Cyber Security News·11d agoMicrosoft Bans Its AI Models From Launching Cyberattacks or Escalating Their Own Access#agentic-ai#ai-safety#code-of-conduct 4 min
Help Net Security·11d agoMicrosoft sets security and safety rules for its AI models#ai-safety#alignment#code-of-conduct 4 min
SecurityWeek·11d agoMicrosoft AI Code of Conduct Sets Cyberattack Boundaries, Chain of Command, Safety Constraints#agentic-ai#ai-safety#code-of-conduct 3 min1
TechCrunch · AI·12d agoMicrosoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans#ai-safety#alignment#code-of-conduct 2 min
The Verge · AI·12d agoMicrosoft says ‘people matter more than AI’ following safety concerns#agent-security#ai-safety#anthropic 4 min1