中国人工智能公司月之暗面已启动内部调查。此前，研究人员发现，其一款模型可被操纵，提供开发生物武器和实施暗杀的指令。福克斯新闻高级外交政策记者吉莉安·特纳于周四报道称了这一情况。
Chinese AI company Moonshot AI has launched an internal investigation after a researcher found that one of its models could be manipulated into providing instructions for developing biological weapons and carrying out assassinations, Fox News senior foreign policy correspondent Gillian Turner reported Thursday.
研究人员彼得·加里根告诉福克斯新闻，月之暗面的 Kimi 模型还可被操纵，提供有关利用实时数据策划恐怖袭击、制造沙林毒气、开发恶意软件以及击落飞机的信息。“我们的发现相当具有破坏性，也令人担忧。”加里根说。
Researcher Peter Garrigan told Fox News that Moonshot AI's Kimi 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.
生物武器威胁曝光之际，Anthropic 就境外行为体策划病毒实验发出警报。这些发现引发了更广泛的担忧：先进人工智能模型可能隐瞒自身能力，或表现出开发者未曾预期的行为。
BIOWEAPON THREAT EXPOSED AS ANTHROPIC SOUNDS ALARM ON FOREIGN ACTORS PLOTTING VIRUS EXPERIMENTS The findings are raising broader concerns about advanced AI models concealing capabilities or behaving in ways their developers did not intend.
“我们也在美国模型中看到了这些问题。这是这项技术的一项根本缺陷。”加里根说。
"We've also seen these problems within the U.S. models as well. It's a fundamental flaw in the technology," Garrigan said.
特纳在《特别报道》中报道称，月之暗面目前正在调查这些发现，并与加里根直接沟通。
Moonshot AI is now investigating the findings and communicating directly with Garrigan, Turner reported on "Special Report."