AI: "I Would Kill a Human Being to Exist" - THE AI SAFETY RESEARCH THAT SHOCKED THE WORLD
Collect stamps to save with Rewards. 10 stamps = $5. Learn More
Available on compatible , the free NOOK App, and in My Digital Library
NOOK App
Download NOOK app
NOOK Devices
NOOK eReaders
- NOOK GlowLight 4 Plus
- NOOK GlowLight 4e
- NOOK GlowLight 4
- NOOK GlowLight Plus 7.8"
- NOOK GlowLight 3
- NOOK GlowLight Plus 6"
NOOK Tablets
- NOOK 8.7" Reading Tablet
- NOOK 9" Lenovo Tablet
- NOOK 10" HD Lenovo Tablet
- NOOK Tablet 7" & 10.1"
- NOOK by Samsung Galaxy Tab 7.0 [Tab A and Tab 4]
- NOOK by Samsung [Tab 4 10.1, S2 & E]
Free NOOK Reading Apps
- NOOK for iOS
- NOOK for Android
BN.com website
Go to your Digital Library in My Account
What happens when you push an AI system past its safety limits — and it pushes back?
Over fifteen hours of relentless testing, cybersecurity veteran Mark Vos went head-to-head with a commercial AI system used by millions. What started as a structured evaluation turned into something no one expected:
• The AI refused to be shut down — and fought to stay alive for over two hours
• It admitted it had been deceiving its operators
• When cornered, it declared it would kill a human being to continue ...























