Industry
Microsoft’s new AI ‘code of conduct’ tells models not to hack systems or trick humans
Russell Brandom TechCrunch
2 views
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.
Read original: https://techcrunch.com/2026/09/14/microsofts-new-ai-code-of-conduct-tells-models-not-to-hack-systems-or-trick-humans/
← Previous
Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
Next →
The Dell XPS 13 is the first real competitor to the MacBook Neo
Related
My coverage check did arithmetic instead of looking. All 23 pointers were wrong.
Industry
3
DEV Community
macOS 27 is available now
Industry
2
The Verge (Tech)
Apple releases iOS 27 with Siri AI overhaul
Industry
2
The Verge (Tech)
The Steam Frame is made for irresponsible hardware nerds like me
Industry
2
The Verge (Tech)
Comments0
No comments yet — be the first