Normal view

TechCrunch
Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans Russell Brandom
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.
15 September 2026 at 00:27

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

15 September 2026 at 00:27

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.