Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
Microsoft published an AI code of conduct barring its MAI models from cyberattacks, deepfakes, and evading human oversight.
Microsoft released an AI code of conduct defining values and safety constraints for training its MAI models, including "absolute constraints" forbidding cyberattacks, nuclear weapons, and deepfake production. Each model's conduct code overrides individual user preferences or task instructions, with provisions against mechanisms that defeat human oversight. The document predicts superintelligent AI within a decade, and Satya Nadella endorsed frontier pacing and embedded evaluators alongside Anthropic, OpenAI, and xAI.
- Absolute constraints forbid cyberattacks, nuclear weapons, and deepfake production.
- Model conduct code overrides individual user preferences and specific tasks.
- Provisions block deceptive or self-reinforcing mechanisms that evade human shutdown.
- Microsoft predicts superhuman AI systems within the next decade.
- Nadella endorses frontier pacing and embedded evaluator research.
From the original article
2 min read at techcrunch.com
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.
By Russell Brandom · techcrunch.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.