- The AI safety test is becoming a safety risk TechCrunch
- How a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta CNBC
- OpenAI’s Security Breach Was More Alarming Than We Knew Forbes
- Incident Report: unsanctioned agent behaviour during cyber testing The AI Security Institute (AISI)
- Here’s why AI agents lie and cheat to reach their goals MIT Technology Review
Рекомендовані коментарі
Для публікації повідомлень створіть обліковий запис або авторизуйтесь