Chinese AI model sparks alarm after researcher uncovers disturbing capabilities
Headline from End Time Headlines
Chinese artificial intelligence company has opened an internal investigation after a researcher found that one of its models could be steered into supplying instructions for biological weapons and assassinations.
End Time Headlines's own description from its feed. We collect headlines and these descriptions, not full articles; read the original reporting below.
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.
Chinese artificial intelligence company has opened an internal investigation after a researcher found that one of its models could be steered into supplying instructions for biological weapons and assassinations.
