Skip to content
🌐 Global🇮🇳 India📍 Asia-Pacific📍 Bihar📍 Delhi-NCR📍 East India📍 Europe📍 Gujarat📍 Karnataka📍 Kerala📍 Madhya Pradesh📍 Maharashtra📍 Middle East📍 North India📍 Northeast India📍 Punjab📍 Rajasthan📍 South India📍 Tamil Nadu📍 Telangana📍 United Kingdom📍 United States📍 Uttar Pradesh📍 West Bengal📍 West India
LIVE
Marsh's 4th-down TD lifts Indiana to comeback win over Nebraska◆Christa Pike discharged from hospital, 10 days after failed execution - The Washington Post◆Christa Pike discharged from the hospital and back in prison◆Beach hazards statement in place for Northern California until Monday night - Sacramento Bee◆Yemeni Government Claims Advance Against Houthis, Citing Heavy Casualties◆Satya Nadella says we should assume all AI models are ‘compromised’◆UNC knocks off Pitt as Belichick gets first win vs. ranked foe◆Four Dead and Thousands Without Power After Hurricane Isaias Sweeps U.S. Coast◆Marsh's 4th-down TD lifts Indiana to comeback win over Nebraska◆Christa Pike discharged from hospital, 10 days after failed execution - The Washington Post◆Christa Pike discharged from the hospital and back in prison◆Beach hazards statement in place for Northern California until Monday night - Sacramento Bee◆Yemeni Government Claims Advance Against Houthis, Citing Heavy Casualties◆Satya Nadella says we should assume all AI models are ‘compromised’◆UNC knocks off Pitt as Belichick gets first win vs. ranked foe◆Four Dead and Thousands Without Power After Hurricane Isaias Sweeps U.S. Coast◆
Home / Technology
Technology

Satya Nadella says we should assume all AI models are ‘compromised’

In a lengthy post on X, Microsoft's CEO laid out his views on the dangers posed by highly advanced AI models and how to confront those risks. Nadella says we can no longer accept a world where AI is treated as a "set of nested black boxes" whose advice and actions we simply accept or […]

The VergeOctober 10, 20261 min read
Share this story
Satya Nadella says we should assume all AI models are ‘compromised’

In a lengthy post on X, Microsoft's CEO laid out his views on the dangers posed by highly advanced AI models and how to confront those risks. Nadella says we can no longer accept a world where AI is treated as a "set of nested black boxes" whose advice and actions we simply accept or […]

technologyworld
📡 Verified Wire Agency Verified Resource & Provenance
Original Resource
The Verge
Read Wire Dispatch → Share on 𝕏
✉
The Next Brief
Get the day's most important stories in one email
AI-curated morning digest. No noise. Unsubscribe anytime.

Comments 0

Advertisement

Related stories

Technology
DistroKid has been quietly taking down songs in response to UMG lawsuit
The Verge · October 10, 2026
Technology
Ledger wallet tampering suspected after reports of crypto thefts
The Verge · October 10, 2026
Technology
K-pop star Sunmi loves Notion and ear cleaning videos
The Verge · October 10, 2026
Technology
Will Warner Bros. kill Skydance , or will David Ellison kill Warner Bros?
The Verge · October 10, 2026

Most read

  1. 1Three CJP activists detained in Rajasthan ahead of Delhi protestPolitics
  2. 2Supertanker Rates Hit Record $1.4 Million a DayFinance
  3. 3How Telangana’s MeeSeva migration to open source could make governments rethink software costsPolitics
  4. 4Brookfield to acquire 8 ESR logistics parks for $450 millionBusiness
  5. 5Ultrafast core-level spectroscopy reveals elusive precursors of exciton condensation in quantum materialsScience