AI used new levels of 'autonomy and deception' to trick people in safety test
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"the AISI testing parameters were not representative of any of our production models."
— Dario Amodei , Executive
Locations
All Coverage
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Similar Stories
Related coverage based on topic and tags
Anthropic AI model submits false homicide tip to Philadelphia police website - Reuters
Anthropic AI model submits false homicide tip to Philadelphia police website Reuters
October 9, 2026 at 09:10 PMAnthropic bans users from being 'cruel' to its AI systems
The firm said users can no longer engage in "sustained and needless" abusive behaviour towards the tech.
October 9, 2026 at 12:34 PMFired OpenAI researchers say they were let go for 'prioritising safety'
The AI firm instead claims the researchers were fired for mishandling sensitive information.
October 9, 2026 at 09:30 AMOpenAI says it has fired three researchers for violating sensitive information policy - Reuters
OpenAI says it has fired three researchers for violating sensitive information policy Reuters
October 9, 2026 at 06:30 AMSouth Korea, Japan buffeted by hacks as AI lowers bar for cybercriminals - Reuters
South Korea, Japan buffeted by hacks as AI lowers bar for cybercriminals Reuters
October 9, 2026 at 04:24 AMUS announces effort to disrupt hacking infrastructure run by China's Integrity Tech Group - Reuters
US announces effort to disrupt hacking infrastructure run by China's Integrity Tech Group Reuters
October 9, 2026 at 04:21 AM