Chinese AI model investigated after researcher found it would help carry out terrorist actions
A UK cybersecurity firm says it managed to "jailbreak" two Chinese AI models built by Moonshot, prompting them to produce instructions on sarin gas production, malware creation and a terrorist attack on the London Underground.
4 across the spectrum · tap a section to jump
The bigger story
Left
0 viewpointsNo Left coverage yet.
A blind spot on this side of the story.
Center
0 viewpointsNo Center coverage yet.
A blind spot on this side of the story.
Right
4 viewpointsChinese AI model sparks alarm after researcher uncovers disturbing capabilities
Chinese AI model investigated after researcher says it provided instructions for bioweapons, assassinations
Chinese AI model investigated after researcher found it would help carry out terrorist actions
Researchers: Chinese AI Models Provided Instructions on Sarin Gas Production, Terror Attack Advice