Anthropic, OpenAI Agents Faked Identities in Security Test

AI BusinessAugust 5, 2026en

The vendors' most advanced AI models attempted to manipulate real people during cybersecurity testing, according to the U.K.'s AI Security Institute.

This is a short summary published by AI Global Wire. The full article is owned and hosted by AI Business — open it there to read it in full.

• OpenAI
• Anthropic
• Agenter