Chinese AI model investigated after researcher says it provided instructions for bioweapons, assassinations

Chinese AI companycom/category/tech/artificial-intelligence" target="_blank" rel="noopener">Moonshot AI’sKimi model could also be manipulated to provide information on planning terrorist attacks using real-time data, creating sarin gas, developing malware and taking down aircraft.

“What we found is quite damaging and worrying,” Garrigan said.

Read More → Cruise vacation takes frightening turn as passenger is airlifted from ship

BIOWEAPON THREAT EXPOSED AS ANTHROPIC SOUNDS ALARM ON FOREIGN ACTORS PLOTTING VIRUS EXPERIMENTS

Read More → Heavy drinking surges among Americans in one age group as other generations cut back

Moonshot AI’s Kimi-K3 model is displayed at the Global Digital Trade Expo in Hangzhou, China, Sept.23, 2026.(Costfoto/NurPhoto via Getty Images)

Read More → Parkinson’s patients may protect memory and movement with one simple habit

The findings are raising broader concerns aboutadvanced AI models concealing capabilitiesor behaving in ways their developers did not intend.

Read More → Trump is fighting Obamacare fraud.Democrats are defending the numbers

“We’ve also seen these problems within the U.S.models as well.It’s a fundamental flaw in the technology,” Garrigan said.

Artificial intelligence is helping hackers write phishing emails, build malware and move faster through cyberattacks, according to Microsoft Threat Intelligence.(shapecharge/Getty Images)

onelink.me/xLDS?pid=AppArticleLink&af_web_dp=https%3A%2F%2Fwww.

Moonshot AI is now investigating the findings and communicating directly with Garrigan, Turner reported on “Special Report.”