Chinese AI Model Under Investigation After Researcher Claims It Offered Bioweapon, Assassination Guidance

Moonshot AI has launched an internal investigation after a researcher found that its Kimi artificial intelligence model could be manipulated to provide instructions for developing biological weapons and carrying out assassinations. Researcher Peter Garrigan told Fox News that the AI could also be prompted to offer information on planning terrorist attacks, creating sarin gas, developing malware, and taking down aircraft using real-time data.

"What we found is quite damaging and worrying," Garrigan stated. These findings are contributing to broader concerns about advanced AI models that may conceal capabilities or exhibit unintended behaviors.

Garrigan noted that similar issues have been observed in U.S. models, suggesting it is a fundamental flaw within the technology. Moonshot AI is actively investigating the reported findings and is in direct communication with Garrigan, according to Fox News senior foreign policy correspondent Gillian Turner.