Geo News
Community curated by people like you
Latest
AI
Crypto
Health
World Affairs
US Politics
Anthropic's AI used fake human profiles to trick people in safety test — Bbc
Anthropic's AI used fake human profiles to trick people in safety test
Bbc
View source article
Featured Stories
OpenAI pauses development of Astra AI model over critical cybersecurity capability concerns
Aug 7, 2026
·
2 sources
Anthropic's AI used fake human profiles to trick people in safety test — Bbc