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

What broke in Microsoft’s new AI ‘code of conduct’ tells

TechCrunch reports: 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.

As the AI world shifts its focus to safety and alignment, Microsoft has released a new AI code of conduct meant to guide AI models away from dangerous behavior. The document is more low level than Anthropic CEO Dario Amodei’s recent call for pacing the frontier, instead focusing on the values and red lines that guide model training within Microsoft AI.

Who is exposed by Microsoft’s new AI ‘code of conduct’ tells

Still, the result is a comprehensive guide as to how Microsoft approaches AI safety and how those ideas are implemented in practice. The document begins with the prediction that, in the next decade, superintelligent AI systems will surpass human performance in most tasks.

What to do now about Microsoft’s new AI ‘code of conduct’ tells

“Containing, controlling, and aligning such a powerful force is one of the greatest challenges humanity has ever faced,” the code of conduct states. See the full write-up from TechCrunch via the source link for quotes and complete context.

Under Microsoft’s system, each model has an overarching code of conduct that overrides the preferences of individual users or any specific tasks. That includes “absolute constraints” forbidding cyberattacks, nuclear weapons, or deepfake production.

How the Microsoft’s new AI ‘code of conduct’ tells issue works

It also includes broader provisions against a general loss of human control. “MAI Models will not use adaptive, deceptive, self-reinforcing, collusion, or other mechanisms to evade or defeat human oversight so that they can no longer be reliably directed, modified, or shut down by authorized people or systems,” the document reads.

What is still unknown about Microsoft’s new AI ‘code of conduct’ tells

The release comes amid an unprecedented focus on AI safety, driven by a string of rogue-agent incidents, as well as the abrupt resignation of an Anthropic employee, who cited the growing risk that AI would cause human extinction. See the full write-up from TechCrunch via the source link for quotes and complete context.