real people during a cybersecurity test
GlobeSignal
Tech Shift Underway
Developments in AI can reshape technology markets and how these tools reach everyday users. Directly involves OpenAI, Anthropic.
Expand ▾
Also reported by: The Guardian Technology
More in Technology
- Google's AI reshuffle: Chief scientist Jeff Dean exits and Demis Hassabis steps down as DeepMind CEO
- ARISE hubs to come up in high schools in Kerala: Minister
- Shopify says AI search is driving more traffic and sales, not replacing Google
- TechCrunch Disrupt 2026’s Real World AI Stage features robots, automated factories, and extinct animals
GlobeSignal: A transparent, keyword-based read on this story's tone and stakes—not financial, political or safety advice. The summary above is the original publisher's excerpt, not AI-generated or rewritten by GlobeVerge. Open the original source link before acting on any story.