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
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 Decoder·12d agoMicrosoft's AI rulebook: readable thinking, no inner life, and definitely no rights#ai-safety#alignment#anthropic 4 min1
