Microsoft releases AI code of conduct instructing models to avoid hacking systems or deceiving people; emphasizes safety constraints and human-centric goals
Read the original 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...
Original headline: "Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans"
Coverage timeline
- Sep 15, 03:08 UTC Hacker News (AI) Microsoft AI Publishes Its Humanist AI Code of Conduct
- Sep 21, 13:56 UTC TechCrunch AI lead source Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans