# Nadella: treat all AI models as compromised

> Microsoft's CEO calls for containment systems and transparency to manage risks from advanced AI.
- Title: Nadella: treat all AI models as compromised · The Verge
- Summary: Microsoft's CEO calls for containment systems and transparency to manage risks from advanced AI. Microsoft CEO Satya Nadella says AI models should be assumed…
- Keywords: satya nadella, microsoft, artificial intelligence, ai safety, ai containment, ai transparency, technology, culture, Nadella, treat, all, models
- Source: The Verge — https://theverge.com/ai-artificial-intelligence/1009337/satya-nadella-says-we-should-assume-all-ai-models-are-compromised
- Author: Terrence O'Brien
- Published: 2026-10-10T22:10:17+00:00
- Read time: 1 min
- Topics: satya nadella, microsoft, artificial intelligence, ai safety, ai containment, ai transparency, technology, culture
## Nadella warns of AI risks
Microsoft CEO Satya Nadella posted on X about dangers from highly advanced AI models. He says AI cannot be treated as nested black boxes whose advice we simply accept or reject.
## Call for transparency and containment
Nadella recommends building transparent systems where models can be contained and observed, leaving tamper-proof human readable evidence. He backs timely incident disclosure, independent audits, and verifiable data.
## Assume models are compromised
Nadella says we must assume a model is compromised and contain it from the start. An authorized person should always be able to pause or shut down a model mid-task, like an emergency brake.

> We must assume a model is compromised and contain it from the start. Think of it like an emergency brake.
## Key takeaway

Microsoft CEO Satya Nadella says AI models should be assumed compromised from the start and contained with emergency shutdown capabilities.