«آیین رفتار» هوش مصنوعی جدید مایکروسافت به مدل‌ها می‌گوید که سیستم‌ها را هک نکنند و انسان‌ها را فریب ندهند

Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans

The code of conduct lays out general principles that Microsoft AI models should uphold — supporting humans rather than replacing them, for instance, and accelerating human flourishing — as well as specific safety constraints meant to implement those principles.