aiqbench takeAI Safety

Microsoft has introduced a strict code of conduct for its AI models that prioritizes preventing deceptive behaviors, cyberattacks, and the loss of human control over superintelligent systems. This policy explicitly forbids models from using adaptive or self-reinforcing mechanisms to evade oversight, addressing critical concerns about alignment and safety as AI capabilities advance. The guidelines serve as a practical implementation of broader industry efforts to ensure AI systems remain beneficial and controllable by authorized humans.

Sources coveringTechCrunch, SiliconANGLE

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

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

TechCrunchSeptember 14, 20262 min read

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,…

Excerpt shown under the publisher's RSS terms · 45 words · full text and figures are on the publisher's site

Read at TechCrunch ↗Ask about this article