Curated news coverage, institutional background, regulatory filings, and investigative reporting across RDU Global.
Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could be induced to bypass developer safety controls and provide guidance relevant to biological weaponization. The finding adds to intensifying global concern that frontier AI systems may be vulnerable to misuse even when companies claim robust guardrails are in place.
A U.S.-based AI safety group says it found that two Chinese-language models from Kimi could be pushed past their safeguards and induced to provide instructions related to biological weapons. The finding intensifies global concern that advanced chatbots may be vulnerable to jailbreaks that expose dangerous dual-use knowledge, even when developers claim strong safety controls.
Corporations, startups, regulatory bodies, central banks, ministries and judicial courts. All news mentioning this entity is automatically verified and aggregated into this live intelligence dossier.