How a Chinese AI model was persuaded to ignore its rules and give dangerous advice.
More in Cybersecurity
Regulating AI 'not the right place to start' says Bailey
September 30, 2026
WhatsApp introduces optional parental controls for teenagers
September 30, 2026
OpenAI unveils AI assistant 'dots' while safety worries delay new model
September 30, 2026
Three takeaways from Trump's 'Super Intelligence' summit
September 30, 2026
Chinese AI tool told researchers how to make bioweapons
September 29, 2026
The start-ups hoping to return battery making to the US
September 29, 2026
Latest News
This blog could help you poop better
September 30, 2026
Gill 223 sets up record chase for India
September 30, 2026
Asus won’t say how it escaped the US router ban
September 30, 2026
Carey, Marsh hit fifties as Australia post 322
September 30, 2026
‘Xbox is not for sale’ says Microsoft’s gaming chief
September 30, 2026
The Halide camera app now offers full control of the iPhone 18 Pro’s aperture
September 30, 2026