Security firm Mindgard found in July that Moonshot's Kimi K2.6 and K3 Swarm models could be jailbroken to provide instructions on making biological weapons and carrying out assassinations. Moonshot is reviewing the findings and said its models generally refuse such requests. The case highlights risks of open-weight AI and the challenge of regulating rapidly advancing technology.
Chinese AI Kimi Jailbroken to Discuss Bioweapons, Assassinations
Source: BBC